stm32: Add CMSIS/STD Libraries for:

F0, F1, F2, F30x/31x, F37x, F4, L1, W1

Also add CPAL and USB_FS drivers.

.gitattributes

@@ -0,0 +1 @@
+*.tar.* filter=lfs diff=lfs merge=lfs -text

libs/CMSIS/DSP_Lib/Examples/Common/Include/math_helper.h

@@ -0,0 +1,53 @@
+/* ----------------------------------------------------------------------
+* Copyright (C) 2010 ARM Limited. All rights reserved.  
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3  
+*  
+* Project: 	    CMSIS DSP Library 
+*
+* Title:	    math_helper.h
+* 
+*
+* Description:	Prototypes of all helper functions required.  
+*
+* Target Processor: Cortex-M4/Cortex-M3
+*  
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation.  
+*   
+* Version 1.0.2 2010/11/11  
+*    Documentation updated.   
+*  
+* Version 1.0.1 2010/10/05   
+*    Production release and review comments incorporated.  
+*  
+* Version 1.0.0 2010/09/20   
+*    Production release and review comments incorporated.  
+*  
+* Version 0.0.7  2010/06/10   
+*    Misra-C changes done 
+* -------------------------------------------------------------------- */
+
+
+#include "arm_math.h"
+
+#ifndef MATH_HELPER_H
+#define MATH_HELPER_H
+
+float arm_snr_f32(float *pRef, float *pTest,  uint32_t buffSize);  
+void arm_float_to_q12_20(float *pIn, q31_t * pOut, uint32_t numSamples);
+void arm_provide_guard_bits_q15(q15_t *input_buf, uint32_t blockSize, uint32_t guard_bits);
+void arm_provide_guard_bits_q31(q31_t *input_buf, uint32_t blockSize, uint32_t guard_bits);
+void arm_float_to_q14(float *pIn, q15_t *pOut, uint32_t numSamples);
+void arm_float_to_q29(float *pIn, q31_t *pOut, uint32_t numSamples);
+void arm_float_to_q28(float *pIn, q31_t *pOut, uint32_t numSamples);
+void arm_float_to_q30(float *pIn, q31_t *pOut, uint32_t numSamples);
+void arm_clip_f32(float *pIn, uint32_t numSamples);
+uint32_t arm_calc_guard_bits(uint32_t num_adds);
+void arm_apply_guard_bits (float32_t * pIn, uint32_t numSamples, uint32_t guard_bits);
+uint32_t arm_compare_fixed_q15(q15_t *pIn, q15_t * pOut, uint32_t numSamples);
+uint32_t arm_compare_fixed_q31(q31_t *pIn, q31_t *pOut, uint32_t numSamples);
+uint32_t arm_calc_2pow(uint32_t guard_bits);
+#endif
+

libs/CMSIS/DSP_Lib/Examples/Common/Source/math_helper.c

@@ -0,0 +1,447 @@
+/* ----------------------------------------------------------------------
+* Copyright (C) 2010 ARM Limited. All rights reserved.  
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3  
+*  
+* Project: 	    CMSIS DSP Library 
+*
+* Title:	    math_helper.c
+*
+* Description:	Definition of all helper functions required.  
+*  
+* Target Processor: Cortex-M4/Cortex-M3
+*  
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation.  
+*   
+* Version 1.0.2 2010/11/11  
+*    Documentation updated.   
+*  
+* Version 1.0.1 2010/10/05   
+*    Production release and review comments incorporated.  
+*  
+* Version 1.0.0 2010/09/20   
+*    Production release and review comments incorporated.  
+*  
+* Version 0.0.7  2010/06/10   
+*    Misra-C changes done 
+* -------------------------------------------------------------------- */
+
+/* ----------------------------------------------------------------------
+*		Include standard header files  
+* -------------------------------------------------------------------- */
+#include<math.h>
+
+/* ----------------------------------------------------------------------
+*		Include project header files  
+* -------------------------------------------------------------------- */
+#include "math_helper.h"
+
+/** 
+ * @brief  Caluclation of SNR
+ * @param  float* 	Pointer to the reference buffer
+ * @param  float*	Pointer to the test buffer
+ * @param  uint32_t	total number of samples
+ * @return float	SNR
+ * The function Caluclates signal to noise ratio for the reference output 
+ * and test output 
+ */
+
+float arm_snr_f32(float *pRef, float *pTest, uint32_t buffSize)
+{
+  float EnergySignal = 0.0, EnergyError = 0.0;
+  uint32_t i;
+  float SNR;
+  int temp;
+  int *test;
+
+  for (i = 0; i < buffSize; i++)
+    {
+ 	  /* Checking for a NAN value in pRef array */
+	  test =   (int *)(&pRef[i]);
+      temp =  *test;
+
+	  if(temp == 0x7FC00000)
+	  {
+	  		return(0);
+	  }
+
+	  /* Checking for a NAN value in pTest array */
+	  test =   (int *)(&pTest[i]);
+      temp =  *test;
+
+	  if(temp == 0x7FC00000)
+	  {
+	  		return(0);
+	  }
+      EnergySignal += pRef[i] * pRef[i];
+      EnergyError += (pRef[i] - pTest[i]) * (pRef[i] - pTest[i]); 
+    }
+
+	/* Checking for a NAN value in EnergyError */
+	test =   (int *)(&EnergyError);
+    temp =  *test;
+
+    if(temp == 0x7FC00000)
+    {
+  		return(0);
+    }
+	
+
+  SNR = 10 * log10 (EnergySignal / EnergyError);
+
+  return (SNR);
+
+}
+
+
+/** 
+ * @brief  Provide guard bits for Input buffer
+ * @param  q15_t* 	    Pointer to input buffer
+ * @param  uint32_t 	blockSize
+ * @param  uint32_t 	guard_bits
+ * @return none
+ * The function Provides the guard bits for the buffer 
+ * to avoid overflow 
+ */
+
+void arm_provide_guard_bits_q15 (q15_t * input_buf, uint32_t blockSize,
+                            uint32_t guard_bits)
+{
+  uint32_t i;
+
+  for (i = 0; i < blockSize; i++)
+    {
+      input_buf[i] = input_buf[i] >> guard_bits;
+    }
+}
+
+/** 
+ * @brief  Converts float to fixed in q12.20 format
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none
+ * The function converts floating point values to fixed point(q12.20) values 
+ */
+
+void arm_float_to_q12_20(float *pIn, q31_t * pOut, uint32_t numSamples)
+{
+  uint32_t i;
+
+  for (i = 0; i < numSamples; i++)
+    {
+	  /* 1048576.0f corresponds to pow(2, 20) */
+      pOut[i] = (q31_t) (pIn[i] * 1048576.0f);
+
+      pOut[i] += pIn[i] > 0 ? 0.5 : -0.5;
+
+      if (pIn[i] == (float) 1.0)
+        {
+          pOut[i] = 0x000FFFFF;
+        }
+    }
+}
+
+/** 
+ * @brief  Compare MATLAB Reference Output and ARM Test output
+ * @param  q15_t* 	Pointer to Ref buffer
+ * @param  q15_t* 	Pointer to Test buffer
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none 
+ */
+
+uint32_t arm_compare_fixed_q15(q15_t *pIn, q15_t * pOut, uint32_t numSamples)
+{
+  uint32_t i; 
+  int32_t diff, diffCrnt = 0;
+  uint32_t maxDiff = 0;
+
+  for (i = 0; i < numSamples; i++)
+  {
+  	diff = pIn[i] - pOut[i];
+  	diffCrnt = (diff > 0) ? diff : -diff;
+
+	if(diffCrnt > maxDiff)
+	{
+		maxDiff = diffCrnt;
+	}	
+  }
+
+  return(maxDiff);
+}
+
+/** 
+ * @brief  Compare MATLAB Reference Output and ARM Test output
+ * @param  q31_t* 	Pointer to Ref buffer
+ * @param  q31_t* 	Pointer to Test buffer
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none 
+ */
+
+uint32_t arm_compare_fixed_q31(q31_t *pIn, q31_t * pOut, uint32_t numSamples)
+{
+  uint32_t i; 
+  int32_t diff, diffCrnt = 0;
+  uint32_t maxDiff = 0;
+
+  for (i = 0; i < numSamples; i++)
+  {
+  	diff = pIn[i] - pOut[i];
+  	diffCrnt = (diff > 0) ? diff : -diff;
+
+	if(diffCrnt > maxDiff)
+	{
+		maxDiff = diffCrnt;
+	}
+  }
+
+  return(maxDiff);
+}
+
+/** 
+ * @brief  Provide guard bits for Input buffer
+ * @param  q31_t* 	Pointer to input buffer
+ * @param  uint32_t 	blockSize
+ * @param  uint32_t 	guard_bits
+ * @return none
+ * The function Provides the guard bits for the buffer 
+ * to avoid overflow 
+ */
+
+void arm_provide_guard_bits_q31 (q31_t * input_buf, 
+								 uint32_t blockSize,
+                                 uint32_t guard_bits)
+{
+  uint32_t i;
+
+  for (i = 0; i < blockSize; i++)
+    {
+      input_buf[i] = input_buf[i] >> guard_bits;
+    }
+}
+
+/** 
+ * @brief  Provide guard bits for Input buffer
+ * @param  q31_t* 	Pointer to input buffer
+ * @param  uint32_t 	blockSize
+ * @param  uint32_t 	guard_bits
+ * @return none
+ * The function Provides the guard bits for the buffer 
+ * to avoid overflow 
+ */
+
+void arm_provide_guard_bits_q7 (q7_t * input_buf, 
+								uint32_t blockSize,
+                                uint32_t guard_bits)
+{
+  uint32_t i;
+
+  for (i = 0; i < blockSize; i++)
+    {
+      input_buf[i] = input_buf[i] >> guard_bits;
+    }
+}
+
+
+
+/** 
+ * @brief  Caluclates number of guard bits 
+ * @param  uint32_t 	number of additions
+ * @return none
+ * The function Caluclates the number of guard bits  
+ * depending on the numtaps 
+ */
+
+uint32_t arm_calc_guard_bits (uint32_t num_adds)
+{
+  uint32_t i = 1, j = 0;
+
+  if (num_adds == 1)
+    {
+      return (0);
+    }
+
+  while (i < num_adds)
+    {
+      i = i * 2;
+      j++;
+    }
+
+  return (j);
+}
+
+/** 
+ * @brief  Converts Q15 to floating-point
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none
+ */
+
+void arm_apply_guard_bits (float32_t * pIn, 
+						   uint32_t numSamples, 
+						   uint32_t guard_bits)
+{
+  uint32_t i;
+
+  for (i = 0; i < numSamples; i++)
+    {
+      pIn[i] = pIn[i] * arm_calc_2pow(guard_bits);
+    }
+}
+
+/** 
+ * @brief  Calculates pow(2, numShifts)
+ * @param  uint32_t 	number of shifts
+ * @return pow(2, numShifts)
+ */
+uint32_t arm_calc_2pow(uint32_t numShifts)
+{
+
+  uint32_t i, val = 1;
+
+  for (i = 0; i < numShifts; i++)
+    {
+      val = val * 2;
+    }	
+
+  return(val);
+}
+
+
+
+/** 
+ * @brief  Converts float to fixed q14 
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none
+ * The function converts floating point values to fixed point values 
+ */
+
+void arm_float_to_q14 (float *pIn, q15_t * pOut, 
+                       uint32_t numSamples)
+{
+  uint32_t i;
+
+  for (i = 0; i < numSamples; i++)
+    {
+	  /* 16384.0f corresponds to pow(2, 14) */
+      pOut[i] = (q15_t) (pIn[i] * 16384.0f);
+
+      pOut[i] += pIn[i] > 0 ? 0.5 : -0.5;
+
+      if (pIn[i] == (float) 2.0)
+        {
+          pOut[i] = 0x7FFF;
+        }
+
+    }
+
+}
+
+ 
+/** 
+ * @brief  Converts float to fixed q30 format
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none
+ * The function converts floating point values to fixed point values 
+ */
+
+void arm_float_to_q30 (float *pIn, q31_t * pOut, 
+					   uint32_t numSamples)
+{
+  uint32_t i;
+
+  for (i = 0; i < numSamples; i++)
+    {
+	  /* 1073741824.0f corresponds to pow(2, 30) */
+      pOut[i] = (q31_t) (pIn[i] * 1073741824.0f);
+
+      pOut[i] += pIn[i] > 0 ? 0.5 : -0.5;
+
+      if (pIn[i] == (float) 2.0)
+        {
+          pOut[i] = 0x7FFFFFFF;
+        }
+    }
+}
+
+/** 
+ * @brief  Converts float to fixed q30 format
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none
+ * The function converts floating point values to fixed point values 
+ */
+
+void arm_float_to_q29 (float *pIn, q31_t * pOut, 
+					   uint32_t numSamples)
+{
+  uint32_t i;
+
+  for (i = 0; i < numSamples; i++)
+    {
+	  /* 1073741824.0f corresponds to pow(2, 30) */
+      pOut[i] = (q31_t) (pIn[i] * 536870912.0f);
+
+      pOut[i] += pIn[i] > 0 ? 0.5 : -0.5;
+
+      if (pIn[i] == (float) 4.0)
+        {
+          pOut[i] = 0x7FFFFFFF;
+        }
+    }
+}
+
+
+/** 
+ * @brief  Converts float to fixed q28 format
+ * @param  uint32_t 	number of samples in the buffer
+ * @return none
+ * The function converts floating point values to fixed point values 
+ */
+
+void arm_float_to_q28 (float *pIn, q31_t * pOut, 
+                       uint32_t numSamples)
+{
+  uint32_t i;
+
+  for (i = 0; i < numSamples; i++)
+    {
+	/* 268435456.0f corresponds to pow(2, 28) */
+      pOut[i] = (q31_t) (pIn[i] * 268435456.0f);
+
+      pOut[i] += pIn[i] > 0 ? 0.5 : -0.5;
+
+      if (pIn[i] == (float) 8.0)
+        {
+          pOut[i] = 0x7FFFFFFF;
+        }
+    }
+}
+
+/** 
+ * @brief  Clip the float values to +/- 1 
+ * @param  pIn 	input buffer
+ * @param  numSamples 	number of samples in the buffer
+ * @return none
+ * The function converts floating point values to fixed point values 
+ */
+
+void arm_clip_f32 (float *pIn, uint32_t numSamples)
+{
+  uint32_t i;
+
+  for (i = 0; i < numSamples; i++)
+    {
+      if(pIn[i] > 1.0f)
+	  {
+	    pIn[i] = 1.0;
+	  }
+	  else if( pIn[i] < -1.0f)
+	  {
+	    pIn[i] = -1.0;
+	  }
+	       
+    }
+}
+
+
+
+

libs/CMSIS/DSP_Lib/Examples/Common/system_ARMCM0.c

@@ -0,0 +1,66 @@
+/**************************************************************************//**
+ * @file     system_ARMCM0.c
+ * @brief    CMSIS Device System Source File for
+ *           ARMCM0 Device Series
+ * @version  V1.07
+ * @date     30. January 2012
+ *
+ * @note
+ * Copyright (C) 2012 ARM Limited. All rights reserved.
+ *
+ * @par
+ * ARM Limited (ARM) is supplying this software for use with Cortex-M 
+ * processor based microcontrollers.  This file can be freely distributed 
+ * within development tools that are supporting such ARM based processors. 
+ *
+ * @par
+ * THIS SOFTWARE IS PROVIDED "AS IS".  NO WARRANTIES, WHETHER EXPRESS, IMPLIED
+ * OR STATUTORY, INCLUDING, BUT NOT LIMITED TO, IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE APPLY TO THIS SOFTWARE.
+ * ARM SHALL NOT, IN ANY CIRCUMSTANCES, BE LIABLE FOR SPECIAL, INCIDENTAL, OR
+ * CONSEQUENTIAL DAMAGES, FOR ANY REASON WHATSOEVER.
+ *
+ ******************************************************************************/
+
+#include "ARMCM0.h"
+
+/*----------------------------------------------------------------------------
+  Define clocks
+ *----------------------------------------------------------------------------*/
+#define __HSI             ( 8000000UL)
+#define __XTAL            ( 5000000UL)    /* Oscillator frequency             */
+
+#define __SYSTEM_CLOCK    (5*__XTAL)
+
+
+/*----------------------------------------------------------------------------
+  Clock Variable definitions
+ *----------------------------------------------------------------------------*/
+uint32_t SystemCoreClock = __SYSTEM_CLOCK;/*!< System Clock Frequency (Core Clock)*/
+
+
+/*----------------------------------------------------------------------------
+  Clock functions
+ *----------------------------------------------------------------------------*/
+void SystemCoreClockUpdate (void)            /* Get Core Clock Frequency      */
+{
+
+  SystemCoreClock = __SYSTEM_CLOCK;
+
+}
+
+/**
+ * Initialize the system
+ *
+ * @param  none
+ * @return none
+ *
+ * @brief  Setup the microcontroller system.
+ *         Initialize the System.
+ */
+void SystemInit (void)
+{
+
+  SystemCoreClock = __SYSTEM_CLOCK;
+
+}

libs/CMSIS/DSP_Lib/Examples/Common/system_ARMCM3.c

@@ -0,0 +1,66 @@
+/**************************************************************************//**
+ * @file     system_ARMCM3.c
+ * @brief    CMSIS Device System Source File for
+ *           ARMCM3 Device Series
+ * @version  V1.07
+ * @date     30. January 2012
+ *
+ * @note
+ * Copyright (C) 2012 ARM Limited. All rights reserved.
+ *
+ * @par
+ * ARM Limited (ARM) is supplying this software for use with Cortex-M 
+ * processor based microcontrollers.  This file can be freely distributed 
+ * within development tools that are supporting such ARM based processors. 
+ *
+ * @par
+ * THIS SOFTWARE IS PROVIDED "AS IS".  NO WARRANTIES, WHETHER EXPRESS, IMPLIED
+ * OR STATUTORY, INCLUDING, BUT NOT LIMITED TO, IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE APPLY TO THIS SOFTWARE.
+ * ARM SHALL NOT, IN ANY CIRCUMSTANCES, BE LIABLE FOR SPECIAL, INCIDENTAL, OR
+ * CONSEQUENTIAL DAMAGES, FOR ANY REASON WHATSOEVER.
+ *
+ ******************************************************************************/
+
+#include "ARMCM3.h"
+
+/*----------------------------------------------------------------------------
+  Define clocks
+ *----------------------------------------------------------------------------*/
+#define __HSI             ( 8000000UL)
+#define __XTAL            ( 5000000UL)    /* Oscillator frequency             */
+
+#define __SYSTEM_CLOCK    (5*__XTAL)
+
+
+/*----------------------------------------------------------------------------
+  Clock Variable definitions
+ *----------------------------------------------------------------------------*/
+uint32_t SystemCoreClock = __SYSTEM_CLOCK;/*!< System Clock Frequency (Core Clock)*/
+
+
+/*----------------------------------------------------------------------------
+  Clock functions
+ *----------------------------------------------------------------------------*/
+void SystemCoreClockUpdate (void)            /* Get Core Clock Frequency      */
+{
+
+  SystemCoreClock = __SYSTEM_CLOCK;
+
+}
+
+/**
+ * Initialize the system
+ *
+ * @param  none
+ * @return none
+ *
+ * @brief  Setup the microcontroller system.
+ *         Initialize the System.
+ */
+void SystemInit (void)
+{
+
+  SystemCoreClock = __SYSTEM_CLOCK;
+
+}

libs/CMSIS/DSP_Lib/Examples/Common/system_ARMCM4.c

@@ -0,0 +1,70 @@
+/**************************************************************************//**
+ * @file     system_ARMCM4.c
+ * @brief    CMSIS Device System Source File for
+ *           ARMCM4 Device Series
+ * @version  V1.07
+ * @date     30. January 2012
+ *
+ * @note
+ * Copyright (C) 2012 ARM Limited. All rights reserved.
+ *
+ * @par
+ * ARM Limited (ARM) is supplying this software for use with Cortex-M 
+ * processor based microcontrollers.  This file can be freely distributed 
+ * within development tools that are supporting such ARM based processors. 
+ *
+ * @par
+ * THIS SOFTWARE IS PROVIDED "AS IS".  NO WARRANTIES, WHETHER EXPRESS, IMPLIED
+ * OR STATUTORY, INCLUDING, BUT NOT LIMITED TO, IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE APPLY TO THIS SOFTWARE.
+ * ARM SHALL NOT, IN ANY CIRCUMSTANCES, BE LIABLE FOR SPECIAL, INCIDENTAL, OR
+ * CONSEQUENTIAL DAMAGES, FOR ANY REASON WHATSOEVER.
+ *
+ ******************************************************************************/
+
+#include "ARMCM4.h"
+
+/*----------------------------------------------------------------------------
+  Define clocks
+ *----------------------------------------------------------------------------*/
+#define __HSI             ( 8000000UL)
+#define __XTAL            ( 5000000UL)    /* Oscillator frequency             */
+
+#define __SYSTEM_CLOCK    (5*__XTAL)
+
+
+/*----------------------------------------------------------------------------
+  Clock Variable definitions
+ *----------------------------------------------------------------------------*/
+uint32_t SystemCoreClock = __SYSTEM_CLOCK;/*!< System Clock Frequency (Core Clock)*/
+
+
+/*----------------------------------------------------------------------------
+  Clock functions
+ *----------------------------------------------------------------------------*/
+void SystemCoreClockUpdate (void)            /* Get Core Clock Frequency      */
+{
+
+  SystemCoreClock = __SYSTEM_CLOCK;
+
+}
+
+/**
+ * Initialize the system
+ *
+ * @param  none
+ * @return none
+ *
+ * @brief  Setup the microcontroller system.
+ *         Initialize the System.
+ */
+void SystemInit (void)
+{
+  #if (__FPU_USED == 1)
+    SCB->CPACR |= ((3UL << 10*2) |                 /* set CP10 Full Access */
+                   (3UL << 11*2)  );               /* set CP11 Full Access */
+  #endif
+
+  SystemCoreClock = __SYSTEM_CLOCK;
+
+}

libs/CMSIS/DSP_Lib/Examples/arm_class_marks_example/arm_class_marks_example_f32.c

@@ -0,0 +1,194 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3 
+*  
+* Project: 	    CMSIS DSP Library  
+* Title:        arm_class_marks_example_f32.c		  
+*  
+* Description:	Example code to calculate Minimum, Maximum 
+*               Mean, std and variance of marks obtained in a class 
+* 
+* Target Processor: Cortex-M4/Cortex-M3
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+*  
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup ClassMarks Class Marks Example  
+ *
+ * \par Description: 
+ * \par
+ * Demonstrates the use the Maximum, Minimum, Mean, Standard Deviation, Variance
+ * and Matrix functions to calculate statistical values of marks obtained in a class.
+ *
+ * \note This example also demonstrates the usage of static initialization.
+ *  
+ * \par Variables Description:
+ * \par
+ * \li \c testMarks_f32 points to the marks scored by 20 students in 4 subjects
+ * \li \c max_marks     Maximum of all marks 
+ * \li \c min_marks     Minimum of all marks 
+ * \li \c mean          Mean of all marks
+ * \li \c var           Variance of the marks
+ * \li \c std           Standard deviation of the marks 
+ * \li \c numStudents   Total number of students in the class
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_mat_init_f32()
+ * - arm_mat_mult_f32()
+ * - arm_max_f32()
+ * - arm_min_f32()
+ * - arm_mean_f32()
+ * - arm_std_f32()
+ * - arm_var_f32()
+ * 
+ * <b> Refer  </b> 
+ * \link arm_class_marks_example_f32.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_class_marks_example_f32.c 
+  */  
+#include "arm_math.h" 
+ 
+#define USE_STATIC_INIT 
+ 
+ /* ---------------------------------------------------------------------- 
+** Global defines  
+** ------------------------------------------------------------------- */ 
+ 
+#define TEST_LENGTH_SAMPLES 	(20*4) 
+ 
+/* ---------------------------------------------------------------------- 
+** List of Marks scored by 20 students for 4 subjects 
+** ------------------------------------------------------------------- */  
+const float32_t testMarks_f32[TEST_LENGTH_SAMPLES] =  
+{    
+	42.000000,	37.000000,	81.000000,	28.000000,	 
+	83.000000,	72.000000,	36.000000,	38.000000,	 
+	32.000000,	51.000000,	63.000000,	64.000000,	 
+	97.000000,	82.000000,	95.000000,	90.000000,	 
+	66.000000,	51.000000,	54.000000,	42.000000,	 
+	67.000000,	56.000000,	45.000000,	57.000000,	 
+	67.000000,	69.000000,	35.000000,	52.000000,	 
+	29.000000,	81.000000,	58.000000,	47.000000,	 
+	38.000000,	76.000000,	100.000000,	29.000000,	 
+	33.000000,	47.000000,	29.000000,	50.000000,	 
+	34.000000,	41.000000,	61.000000,	46.000000,	 
+	52.000000,	50.000000,	48.000000,	36.000000,	 
+	47.000000,	55.000000,	44.000000,	40.000000,	 
+	100.000000,	94.000000,	84.000000,	37.000000,	 
+	32.000000,	71.000000,	47.000000,	77.000000,	 
+	31.000000,	50.000000,	49.000000,	35.000000,	 
+	63.000000,	67.000000,	40.000000,	31.000000,	 
+	29.000000,	68.000000,	61.000000,	38.000000,	 
+	31.000000,	28.000000,	28.000000,	76.000000,	 
+	55.000000,	33.000000,	29.000000,	39.000000 
+};  
+ 
+ 
+/* ---------------------------------------------------------------------- 
+* Number of subjects X 1  
+* ------------------------------------------------------------------- */  
+const float32_t testUnity_f32[4] =  
+{    
+	1.000,  1.000, 	1.000,  1.000 
+}; 
+ 
+ 
+/* ---------------------------------------------------------------------- 
+** f32 Output buffer 
+** ------------------------------------------------------------------- */  
+static float32_t testOutput[TEST_LENGTH_SAMPLES]; 
+ 
+ 
+/* ------------------------------------------------------------------ 
+* Global defines  
+*------------------------------------------------------------------- */ 
+#define 	NUMSTUDENTS  20 
+#define     NUMSUBJECTS  4 
+ 
+/* ------------------------------------------------------------------ 
+* Global variables  
+*------------------------------------------------------------------- */ 
+ 
+uint32_t  	numStudents = 20; 
+uint32_t  	numSubjects = 4;  
+float32_t	max_marks, min_marks, mean, std, var; 
+uint32_t 	student_num;    
+ 
+/* ---------------------------------------------------------------------------------- 
+* Main f32 test function.  It returns maximum marks secured and student number 
+* ------------------------------------------------------------------------------- */ 
+ 
+int32_t main() 
+{ 
+ 
+#ifndef  USE_STATIC_INIT 
+ 
+  	arm_matrix_instance_f32 srcA; 
+  	arm_matrix_instance_f32 srcB; 
+  	arm_matrix_instance_f32 dstC;  
+ 
+	/* Input and output matrices initializations */  
+	arm_mat_init_f32(&srcA, numStudents, numSubjects, (float32_t *)testMarks_f32);  
+	arm_mat_init_f32(&srcB, numSubjects, 1, (float32_t *)testUnity_f32);  
+	arm_mat_init_f32(&dstC, numStudents, 1, testOutput);  
+ 
+#else 
+ 
+	/* Static Initializations of Input and output matrix sizes and array */ 
+	arm_matrix_instance_f32 srcA = {NUMSTUDENTS, NUMSUBJECTS, (float32_t *)testMarks_f32}; 
+	arm_matrix_instance_f32 srcB = {NUMSUBJECTS, 1, (float32_t *)testUnity_f32}; 
+	arm_matrix_instance_f32 dstC = {NUMSTUDENTS, 1, testOutput}; 
+ 
+#endif 
+ 
+	 
+	/* ---------------------------------------------------------------------- 
+	*Call the Matrix multiplication process function   
+	* ------------------------------------------------------------------- */ 
+	arm_mat_mult_f32(&srcA, &srcB, &dstC); 
+	 
+	/* ---------------------------------------------------------------------- 
+	** Call the Max function to calculate max marks among numStudents 
+	** ------------------------------------------------------------------- */ 
+	arm_max_f32(testOutput, numStudents, &max_marks, &student_num);  
+ 
+	/* ---------------------------------------------------------------------- 
+	** Call the Min function to calculate min marks among numStudents 
+	** ------------------------------------------------------------------- */ 
+	arm_min_f32(testOutput, numStudents, &min_marks, &student_num);  
+ 
+	/* ---------------------------------------------------------------------- 
+	** Call the Mean function to calculate mean 
+	** ------------------------------------------------------------------- */ 
+	arm_mean_f32(testOutput, numStudents, &mean); 
+ 
+	/* ---------------------------------------------------------------------- 
+	** Call the std function to calculate standard deviation 
+	** ------------------------------------------------------------------- */ 
+	arm_std_f32(testOutput, numStudents, &std); 
+ 
+	/* ---------------------------------------------------------------------- 
+	** Call the var function to calculate variance 
+	** ------------------------------------------------------------------- */ 
+	arm_var_f32(testOutput, numStudents, &var); 
+ 
+    while(1);                             /* main function does not return */
+} 

libs/CMSIS/DSP_Lib/Examples/arm_convolution_example/arm_convolution_example_f32.c

@@ -0,0 +1,232 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3 
+*  
+* Project: 	    CMSIS DSP Library  
+* Title:	    arm_convolution_example_f32.c		  
+*  
+* Description:	Example code demonstrating Convolution of two input signals using fft. 
+* 
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup ConvolutionExample Convolution Example    
+ * 
+ * \par Description: 
+ * \par
+ * Demonstrates the convolution theorem with the use of the Complex FFT, Complex-by-Complex 
+ * Multiplication, and Support Functions.
+ *
+ * \par Algorithm:
+ * \par
+ * The convolution theorem states that convolution in the time domain corresponds to 
+ * multiplication in the frequency domain. Therefore, the Fourier transform of the convoution of 
+ * two signals is equal to the product of their individual Fourier transforms. 
+ * The Fourier transform of a signal can be evaluated efficiently using the Fast Fourier Transform (FFT). 
+ * \par
+ * Two input signals, <code>a[n]</code> and <code>b[n]</code>, with lengths \c n1 and \c n2 respectively,
+ * are zero padded so that their lengths become \c N, which is greater than or equal to <code>(n1+n2-1)</code>
+ * and is a power of 4 as FFT implementation is radix-4.  
+ * The convolution of <code>a[n]</code> and <code>b[n]</code> is obtained by taking the FFT of the input 
+ * signals, multiplying the Fourier transforms of the two signals, and taking the inverse FFT of 
+ * the multiplied result.
+ * \par
+ * This is denoted by the following equations:
+ * <pre> A[k] = FFT(a[n],N)
+ * B[k] = FFT(b[n],N)
+ * conv(a[n], b[n]) = IFFT(A[k] * B[k], N)</pre>
+ * where <code>A[k]</code> and <code>B[k]</code> are the N-point FFTs of the signals <code>a[n]</code> 
+ * and <code>b[n]</code> respectively. 
+ * The length of the convolved signal is <code>(n1+n2-1)</code>.
+ *
+ * \par Block Diagram:
+ * \par
+ * \image html Convolution.gif 
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c testInputA_f32 points to the first input sequence
+ * \li \c srcALen length of the first input sequence
+ * \li \c testInputB_f32 points to the second input sequence
+ * \li \c srcBLen length of the second input sequence
+ * \li \c outLen length of convolution output sequence, <code>(srcALen + srcBLen - 1)</code>
+ * \li \c AxB points to the output array where the product of individual FFTs of inputs is stored.
+ * 
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_fill_f32()
+ * - arm_copy_f32()
+ * - arm_cfft_radix4_init_f32()
+ * - arm_cfft_radix4_f32()
+ * - arm_cmplx_mult_cmplx_f32()  
+ * 
+ * <b> Refer  </b> 
+ * \link arm_convolution_example_f32.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_convolution_example_f32.c 
+  */  
+     
+#include "arm_math.h" 
+#include "math_helper.h"				 
+ 
+/* ---------------------------------------------------------------------- 
+* Defines each of the tests performed 
+* ------------------------------------------------------------------- */ 
+#define MAX_BLOCKSIZE	128 
+#define DELTA           (0.000001f) 
+#define SNR_THRESHOLD 	90 
+ 
+/* ---------------------------------------------------------------------- 
+* Declare I/O buffers  
+* ------------------------------------------------------------------- */ 
+float32_t Ak[MAX_BLOCKSIZE];		/* Input A */ 
+float32_t Bk[MAX_BLOCKSIZE];		/* Input B */ 
+float32_t AxB[MAX_BLOCKSIZE * 2];	/* Output */ 
+ 
+/* ---------------------------------------------------------------------- 
+* Test input data for Floating point Convolution example for 32-blockSize 
+* Generated by the MATLAB randn() function 
+* ------------------------------------------------------------------- */ 
+float32_t testInputA_f32[64] =  
+{  
+-0.808920,	1.357369,	1.180861,	-0.504544,	1.762637,	-0.703285,	 
+1.696966,	0.620571,	-0.151093,	-0.100235,	-0.872382,	-0.403579,	 
+-0.860749,	-0.382648,	-1.052338,	0.128113,	-0.646269,	1.093377,	 
+-2.209198,	0.471706,	0.408901,	1.266242,	0.598252,	1.176827,	 
+-0.203421,	0.213596,	-0.851964,	-0.466958,	0.021841,	-0.698938,	 
+-0.604107,	0.461778,	-0.318219,	0.942520,	0.577585,	0.417619,	 
+0.614665,	0.563679,	-1.295073,	-0.764437,	0.952194,	-0.859222,	 
+-0.618554,	-2.268542,	-1.210592,	1.655853,	-2.627219,	-0.994249,	 
+-1.374704,	0.343799,	0.025619,	1.227481,	-0.708031,	0.069355,	 
+-1.845228,	-1.570886,	1.010668,	-1.802084,	1.630088,	1.286090,	 
+-0.161050,	-0.940794,	0.367961,	0.291907 
+		 
+};  
+  
+float32_t testInputB_f32[64] =  
+{  
+0.933724,	0.046881,	1.316470,	0.438345,	0.332682,	2.094885,	 
+0.512081,	0.035546,	0.050894,	-2.320371,	0.168711,	-1.830493,	 
+-0.444834,	-1.003242,	-0.531494,	-1.365600,	-0.155420,	-0.757692,	 
+-0.431880,	-0.380021,	0.096243,	-0.695835,	0.558850,	-1.648962,	 
+0.020369,	-0.363630,	0.887146,	0.845503,	-0.252864,	-0.330397,	 
+1.269131,	-1.109295,	-1.027876,	0.135940,	0.116721,	-0.293399,	 
+-1.349799,	0.166078,	-0.802201,	0.369367,	-0.964568,	-2.266011,	 
+0.465178,	0.651222,	-0.325426,	0.320245,	-0.784178,	-0.579456,	 
+0.093374,	0.604778,	-0.048225,	0.376297,	-0.394412,	0.578182,	 
+-1.218141,	-1.387326,	0.692462,	-0.631297,	0.153137,	-0.638952,	 
+0.635474,	-0.970468,	1.334057,	-0.111370 
+};  
+  
+const float testRefOutput_f32[126] =   
+{  
+-0.818943,	1.229484,	-0.533664,	1.016604,	0.341875,	-1.963656,	 
+5.171476,	3.478033,	7.616361,	6.648384,	0.479069,	1.792012,	 
+-1.295591,	-7.447818,	0.315830,	-10.657445,	-2.483469,	-6.524236,	 
+-7.380591,	-3.739005,	-8.388957,	0.184147,	-1.554888,	3.786508,	 
+-1.684421,	5.400610,	-1.578126,	7.403361,	8.315999,	2.080267,	 
+11.077776,	2.749673,	7.138962,	2.748762,	0.660363,	0.981552,	 
+1.442275,	0.552721,	-2.576892,	4.703989,	0.989156,	8.759344,	 
+-0.564825,	-3.994680,	0.954710,	-5.014144,	6.592329,	1.599488,	 
+-13.979146,	-0.391891,	-4.453369,	-2.311242,	-2.948764,	1.761415,	 
+-0.138322,	10.433007,	-2.309103,	4.297153,	8.535523,	3.209462,	 
+8.695819,	5.569919,	2.514304,	5.582029,	2.060199,	0.642280,	 
+7.024616,	1.686615,	-6.481756,	1.343084,	-3.526451,	1.099073,	 
+-2.965764,	-0.173723,	-4.111484,	6.528384,	-6.965658,	1.726291,	 
+1.535172,	11.023435,	2.338401,	-4.690188,	1.298210,	3.943885,	 
+8.407885,	5.168365,	0.684131,	1.559181,	1.859998,	2.852417,	 
+8.574070,	-6.369078,	6.023458,	11.837963,	-6.027632,	4.469678,	 
+-6.799093,	-2.674048,	6.250367,	-6.809971,	-3.459360,	9.112410,	 
+-2.711621,	-1.336678,	1.564249,	-1.564297,	-1.296760,	8.904013,	 
+-3.230109,	6.878013,	-7.819823,	3.369909,	-1.657410,	-2.007358,	 
+-4.112825,	1.370685,	-3.420525,	-6.276605,	3.244873,	-3.352638,	 
+1.545372,	0.902211,	0.197489,	-1.408732,	0.523390,	0.348440 
+}; 
+ 
+ 
+/* ---------------------------------------------------------------------- 
+* Declare Global variables  
+* ------------------------------------------------------------------- */ 
+uint32_t srcALen = 64;	 /* Length of Input A */ 
+uint32_t srcBLen = 64;	 /* Length of Input B */ 
+uint32_t outLen;		 /* Length of convolution output */ 
+float32_t snr; 			 /* output SNR */ 
+ 
+int32_t main(void) 
+{ 
+	arm_status status;	   /* Status of the example */ 
+	arm_cfft_radix4_instance_f32 cfft_instance;	/* CFFT Structure instance */ 
+ 
+	/* CFFT Structure instance pointer */ 
+    arm_cfft_radix4_instance_f32 *cfft_instance_ptr =  
+			(arm_cfft_radix4_instance_f32*) &cfft_instance; 
+ 
+	/* output length of convolution */ 
+	outLen = srcALen + srcBLen - 1; 
+ 
+	/* Initialise the fft input buffers with all zeros */ 
+	arm_fill_f32(0.0,  Ak, MAX_BLOCKSIZE); 
+	arm_fill_f32(0.0,  Bk, MAX_BLOCKSIZE); 
+ 
+	/* Copy the input values to the fft input buffers */ 
+	arm_copy_f32(testInputA_f32,  Ak, MAX_BLOCKSIZE/2); 
+	arm_copy_f32(testInputB_f32,  Bk, MAX_BLOCKSIZE/2); 
+	 
+	/* Initialize the CFFT function to compute 64 point fft */  
+    status = arm_cfft_radix4_init_f32(cfft_instance_ptr, 64, 0, 1); 
+ 
+	/* Transform input a[n] from time domain to frequency domain A[k] */ 
+	arm_cfft_radix4_f32(cfft_instance_ptr, Ak); 
+	/* Transform input b[n] from time domain to frequency domain B[k] */ 
+	arm_cfft_radix4_f32(cfft_instance_ptr, Bk); 
+	 
+	/* Complex Multiplication of the two input buffers in frequency domain */ 
+	arm_cmplx_mult_cmplx_f32(Ak, Bk, AxB, MAX_BLOCKSIZE/2);  
+ 
+    /* Initialize the CIFFT function to compute 64 point ifft */  
+	status = arm_cfft_radix4_init_f32(cfft_instance_ptr, 64, 1, 1); 
+ 
+	/* Transform the multiplication output from frequency domain to time domain, 
+	   that gives the convolved output  */ 
+	arm_cfft_radix4_f32(cfft_instance_ptr, AxB); 
+ 
+	/* SNR Calculation */ 
+	snr = arm_snr_f32((float32_t *)testRefOutput_f32, AxB, srcALen + srcBLen - 1); 
+	 
+	/* Compare the SNR with threshold to test whether the  
+	   computed output is matched with the reference output values. */ 
+	if( snr > SNR_THRESHOLD) 
+	{ 
+		status = ARM_MATH_SUCCESS; 
+	} 
+		 
+	if( status != ARM_MATH_SUCCESS) 
+	{ 
+	  while(1); 
+	} 
+
+    while(1);                             /* main function does not return */
+} 
+								  
+ /** \endlink */ 
+ 

libs/CMSIS/DSP_Lib/Examples/arm_dotproduct_example/arm_dotproduct_example_f32.c

@@ -0,0 +1,163 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3 
+*  
+* Project: 	    CMSIS DSP Library  
+* Title:	    arm_dotproduct_example_f32.c		  
+*  
+* Description:	Example code computing dot product of two vectors. 
+* 
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup DotproductExample Dot Product Example    
+ * 
+ * \par Description: 
+ * \par
+ * Demonstrates the use of the Multiply and Add functions to perform the dot product.
+ * The dot product of two vectors is obtained by multiplying corresponding elements
+ * and summing the products.
+
+ * \par Algorithm:
+ * \par
+ * The two input vectors \c A and \c B with length \c n, are multiplied element-by-element
+ * and then added to obtain dot product.
+ * \par
+ * This is denoted by the following equation:
+ *         <pre>  dotProduct = A[0] * B[0] + A[1] * B[1] + ... + A[n-1] * B[n-1]</pre> 
+ *
+ * \par Block Diagram:
+ * \par
+ * \image html dotProduct.gif 
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c srcA_buf_f32 points to first input vector
+ * \li \c srcB_buf_f32 points to second input vector 
+ * \li \c testOutput   stores dot product of the two input vectors.
+ * 
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_mult_f32() 
+ * - arm_add_f32()
+ * 
+ * <b> Refer  </b> 
+ * \link arm_dotproduct_example_f32.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_dotproduct_example_f32.c 
+  */  
+
+#include <math.h>     
+#include "arm_math.h" 
+ 
+/* ---------------------------------------------------------------------- 
+* Defines each of the tests performed 
+* ------------------------------------------------------------------- */ 
+#define MAX_BLOCKSIZE	32 
+#define DELTA           (0.000001f) 
+ 
+/* ---------------------------------------------------------------------- 
+* Test input data for Floating point Dot Product example for 32-blockSize 
+* Generated by the MATLAB randn() function 
+* ------------------------------------------------------------------- */  
+/* ----------------------------------------------------------------------  
+** Test input data of srcA for blockSize 32   
+** ------------------------------------------------------------------- */  
+float32_t srcA_buf_f32[MAX_BLOCKSIZE] =   
+{   
+-0.4325648115282207,	-1.6655843782380970,	0.1253323064748307,	 
+ 0.2876764203585489,    -1.1464713506814637,	1.1909154656429988,	 
+ 1.1891642016521031,    -0.0376332765933176,	0.3272923614086541,	 
+ 0.1746391428209245,    -0.1867085776814394,	0.7257905482933027,	 
+-0.5883165430141887,	 2.1831858181971011,   -0.1363958830865957,	 
+ 0.1139313135208096,	 1.0667682113591888,	0.0592814605236053,	 
+-0.0956484054836690,	-0.8323494636500225,	0.2944108163926404,	 
+-1.3361818579378040,	 0.7143245518189522,	1.6235620644462707,	 
+-0.6917757017022868,	 0.8579966728282626,	1.2540014216025324,	 
+-1.5937295764474768,	-1.4409644319010200,	0.5711476236581780,	 
+-0.3998855777153632,	 0.6899973754643451 
+};   
+  
+/* ----------------------------------------------------------------------  
+** Test input data of srcB for blockSize 32   
+** ------------------------------------------------------------------- */   
+float32_t srcB_buf_f32[MAX_BLOCKSIZE] =   
+{   
+ 1.7491401329284098,	0.1325982188803279,	 0.3252281811989881,	 
+-0.7938091410349637,	0.3149236145048914,	-0.5272704888029532,	 
+ 0.9322666565031119,	1.1646643544607362,	-2.0456694357357357,	 
+-0.6443728590041911,	1.7410657940825480,	 0.4867684246821860,	 
+ 1.0488288293660140,	1.4885752747099299,	 1.2705014969484090,	 
+-1.8561241921210170,	2.1343209047321410,  1.4358467535865909,	 
+-0.9173023332875400,   -1.1060770780029008,	 0.8105708062681296,	 
+ 0.6985430696369063,   -0.4015827425012831,	 1.2687512030669628,	 
+-0.7836083053674872,	0.2132664971465569,	 0.7878984786088954,	 
+ 0.8966819356782295,   -0.1869172943544062,	 1.0131816724341454,	 
+ 0.2484350696132857,	0.0596083377937976 
+};   
+ 
+/* Reference dot product output */ 
+float32_t  refDotProdOut = 5.9273644806352142; 	 
+ 
+/* ---------------------------------------------------------------------- 
+* Declare Global variables  
+* ------------------------------------------------------------------- */ 
+float32_t multOutput[MAX_BLOCKSIZE];  /* Intermediate output */ 
+float32_t testOutput;  /* Final ouput */ 
+ 
+arm_status status;	 /* Status of the example */ 
+
+int32_t main(void) 
+{ 
+	uint32_t i;			 /* Loop counter */ 
+	float32_t diff;		 /* Difference between reference and test outputs */ 
+ 
+	/* Multiplication of two input buffers */ 
+	arm_mult_f32(srcA_buf_f32, srcB_buf_f32, multOutput, MAX_BLOCKSIZE); 
+	 
+	/* Accumulate the multiplication output values to  
+	   get the dot product of the two inputs */ 
+	for(i=0; i< MAX_BLOCKSIZE; i++) 
+    {          
+		arm_add_f32(&testOutput, &multOutput[i], &testOutput, 1);	 
+    } 
+ 
+	/* absolute value of difference between ref and test */ 
+	diff = fabsf(refDotProdOut - testOutput); 
+	 
+	/* Comparison of dot product value with reference */ 
+	if(diff > DELTA) 
+	{ 
+		status = ARM_MATH_TEST_FAILURE; 
+	} 
+		 
+	if( status == ARM_MATH_TEST_FAILURE) 
+	{ 
+	  while(1); 
+	} 
+
+    while(1);                             /* main function does not return */
+} 
+ 
+ /** \endlink */ 
+ 

libs/CMSIS/DSP_Lib/Examples/arm_fft_bin_example/arm_fft_bin_data.c

@@ -0,0 +1,268 @@
+#include "arm_math.h"
+
+/* ----------------------------------------------------------------------
+Test Input signal contains 10KHz signal + Uniformly distributed white noise
+** ------------------------------------------------------------------- */
+
+float32_t testInput_f32_10khz[2048] = 
+{   
+-0.865129623056441, 	0.000000000000000, 	-2.655020678073846, 	0.000000000000000, 	0.600664612949661, 	0.000000000000000, 	0.080378093886515, 	0.000000000000000, 	
+-2.899160484012034, 	0.000000000000000, 	2.563004262857762, 	0.000000000000000, 	3.078328403304206, 	0.000000000000000, 	0.105906778385130, 	0.000000000000000, 	
+0.048366940168201, 	0.000000000000000, 	-0.145696461188734, 	0.000000000000000, 	-0.023417155362879, 	0.000000000000000, 	2.127729174988954, 	0.000000000000000, 	
+-1.176633086028377, 	0.000000000000000, 	3.690223557991855, 	0.000000000000000, 	-0.622791766173194, 	0.000000000000000, 	0.722837373872203, 	0.000000000000000, 	
+2.739754205367484, 	0.000000000000000, 	-0.062610410524552, 	0.000000000000000, 	-0.891296810967338, 	0.000000000000000, 	-1.845872258871811, 	0.000000000000000, 	
+1.195039415434387, 	0.000000000000000, 	-2.177388969045026, 	0.000000000000000, 	1.078649103637905, 	0.000000000000000, 	2.570976050490193, 	0.000000000000000, 	
+-1.383551403404574, 	0.000000000000000, 	2.392141424058873, 	0.000000000000000, 	2.858002843205065, 	0.000000000000000, 	-3.682433899725536, 	0.000000000000000, 	
+-3.488146646451150, 	0.000000000000000, 	1.323468578888120, 	0.000000000000000, 	-0.099771155430726, 	0.000000000000000, 	1.561168082500454, 	0.000000000000000, 	
+1.025026795103179, 	0.000000000000000, 	0.928841900171200, 	0.000000000000000, 	2.930499509864950, 	0.000000000000000, 	2.013349089766430, 	0.000000000000000, 	
+2.381676148486737, 	0.000000000000000, 	-3.081062307950236, 	0.000000000000000, 	-0.389579115537544, 	0.000000000000000, 	0.181540149166620, 	0.000000000000000, 	
+-2.601953341353208, 	0.000000000000000, 	0.333435137783218, 	0.000000000000000, 	-2.812945856162965, 	0.000000000000000, 	2.649109640172910, 	0.000000000000000, 	
+-1.003963025744654, 	0.000000000000000, 	1.552460768755035, 	0.000000000000000, 	0.088641345335247, 	0.000000000000000, 	-2.519951327113426, 	0.000000000000000, 	
+-4.341348988610527, 	0.000000000000000, 	0.557772429359965, 	0.000000000000000, 	-1.671267412948494, 	0.000000000000000, 	0.733951350960387, 	0.000000000000000, 	
+0.409263788034864, 	0.000000000000000, 	3.566033071952806, 	0.000000000000000, 	1.882565173848352, 	0.000000000000000, 	-1.106017073793287, 	0.000000000000000, 	
+0.154456720778718, 	0.000000000000000, 	-2.513205795512153, 	0.000000000000000, 	0.310978660939421, 	0.000000000000000, 	0.579706500111723, 	0.000000000000000, 	
+0.000086383683251, 	0.000000000000000, 	-1.311866980897721, 	0.000000000000000, 	1.840007477574986, 	0.000000000000000, 	-3.253005768451345, 	0.000000000000000, 	
+1.462584328739432, 	0.000000000000000, 	1.610103610851738, 	0.000000000000000, 	0.761914676858907, 	0.000000000000000, 	0.974541361089834, 	0.000000000000000, 	
+0.686845845885983, 	0.000000000000000, 	1.849153122025191, 	0.000000000000000, 	0.787800410401453, 	0.000000000000000, 	-1.187438909666279, 	0.000000000000000, 	
+-0.754937911044720, 	0.000000000000000, 	0.084373858395232, 	0.000000000000000, 	-2.600269011710521, 	0.000000000000000, 	-0.962982842142644, 	0.000000000000000, 	
+-0.369328108540868, 	0.000000000000000, 	0.810791418361879, 	0.000000000000000, 	3.587016488699641, 	0.000000000000000, 	-0.520776145083723, 	0.000000000000000, 	
+0.640249919627884, 	0.000000000000000, 	1.103122489464969, 	0.000000000000000, 	2.231779881455556, 	0.000000000000000, 	-1.308035392685241, 	0.000000000000000, 	
+0.424070304330106, 	0.000000000000000, 	-0.200383932651189, 	0.000000000000000, 	-2.365526783356541, 	0.000000000000000, 	-0.989114757436628, 	0.000000000000000, 	
+2.770807688959777, 	0.000000000000000, 	-0.444172737462307, 	0.000000000000000, 	0.079760979374078, 	0.000000000000000, 	-0.005199118412183, 	0.000000000000000, 	
+-0.664712668309527, 	0.000000000000000, 	-0.624171857561896, 	0.000000000000000, 	0.537306979007338, 	0.000000000000000, 	-2.575955675497642, 	0.000000000000000, 	
+1.562363235756780, 	0.000000000000000, 	1.814069369848895, 	0.000000000000000, 	-1.293428583392509, 	0.000000000000000, 	-1.026188449495686, 	0.000000000000000, 	
+-2.981771815588717, 	0.000000000000000, 	-4.223468103075124, 	0.000000000000000, 	2.672674782004045, 	0.000000000000000, 	-0.856096801117735, 	0.000000000000000, 	
+0.048517345512563, 	0.000000000000000, 	-0.026860721136222, 	0.000000000000000, 	0.392932277758187, 	0.000000000000000, 	-1.331740855093099, 	0.000000000000000, 	
+-1.894292129477081, 	0.000000000000000, 	-1.425006468460681, 	0.000000000000000, 	-2.721772427617057, 	0.000000000000000, 	-1.616831100216806, 	0.000000000000000, 	
+3.551177651488947, 	0.000000000000000, 	-0.069685667896087, 	0.000000000000000, 	-3.134634907409102, 	0.000000000000000, 	-0.263627598944639, 	0.000000000000000, 	
+-1.650469945991350, 	0.000000000000000, 	-2.203580339374399, 	0.000000000000000, 	-0.872203246123242, 	0.000000000000000, 	1.230782812607287, 	0.000000000000000, 	
+0.257288860093291, 	0.000000000000000, 	1.989083106173137, 	0.000000000000000, 	-1.985638729453261, 	0.000000000000000, 	-1.416185105842892, 	0.000000000000000, 	
+-1.131097688325772, 	0.000000000000000, 	-2.245130805416057, 	0.000000000000000, 	-1.938873996219074, 	0.000000000000000, 	2.043608361562645, 	0.000000000000000, 	
+-0.583727989880841, 	0.000000000000000, 	-1.785266378212929, 	0.000000000000000, 	1.961457586224753, 	0.000000000000000, 	1.139400099963223, 	0.000000000000000, 	
+-1.979519343363991, 	0.000000000000000, 	2.003023322818429, 	0.000000000000000, 	0.229004069076829, 	0.000000000000000, 	3.452808862193135, 	0.000000000000000, 	
+2.882273808365857, 	0.000000000000000, 	-1.549450501844438, 	0.000000000000000, 	-3.283872089931876, 	0.000000000000000, 	-0.327025884099064, 	0.000000000000000, 	
+-0.054979977136430, 	0.000000000000000, 	-1.192280531479012, 	0.000000000000000, 	0.645539328365578, 	0.000000000000000, 	2.300832863404618, 	0.000000000000000, 	
+-1.092951789535240, 	0.000000000000000, 	-1.017368249363773, 	0.000000000000000, 	-0.142673056169787, 	0.000000000000000, 	0.831073544881250, 	0.000000000000000, 	
+-2.314612531587064, 	0.000000000000000, 	-2.221456299106321, 	0.000000000000000, 	0.460261143885226, 	0.000000000000000, 	0.050585301888595, 	0.000000000000000, 	
+0.364373329183988, 	0.000000000000000, 	-1.685956552069538, 	0.000000000000000, 	0.050664512351055, 	0.000000000000000, 	-0.193355783902718, 	0.000000000000000, 	
+-0.158660446046828, 	0.000000000000000, 	2.394156453841953, 	0.000000000000000, 	-1.562965718554525, 	0.000000000000000, 	-2.199750600869900, 	0.000000000000000, 	
+1.544984022381773, 	0.000000000000000, 	-1.988307216807315, 	0.000000000000000, 	-0.628240722541046, 	0.000000000000000, 	-1.436235771505429, 	0.000000000000000, 	
+1.677013691147313, 	0.000000000000000, 	1.600741781678228, 	0.000000000000000, 	-0.757380959134706, 	0.000000000000000, 	-4.784797439515566, 	0.000000000000000, 	
+0.265121462834569, 	0.000000000000000, 	3.862029485934378, 	0.000000000000000, 	2.386823577249430, 	0.000000000000000, 	-3.655779745436893, 	0.000000000000000, 	
+-0.763541621368016, 	0.000000000000000, 	-1.182140388432962, 	0.000000000000000, 	-1.349106114858063, 	0.000000000000000, 	-2.287533624396759, 	0.000000000000000, 	
+-0.028603745188423, 	0.000000000000000, 	-1.353580755934427, 	0.000000000000000, 	0.461602380352937, 	0.000000000000000, 	-0.059599055078928, 	0.000000000000000, 	
+-0.929946734342228, 	0.000000000000000, 	0.065773089295561, 	0.000000000000000, 	1.106565863102982, 	0.000000000000000, 	4.719295086373593, 	0.000000000000000, 	
+-2.108377703544395, 	0.000000000000000, 	-2.226393620240159, 	0.000000000000000, 	1.375668397437521, 	0.000000000000000, 	-0.960772428525443, 	0.000000000000000, 	
+-2.156313465390571, 	0.000000000000000, 	1.126060012375311, 	0.000000000000000, 	2.756485137030720, 	0.000000000000000, 	0.739639690862600, 	0.000000000000000, 	
+3.914769510295006, 	0.000000000000000, 	1.685232785586675, 	0.000000000000000, 	4.079058040970612, 	0.000000000000000, 	-1.174598301660513, 	0.000000000000000, 	
+-2.885776587275580, 	0.000000000000000, 	-0.241073635188767, 	0.000000000000000, 	3.080489872502403, 	0.000000000000000, 	-2.051244183999421, 	0.000000000000000, 	
+0.664330486845139, 	0.000000000000000, 	-1.697798999370016, 	0.000000000000000, 	1.452369423649782, 	0.000000000000000, 	-1.523532831019280, 	0.000000000000000, 	
+0.171981186587481, 	0.000000000000000, 	-4.685274721583927, 	0.000000000000000, 	-1.336175835319380, 	0.000000000000000, 	1.419070770428945, 	0.000000000000000, 	
+-0.035791601713475, 	0.000000000000000, 	2.291937971632081, 	0.000000000000000, 	-1.962559313450293, 	0.000000000000000, 	-4.831595589339301, 	0.000000000000000, 	
+-1.857055284000925, 	0.000000000000000, 	2.606271522635512, 	0.000000000000000, 	-0.576447978738030, 	0.000000000000000, 	0.082299166967720, 	0.000000000000000, 	
+1.888399453494614, 	0.000000000000000, 	-3.564705298046079, 	0.000000000000000, 	-0.939357831083889, 	0.000000000000000, 	-1.903578203697778, 	0.000000000000000, 	
+-2.642492215447250, 	0.000000000000000, 	-0.182990405251017, 	0.000000000000000, 	3.742026478011174, 	0.000000000000000, 	0.104295803798333, 	0.000000000000000, 	
+1.848678195370347, 	0.000000000000000, 	-1.887384346896369, 	0.000000000000000, 	0.365048973046045, 	0.000000000000000, 	-0.889638010354219, 	0.000000000000000, 	
+1.173877118428863, 	0.000000000000000, 	-1.178562827540109, 	0.000000000000000, 	0.610271645685184, 	0.000000000000000, 	1.831284815697871, 	0.000000000000000, 	
+0.449575390102283, 	0.000000000000000, 	1.597171905253443, 	0.000000000000000, 	3.918574971904773, 	0.000000000000000, 	0.868104027970404, 	0.000000000000000, 	
+0.582643134746494, 	0.000000000000000, 	2.321256382353331, 	0.000000000000000, 	-0.238118642223180, 	0.000000000000000, 	-2.890287868054370, 	0.000000000000000, 	
+0.970995414625622, 	0.000000000000000, 	0.666137930891283, 	0.000000000000000, 	-0.202435718709502, 	0.000000000000000, 	2.057930200518194, 	0.000000000000000, 	
+3.120583443719949, 	0.000000000000000, 	-0.863945271701041, 	0.000000000000000, 	0.906848893874630, 	0.000000000000000, 	-1.434124930222570, 	0.000000000000000, 	
+0.754659384848783, 	0.000000000000000, 	-5.224154442713778, 	0.000000000000000, 	2.330229744098967, 	0.000000000000000, 	1.113946320164698, 	0.000000000000000, 	
+0.523324920322840, 	0.000000000000000, 	1.750740911548348, 	0.000000000000000, 	-0.899333972913577, 	0.000000000000000, 	0.228705845203506, 	0.000000000000000, 	
+-1.934782624767648, 	0.000000000000000, 	-3.508386237231303, 	0.000000000000000, 	-2.107108523073510, 	0.000000000000000, 	0.380587645474815, 	0.000000000000000, 	
+-0.476200877183279, 	0.000000000000000, 	-2.172086712642198, 	0.000000000000000, 	1.795372535780299, 	0.000000000000000, 	-2.100318983391055, 	0.000000000000000, 	
+-0.022571122461405, 	0.000000000000000, 	0.674514020010955, 	0.000000000000000, 	-0.148872569390857, 	0.000000000000000, 	0.298175890592737, 	0.000000000000000, 	
+-1.134244492493590, 	0.000000000000000, 	-3.146848422289455, 	0.000000000000000, 	-1.357950199087602, 	0.000000000000000, 	0.667362732020878, 	0.000000000000000, 	
+-3.119397998316724, 	0.000000000000000, 	-1.189341126297637, 	0.000000000000000, 	-1.532744386856668, 	0.000000000000000, 	-1.672972484202534, 	0.000000000000000, 	
+-2.042283373871558, 	0.000000000000000, 	-1.479481547595924, 	0.000000000000000, 	-0.002668662875396, 	0.000000000000000, 	0.262737760129546, 	0.000000000000000, 	
+2.734456080621830, 	0.000000000000000, 	-0.671945925075102, 	0.000000000000000, 	-3.735078262179111, 	0.000000000000000, 	-0.161705013319883, 	0.000000000000000, 	
+0.748963512361001, 	0.000000000000000, 	1.128046374367600, 	0.000000000000000, 	0.649651335592966, 	0.000000000000000, 	1.880020215025867, 	0.000000000000000, 	
+-1.095632293842306, 	0.000000000000000, 	1.197764876160487, 	0.000000000000000, 	0.323646656252985, 	0.000000000000000, 	-1.655502751114502, 	0.000000000000000, 	
+3.666399062961496, 	0.000000000000000, 	-0.334060899735197, 	0.000000000000000, 	-2.119056978738397, 	0.000000000000000, 	3.721375117275012, 	0.000000000000000, 	
+0.044874186872307, 	0.000000000000000, 	-2.733053897593234, 	0.000000000000000, 	1.590700278891042, 	0.000000000000000, 	3.215711772781902, 	0.000000000000000, 	
+-1.792085012843801, 	0.000000000000000, 	-0.405797188885475, 	0.000000000000000, 	-0.628080020080892, 	0.000000000000000, 	-1.831815840843960, 	0.000000000000000, 	
+2.973656862522834, 	0.000000000000000, 	-0.212032655138417, 	0.000000000000000, 	0.372437389437234, 	0.000000000000000, 	-1.614030579023492, 	0.000000000000000, 	
+-0.704900996358698, 	0.000000000000000, 	1.123700273452105, 	0.000000000000000, 	-0.136371848130819, 	0.000000000000000, 	3.020284357635585, 	0.000000000000000, 	
+-0.550211350877649, 	0.000000000000000, 	5.101256236381711, 	0.000000000000000, 	3.367051512192333, 	0.000000000000000, 	-4.385131946669234, 	0.000000000000000, 	
+-3.967303337694391, 	0.000000000000000, 	-0.965894936640022, 	0.000000000000000, 	0.328366945264681, 	0.000000000000000, 	0.199041562924914, 	0.000000000000000, 	
+1.067681999025495, 	0.000000000000000, 	-1.939516091697170, 	0.000000000000000, 	-1.092980954328824, 	0.000000000000000, 	0.273786079368066, 	0.000000000000000, 	
+-0.040928322190265, 	0.000000000000000, 	-0.118368078577437, 	0.000000000000000, 	1.766589628899997, 	0.000000000000000, 	1.738321311635393, 	0.000000000000000, 	
+-2.895012794321649, 	0.000000000000000, 	1.213521771395142, 	0.000000000000000, 	0.922971726633985, 	0.000000000000000, 	1.091516563636489, 	0.000000000000000, 	
+3.226378465469620, 	0.000000000000000, 	1.149169778666974, 	0.000000000000000, 	-1.695986327709386, 	0.000000000000000, 	-0.974803077355813, 	0.000000000000000, 	
+-4.898035507513607, 	0.000000000000000, 	1.622719302889447, 	0.000000000000000, 	0.583891313586579, 	0.000000000000000, 	-1.677182424094957, 	0.000000000000000, 	
+-1.915633132814685, 	0.000000000000000, 	-1.980150370851616, 	0.000000000000000, 	0.604538269404190, 	0.000000000000000, 	0.939862406149365, 	0.000000000000000, 	
+-1.266939874246416, 	0.000000000000000, 	-1.494771249200063, 	0.000000000000000, 	0.278042784093988, 	0.000000000000000, 	0.326627416008916, 	0.000000000000000, 	
+-1.914530157643303, 	0.000000000000000, 	1.908947721862196, 	0.000000000000000, 	0.531819285694044, 	0.000000000000000, 	3.056856632319658, 	0.000000000000000, 	
+-0.389241827774643, 	0.000000000000000, 	-2.418606606780420, 	0.000000000000000, 	0.915299238878703, 	0.000000000000000, 	-0.098774174295283, 	0.000000000000000, 	
+-0.906199428444304, 	0.000000000000000, 	0.316716451217743, 	0.000000000000000, 	-4.367700643578311, 	0.000000000000000, 	1.491687997515293, 	0.000000000000000, 	
+-1.962381126288365, 	0.000000000000000, 	-0.700829196527045, 	0.000000000000000, 	3.028958963615630, 	0.000000000000000, 	-2.313461067462598, 	0.000000000000000, 	
+-1.431933239886712, 	0.000000000000000, 	-0.831153039725342, 	0.000000000000000, 	3.939495598250743, 	0.000000000000000, 	0.342974753984771, 	0.000000000000000, 	
+-2.768330763002974, 	0.000000000000000, 	-2.744010370019008, 	0.000000000000000, 	3.821352685212561, 	0.000000000000000, 	4.551065271455856, 	0.000000000000000, 	
+3.270136437041298, 	0.000000000000000, 	-3.188028411950982, 	0.000000000000000, 	-0.777075012417436, 	0.000000000000000, 	0.097110650265216, 	0.000000000000000, 	
+1.221216137608812, 	0.000000000000000, 	-1.325824244541822, 	0.000000000000000, 	-2.655296734084113, 	0.000000000000000, 	-1.074792144885704, 	0.000000000000000, 	
+2.770401584439407, 	0.000000000000000, 	5.240270645610543, 	0.000000000000000, 	0.108576672208892, 	0.000000000000000, 	-1.209394350650142, 	0.000000000000000, 	
+1.403344353838785, 	0.000000000000000, 	-0.299032904177277, 	0.000000000000000, 	4.074959450638227, 	0.000000000000000, 	1.718727473952107, 	0.000000000000000, 	
+-3.061349227080806, 	0.000000000000000, 	-1.158596888541269, 	0.000000000000000, 	3.381858904662625, 	0.000000000000000, 	0.957339964054052, 	0.000000000000000, 	
+0.179900074904899, 	0.000000000000000, 	-3.909641902506081, 	0.000000000000000, 	0.805717289408649, 	0.000000000000000, 	2.047413793928261, 	0.000000000000000, 	
+-1.273580225826614, 	0.000000000000000, 	-2.681359186869971, 	0.000000000000000, 	-0.721241345822093, 	0.000000000000000, 	-1.613090681569475, 	0.000000000000000, 	
+0.463138804815955, 	0.000000000000000, 	0.377223507800954, 	0.000000000000000, 	2.046550684968141, 	0.000000000000000, 	0.178508732797712, 	0.000000000000000, 	
+-0.477815330358845, 	0.000000000000000, 	3.763355908332053, 	0.000000000000000, 	1.300430303035163, 	0.000000000000000, 	-0.214625793857725, 	0.000000000000000, 	
+1.343267891864081, 	0.000000000000000, 	-0.340007682433245, 	0.000000000000000, 	2.062703194680005, 	0.000000000000000, 	0.042032160234235, 	0.000000000000000, 	
+0.643732569732250, 	0.000000000000000, 	-1.913502543857589, 	0.000000000000000, 	3.771340762937158, 	0.000000000000000, 	1.050024807363386, 	0.000000000000000, 	
+-4.440489488592649, 	0.000000000000000, 	0.444904302066643, 	0.000000000000000, 	2.898702265650048, 	0.000000000000000, 	1.953232980548558, 	0.000000000000000, 	
+2.761564952735079, 	0.000000000000000, 	1.963537633260397, 	0.000000000000000, 	-2.168858472916215, 	0.000000000000000, 	-4.116235357699841, 	0.000000000000000, 	
+4.183678271896528, 	0.000000000000000, 	0.600422284944681, 	0.000000000000000, 	-0.659352647255126, 	0.000000000000000, 	-0.993127338218109, 	0.000000000000000, 	
+-2.463571314945747, 	0.000000000000000, 	0.937720951545881, 	0.000000000000000, 	-3.098957308429730, 	0.000000000000000, 	-2.354719140045463, 	0.000000000000000, 	
+-0.417285119323949, 	0.000000000000000, 	2.187974075975947, 	0.000000000000000, 	1.101468905172585, 	0.000000000000000, 	-3.185800678152109, 	0.000000000000000, 	
+2.357534709345083, 	0.000000000000000, 	0.246645606729407, 	0.000000000000000, 	4.440905650784504, 	0.000000000000000, 	-2.236807716637866, 	0.000000000000000, 	
+-2.171481518317550, 	0.000000000000000, 	-2.029571795072690, 	0.000000000000000, 	0.135599790431348, 	0.000000000000000, 	-1.277965265520191, 	0.000000000000000, 	
+-1.927976233157507, 	0.000000000000000, 	-5.434492783745394, 	0.000000000000000, 	-2.026375829312657, 	0.000000000000000, 	1.009666016819321, 	0.000000000000000, 	
+0.238549782367247, 	0.000000000000000, 	-0.516403923971309, 	0.000000000000000, 	-0.933977817429352, 	0.000000000000000, 	0.155803015935614, 	0.000000000000000, 	
+-0.396194809997929, 	0.000000000000000, 	-0.915178100253214, 	0.000000000000000, 	0.666329367985015, 	0.000000000000000, 	-1.517991149945785, 	0.000000000000000, 	
+0.458266744144822, 	0.000000000000000, 	-1.242845974381418, 	0.000000000000000, 	0.057914823556477, 	0.000000000000000, 	0.994101307476875, 	0.000000000000000, 	
+-2.387209849199325, 	0.000000000000000, 	0.459297048883826, 	0.000000000000000, 	0.227711405683905, 	0.000000000000000, 	0.030255073506117, 	0.000000000000000, 	
+-1.323361608181337, 	0.000000000000000, 	-4.650244457426706, 	0.000000000000000, 	0.062908579526021, 	0.000000000000000, 	3.462831028244432, 	0.000000000000000, 	
+1.303608183314856, 	0.000000000000000, 	-1.430415193881612, 	0.000000000000000, 	-1.672886118942142, 	0.000000000000000, 	0.992890699210099, 	0.000000000000000, 	
+-0.160814531784247, 	0.000000000000000, 	-1.238132939350430, 	0.000000000000000, 	-0.589223271459376, 	0.000000000000000, 	2.326363810561534, 	0.000000000000000, 	
+-4.433789496230785, 	0.000000000000000, 	1.664686987538929, 	0.000000000000000, 	-2.366128834617921, 	0.000000000000000, 	1.212421570743837, 	0.000000000000000, 	
+-4.847914267690055, 	0.000000000000000, 	0.228485221404712, 	0.000000000000000, 	0.466139765470957, 	0.000000000000000, 	-1.344202776943546, 	0.000000000000000, 	
+-1.012053673330574, 	0.000000000000000, 	-2.844980626424742, 	0.000000000000000, 	-1.552703722026340, 	0.000000000000000, 	-1.448830983885038, 	0.000000000000000, 	
+0.127010756753980, 	0.000000000000000, 	-1.667188263752299, 	0.000000000000000, 	3.424818052085100, 	0.000000000000000, 	0.956291135453840, 	0.000000000000000, 	
+-3.725533331754662, 	0.000000000000000, 	-1.584534272368832, 	0.000000000000000, 	-1.654148210472472, 	0.000000000000000, 	0.701610500675698, 	0.000000000000000, 	
+0.164954538683927, 	0.000000000000000, 	-0.739260064712987, 	0.000000000000000, 	-2.167324026090101, 	0.000000000000000, 	-0.310240491909496, 	0.000000000000000, 	
+-2.281790349106906, 	0.000000000000000, 	1.719655331305361, 	0.000000000000000, 	-2.997005923606441, 	0.000000000000000, 	-1.999301431556852, 	0.000000000000000, 	
+-0.292229010068828, 	0.000000000000000, 	1.172317994855851, 	0.000000000000000, 	0.196734885241533, 	0.000000000000000, 	2.981365193477068, 	0.000000000000000, 	
+2.637726016926352, 	0.000000000000000, 	1.434045125217982, 	0.000000000000000, 	0.883627180451827, 	0.000000000000000, 	-1.434040761445747, 	0.000000000000000, 	
+-1.528891971086553, 	0.000000000000000, 	-3.306913135367542, 	0.000000000000000, 	-0.399059265470646, 	0.000000000000000, 	-0.265674394285178, 	0.000000000000000, 	
+3.502591252855384, 	0.000000000000000, 	0.830301156604454, 	0.000000000000000, 	-0.220021317046083, 	0.000000000000000, 	-0.090553770476646, 	0.000000000000000, 	
+0.771863477047951, 	0.000000000000000, 	1.351209629105760, 	0.000000000000000, 	3.773699756201963, 	0.000000000000000, 	0.472600118752329, 	0.000000000000000, 	
+2.332825668012222, 	0.000000000000000, 	1.853747950314528, 	0.000000000000000, 	0.759515251766178, 	0.000000000000000, 	1.327112776215496, 	0.000000000000000, 	
+2.518730296237868, 	0.000000000000000, 	0.764450208786353, 	0.000000000000000, 	-0.278275349491296, 	0.000000000000000, 	-0.041559465082020, 	0.000000000000000, 	
+1.387166083167787, 	0.000000000000000, 	2.612996769598122, 	0.000000000000000, 	-0.385404831721799, 	0.000000000000000, 	2.005630016170309, 	0.000000000000000, 	
+-0.950500047307998, 	0.000000000000000, 	-1.166884021392492, 	0.000000000000000, 	1.432973552928162, 	0.000000000000000, 	2.540370505384567, 	0.000000000000000, 	
+-1.140505295054501, 	0.000000000000000, 	-3.673358835201185, 	0.000000000000000, 	-0.450691288038056, 	0.000000000000000, 	1.601024294408014, 	0.000000000000000, 	
+0.773213556014045, 	0.000000000000000, 	2.973873693246168, 	0.000000000000000, 	-1.361548406382279, 	0.000000000000000, 	1.409136332424815, 	0.000000000000000, 	
+-0.963382518314713, 	0.000000000000000, 	-2.031268227368161, 	0.000000000000000, 	0.983309972085586, 	0.000000000000000, 	-3.461412488471631, 	0.000000000000000, 	
+-2.601124929406039, 	0.000000000000000, 	-0.533896239766343, 	0.000000000000000, 	-2.627129008866350, 	0.000000000000000, 	0.622111169161305, 	0.000000000000000, 	
+-1.160926365580422, 	0.000000000000000, 	-2.406196188132628, 	0.000000000000000, 	-1.076870362758737, 	0.000000000000000, 	-1.791866820937175, 	0.000000000000000, 	
+-0.749453071522325, 	0.000000000000000, 	-5.324156615990973, 	0.000000000000000, 	-1.038698022238289, 	0.000000000000000, 	-2.106629944730630, 	0.000000000000000, 	
+0.659295598564773, 	0.000000000000000, 	0.520940881580988, 	0.000000000000000, 	-0.055649203928700, 	0.000000000000000, 	0.292096765423137, 	0.000000000000000, 	
+-4.663743901790872, 	0.000000000000000, 	-0.125066503391666, 	0.000000000000000, 	-2.452620252445380, 	0.000000000000000, 	-0.712128227397468, 	0.000000000000000, 	
+-0.048938037970968, 	0.000000000000000, 	-1.821520226003361, 	0.000000000000000, 	0.810106421304257, 	0.000000000000000, 	-0.196636623956257, 	0.000000000000000, 	
+-0.701769836763804, 	0.000000000000000, 	2.460345045649201, 	0.000000000000000, 	3.506597671641116, 	0.000000000000000, 	-2.711322611972225, 	0.000000000000000, 	
+-0.658079876600542, 	0.000000000000000, 	-2.040082099646173, 	0.000000000000000, 	2.201668355395807, 	0.000000000000000, 	1.181507395879711, 	0.000000000000000, 	
+-1.640739552179682, 	0.000000000000000, 	-1.613393726467190, 	0.000000000000000, 	-1.156741241731352, 	0.000000000000000, 	2.527773464519963, 	0.000000000000000, 	
+-0.497040638009502, 	0.000000000000000, 	-0.975817112895589, 	0.000000000000000, 	-2.866830755546166, 	0.000000000000000, 	1.120214498507878, 	0.000000000000000, 	
+5.986771654661698, 	0.000000000000000, 	0.398219252656757, 	0.000000000000000, 	-3.545606013198135, 	0.000000000000000, 	0.312398099396191, 	0.000000000000000, 	
+-2.265327979531788, 	0.000000000000000, 	0.792121001107366, 	0.000000000000000, 	-3.736145137670100, 	0.000000000000000, 	0.762228883650802, 	0.000000000000000, 	
+2.283545661214646, 	0.000000000000000, 	3.780020629583529, 	0.000000000000000, 	3.117260228608810, 	0.000000000000000, 	-2.011159255609613, 	0.000000000000000, 	
+0.279107700476072, 	0.000000000000000, 	2.003369134246936, 	0.000000000000000, 	-1.448171234480257, 	0.000000000000000, 	0.584697150310140, 	0.000000000000000, 	
+0.919508663636197, 	0.000000000000000, 	-3.071349141675388, 	0.000000000000000, 	-1.555923649263667, 	0.000000000000000, 	2.232497079438850, 	0.000000000000000, 	
+-0.012662139119883, 	0.000000000000000, 	0.372825540734715, 	0.000000000000000, 	2.378543590847629, 	0.000000000000000, 	1.459053407813062, 	0.000000000000000, 	
+-0.967913907390927, 	0.000000000000000, 	1.322825200678212, 	0.000000000000000, 	-1.033775820061824, 	0.000000000000000, 	-1.813629552693142, 	0.000000000000000, 	
+4.794348161661486, 	0.000000000000000, 	0.655279811518676, 	0.000000000000000, 	-2.224590138589720, 	0.000000000000000, 	0.595329481295766, 	0.000000000000000, 	
+3.364055988866225, 	0.000000000000000, 	1.863416422998127, 	0.000000000000000, 	1.930305751828105, 	0.000000000000000, 	-0.284467053432545, 	0.000000000000000, 	
+-0.923374905878938, 	0.000000000000000, 	1.922988234041399, 	0.000000000000000, 	0.310482143432719, 	0.000000000000000, 	0.332122302397134, 	0.000000000000000, 	
+-1.659487472408966, 	0.000000000000000, 	-1.865943507877961, 	0.000000000000000, 	-0.186775297569864, 	0.000000000000000, 	-1.700543850628361, 	0.000000000000000, 	
+0.497157959366735, 	0.000000000000000, 	-0.471244843957418, 	0.000000000000000, 	-0.432013753969948, 	0.000000000000000, 	-4.000189880113231, 	0.000000000000000, 	
+-0.415335170016467, 	0.000000000000000, 	0.317311950972859, 	0.000000000000000, 	0.038393428927595, 	0.000000000000000, 	0.177219909465206, 	0.000000000000000, 	
+0.531650958095143, 	0.000000000000000, 	-2.711644985175806, 	0.000000000000000, 	0.328744077805156, 	0.000000000000000, 	-0.938417707547928, 	0.000000000000000, 	
+0.970379584897379, 	0.000000000000000, 	1.873649473917137, 	0.000000000000000, 	0.177938226987023, 	0.000000000000000, 	0.155609346302393, 	0.000000000000000, 	
+-1.276504241867208, 	0.000000000000000, 	-0.463725075928807, 	0.000000000000000, 	-0.064748250389500, 	0.000000000000000, 	-1.725568534062385, 	0.000000000000000, 	
+-0.139066584804067, 	0.000000000000000, 	1.975514554117767, 	0.000000000000000, 	-0.807063199499478, 	0.000000000000000, 	-0.326926659682788, 	0.000000000000000, 	
+1.445727032487938, 	0.000000000000000, 	-0.597151107739100, 	0.000000000000000, 	2.732557531709386, 	0.000000000000000, 	-2.907130934109188, 	0.000000000000000, 	
+-1.461264832679981, 	0.000000000000000, 	-1.708588604968163, 	0.000000000000000, 	3.652851925431363, 	0.000000000000000, 	0.682050868282879, 	0.000000000000000, 	
+-0.281312579963294, 	0.000000000000000, 	0.554966483307825, 	0.000000000000000, 	-0.981341739340932, 	0.000000000000000, 	1.279543331141603, 	0.000000000000000, 	
+0.036589747826856, 	0.000000000000000, 	2.312073745896073, 	0.000000000000000, 	1.754682200732425, 	0.000000000000000, 	-0.957515875428627, 	0.000000000000000, 	
+-0.833596942819695, 	0.000000000000000, 	0.437054368791033, 	0.000000000000000, 	-0.898819399360279, 	0.000000000000000, 	-0.296050580896839, 	0.000000000000000, 	
+-0.785144257649601, 	0.000000000000000, 	-2.541503089003311, 	0.000000000000000, 	2.225075846758761, 	0.000000000000000, 	-1.587290487902002, 	0.000000000000000, 	
+-1.421404172056462, 	0.000000000000000, 	-3.015149802293631, 	0.000000000000000, 	1.780874288867949, 	0.000000000000000, 	-0.865812740882613, 	0.000000000000000, 	
+-2.845327531197112, 	0.000000000000000, 	1.445225867774367, 	0.000000000000000, 	2.183733236584647, 	0.000000000000000, 	1.163371072749080, 	0.000000000000000, 	
+0.883547693520409, 	0.000000000000000, 	-1.224093106684675, 	0.000000000000000, 	-1.854501116331044, 	0.000000000000000, 	1.783082089255796, 	0.000000000000000, 	
+2.301508706196191, 	0.000000000000000, 	-0.539901944139077, 	0.000000000000000, 	1.962315832319967, 	0.000000000000000, 	-0.060709041870503, 	0.000000000000000, 	
+-1.353139923300238, 	0.000000000000000, 	-1.482887537805234, 	0.000000000000000, 	1.273732601967176, 	0.000000000000000, 	-3.456609915556321, 	0.000000000000000, 	
+-3.752320586540873, 	0.000000000000000, 	3.536356614978951, 	0.000000000000000, 	0.206035952043233, 	0.000000000000000, 	5.933966913773842, 	0.000000000000000, 	
+-0.486633898075490, 	0.000000000000000, 	-0.329595089863342, 	0.000000000000000, 	1.496414153905337, 	0.000000000000000, 	0.137868749388880, 	0.000000000000000, 	
+-0.437192030996792, 	0.000000000000000, 	2.682750615210656, 	0.000000000000000, 	-2.440234892848570, 	0.000000000000000, 	1.433910252426186, 	0.000000000000000, 	
+-0.415051506104074, 	0.000000000000000, 	1.982003013708649, 	0.000000000000000, 	1.345796609972435, 	0.000000000000000, 	-2.335949513404370, 	0.000000000000000, 	
+1.065988867433025, 	0.000000000000000, 	2.741844905000464, 	0.000000000000000, 	-1.754047930934362, 	0.000000000000000, 	0.229252730015575, 	0.000000000000000, 	
+-0.679791016408669, 	0.000000000000000, 	-2.274097820043743, 	0.000000000000000, 	0.149802252231876, 	0.000000000000000, 	-0.139697151364830, 	0.000000000000000, 	
+-2.773367420505435, 	0.000000000000000, 	-4.403400246165611, 	0.000000000000000, 	-1.468974515184135, 	0.000000000000000, 	0.664990623095844, 	0.000000000000000, 	
+-3.446979775557143, 	0.000000000000000, 	1.850006428987618, 	0.000000000000000, 	-1.550866747921936, 	0.000000000000000, 	-3.632874882935257, 	0.000000000000000, 	
+0.828039662992464, 	0.000000000000000, 	2.794055182632816, 	0.000000000000000, 	-0.593995716682633, 	0.000000000000000, 	0.142788156054200, 	0.000000000000000, 	
+0.552461945119668, 	0.000000000000000, 	0.842127129738758, 	0.000000000000000, 	1.414335509600077, 	0.000000000000000, 	-0.311559241382430, 	0.000000000000000, 	
+1.510590844695250, 	0.000000000000000, 	1.692217183824300, 	0.000000000000000, 	0.613760285711957, 	0.000000000000000, 	0.065233463207770, 	0.000000000000000, 	
+-2.571912893711505, 	0.000000000000000, 	-1.707001531141341, 	0.000000000000000, 	0.673884968382041, 	0.000000000000000, 	0.889863883420103, 	0.000000000000000, 	
+-2.395635435233346, 	0.000000000000000, 	1.129247296359819, 	0.000000000000000, 	0.569074704779735, 	0.000000000000000, 	6.139436017480722, 	0.000000000000000, 	
+0.822158309259017, 	0.000000000000000, 	-3.289872016222589, 	0.000000000000000, 	0.417612988384414, 	0.000000000000000, 	1.493982103868165, 	0.000000000000000, 	
+-0.415353391377005, 	0.000000000000000, 	0.288670764933155, 	0.000000000000000, 	-1.895650228872272, 	0.000000000000000, 	-0.139631694475020, 	0.000000000000000, 	
+1.445103299005436, 	0.000000000000000, 	2.877182243683429, 	0.000000000000000, 	1.192428490172580, 	0.000000000000000, 	-5.964591921763842, 	0.000000000000000, 	
+0.570859795882959, 	0.000000000000000, 	2.328333316356666, 	0.000000000000000, 	0.333755014930026, 	0.000000000000000, 	1.221901577771909, 	0.000000000000000, 	
+0.943358697415568, 	0.000000000000000, 	2.793063983613067, 	0.000000000000000, 	3.163005066073616, 	0.000000000000000, 	2.098300664513867, 	0.000000000000000, 	
+-3.915313164333447, 	0.000000000000000, 	-2.475766769064539, 	0.000000000000000, 	1.720472044894277, 	0.000000000000000, 	-1.273591949275665, 	0.000000000000000, 	
+-1.213451272938616, 	0.000000000000000, 	0.697439404325690, 	0.000000000000000, 	-0.309902287574293, 	0.000000000000000, 	2.622575852162781, 	0.000000000000000, 	
+-2.075881936219060, 	0.000000000000000, 	0.777847545691770, 	0.000000000000000, 	-3.967947986440650, 	0.000000000000000, 	-3.066503371806472, 	0.000000000000000, 	
+1.193780625937845, 	0.000000000000000, 	0.214246579281311, 	0.000000000000000, 	-2.610681491162162, 	0.000000000000000, 	-1.261224183972745, 	0.000000000000000, 	
+-1.165071748544285, 	0.000000000000000, 	-1.116548474834374, 	0.000000000000000, 	0.847202164846982, 	0.000000000000000, 	-3.474301529532390, 	0.000000000000000, 	
+0.020799541946476, 	0.000000000000000, 	-3.868995473288166, 	0.000000000000000, 	1.757979409638067, 	0.000000000000000, 	0.868115130183109, 	0.000000000000000, 	
+0.910167436737958, 	0.000000000000000, 	-1.878855115563720, 	0.000000000000000, 	1.710357104174161, 	0.000000000000000, 	-1.468933980990902, 	0.000000000000000, 	
+1.799544171601169, 	0.000000000000000, 	-4.922332880027887, 	0.000000000000000, 	0.219424548939720, 	0.000000000000000, 	-0.971671113451924, 	0.000000000000000, 	
+-0.940533475616266, 	0.000000000000000, 	0.122510114412152, 	0.000000000000000, 	-1.373686254916911, 	0.000000000000000, 	1.760348103896323, 	0.000000000000000, 	
+0.391745067829643, 	0.000000000000000, 	2.521958505327354, 	0.000000000000000, 	-1.300693516405092, 	0.000000000000000, 	-0.538251788309178, 	0.000000000000000, 	
+0.797184135810173, 	0.000000000000000, 	2.908800548982588, 	0.000000000000000, 	1.590902251655215, 	0.000000000000000, 	-1.070323714487264, 	0.000000000000000, 	
+-3.349764443340999, 	0.000000000000000, 	-1.190563529731447, 	0.000000000000000, 	1.363369471291963, 	0.000000000000000, 	-1.814270299924576, 	0.000000000000000, 	
+-0.023381588315711, 	0.000000000000000, 	1.719182048679569, 	0.000000000000000, 	0.839917213252626, 	0.000000000000000, 	1.006099633839122, 	0.000000000000000, 	
+0.812462674381527, 	0.000000000000000, 	1.755814336346739, 	0.000000000000000, 	2.546848681206319, 	0.000000000000000, 	-1.555300208869455, 	0.000000000000000, 	
+1.017053811631167, 	0.000000000000000, 	0.996591039170903, 	0.000000000000000, 	-1.228047247924881, 	0.000000000000000, 	4.809462271463009, 	0.000000000000000, 	
+2.318113116151685, 	0.000000000000000, 	-1.206932520679733, 	0.000000000000000, 	1.273757685623312, 	0.000000000000000, 	0.724335352481802, 	0.000000000000000, 	
+1.519876652073198, 	0.000000000000000, 	-2.749670314714158, 	0.000000000000000, 	3.424042481847581, 	0.000000000000000, 	-3.714668360421517, 	0.000000000000000, 	
+1.612834197004014, 	0.000000000000000, 	-2.038234723985566, 	0.000000000000000, 	1.470938786562152, 	0.000000000000000, 	2.111634918450302, 	0.000000000000000, 	
+1.030376670151787, 	0.000000000000000, 	-0.420877189003829, 	0.000000000000000, 	-1.502024800532894, 	0.000000000000000, 	0.452310749163804, 	0.000000000000000, 	
+-1.606059382300987, 	0.000000000000000, 	-4.006159967834147, 	0.000000000000000, 	-2.152801208196508, 	0.000000000000000, 	1.671674089372579, 	0.000000000000000, 	
+1.714536333564101, 	0.000000000000000, 	-1.011518543005344, 	0.000000000000000, 	-0.576410282180584, 	0.000000000000000, 	0.733689809480836, 	0.000000000000000, 	
+1.004245602717974, 	0.000000000000000, 	1.010090391888449, 	0.000000000000000, 	3.811459513385621, 	0.000000000000000, 	-5.230621089271954, 	0.000000000000000, 	
+0.678044861034399, 	0.000000000000000, 	1.255935859598107, 	0.000000000000000, 	1.674521701615288, 	0.000000000000000, 	-1.656695216761705, 	0.000000000000000, 	
+1.169286028869693, 	0.000000000000000, 	0.524915416191998, 	0.000000000000000, 	2.397642885039520, 	0.000000000000000, 	2.108711400616072, 	0.000000000000000, 	
+2.037618211018084, 	0.000000000000000, 	-0.623664553406925, 	0.000000000000000, 	2.984106170984409, 	0.000000000000000, 	1.132182737400932, 	0.000000000000000, 	
+-2.859274340352130, 	0.000000000000000, 	-0.975550071398723, 	0.000000000000000, 	-1.359935119997407, 	0.000000000000000, 	-2.963308211050121, 	0.000000000000000, 	
+-0.228726662781163, 	0.000000000000000, 	-1.411110379682043, 	0.000000000000000, 	0.741553355734225, 	0.000000000000000, 	0.497554254758309, 	0.000000000000000, 	
+2.371907950598855, 	0.000000000000000, 	1.063465168988748, 	0.000000000000000, 	-0.641082692081488, 	0.000000000000000, 	-0.855439878540726, 	0.000000000000000, 	
+0.578321738578726, 	0.000000000000000, 	3.005809768796194, 	0.000000000000000, 	1.961458699064065, 	0.000000000000000, 	-3.206261663772745, 	0.000000000000000, 	
+-0.364431989095434, 	0.000000000000000, 	-0.263182496622273, 	0.000000000000000, 	1.843464680631139, 	0.000000000000000, 	-0.419107530229249, 	0.000000000000000, 	
+1.662335873298487, 	0.000000000000000, 	-0.853687563304005, 	0.000000000000000, 	-2.584133404357169, 	0.000000000000000, 	3.466839568922895, 	0.000000000000000, 	
+0.881671345091973, 	0.000000000000000, 	0.454620014206908, 	0.000000000000000, 	-1.737245187402739, 	0.000000000000000, 	2.162713238369243, 	0.000000000000000, 	
+-3.868539002714486, 	0.000000000000000, 	2.014114855933826, 	0.000000000000000, 	-0.703233831811006, 	0.000000000000000, 	-3.410319935997574, 	0.000000000000000, 	
+-1.851235811006584, 	0.000000000000000, 	0.909783907894036, 	0.000000000000000, 	0.091884002136728, 	0.000000000000000, 	-2.688294201131650, 	0.000000000000000, 	
+-0.906134178460955, 	0.000000000000000, 	3.475054609035133, 	0.000000000000000, 	-0.573927964170323, 	0.000000000000000, 	-0.429542937515399, 	0.000000000000000, 	
+0.991348618739939, 	0.000000000000000, 	1.974804904926325, 	0.000000000000000, 	0.975783450796698, 	0.000000000000000, 	-3.057119549071503, 	0.000000000000000, 	
+-3.899429237481194, 	0.000000000000000, 	0.362439009175350, 	0.000000000000000, 	-1.124461670265618, 	0.000000000000000, 	1.806000360163583, 	0.000000000000000, 	
+-2.768333362600288, 	0.000000000000000, 	0.244387897900379, 	0.000000000000000, 	0.908767296720926, 	0.000000000000000, 	1.254669374391882, 	0.000000000000000, 	
+-1.420441929463686, 	0.000000000000000, 	-0.875658895966293, 	0.000000000000000, 	0.183824603376167, 	0.000000000000000, 	-3.361653917011686, 	0.000000000000000, 	
+-0.796615630227952, 	0.000000000000000, 	-1.660226542658673, 	0.000000000000000, 	1.654439358307226, 	0.000000000000000, 	2.782812946709771, 	0.000000000000000, 	
+1.418064412811531, 	0.000000000000000, 	-0.819645647243761, 	0.000000000000000, 	0.807724772592699, 	0.000000000000000, 	-0.941967976379298, 	0.000000000000000, 	
+-2.312768306047469, 	0.000000000000000, 	0.872426936477443, 	0.000000000000000, 	0.919528961530845, 	0.000000000000000, 	-2.084904575264847, 	0.000000000000000, 	
+-1.972464868459322, 	0.000000000000000, 	-1.050687203338466, 	0.000000000000000, 	1.659579707007902, 	0.000000000000000, 	-1.820640014705855, 	0.000000000000000, 	
+-1.195078061671045, 	0.000000000000000, 	-1.639773173762048, 	0.000000000000000, 	1.616744338157063, 	0.000000000000000, 	4.019216096811563, 	0.000000000000000, 	
+3.461021102549681, 	0.000000000000000, 	1.642352734361484, 	0.000000000000000, 	-0.046354693720813, 	0.000000000000000, 	-0.041936252359677, 	0.000000000000000, 	
+-2.393307519480551, 	0.000000000000000, 	-0.341471634615121, 	0.000000000000000, 	-0.392073595257017, 	0.000000000000000, 	-0.219299018372730, 	0.000000000000000, 	
+-2.016391579662071, 	0.000000000000000, 	-0.653096251969787, 	0.000000000000000, 	1.466353155666821, 	0.000000000000000, 	-2.872058864320412, 	0.000000000000000, 	
+-2.157180779503830, 	0.000000000000000, 	0.723257479841560, 	0.000000000000000, 	3.769951308104384, 	0.000000000000000, 	-1.923392042420024, 	0.000000000000000, 	
+0.644899359942840, 	0.000000000000000, 	-2.090226891621437, 	0.000000000000000, 	-0.277043982890403, 	0.000000000000000, 	-0.528271428321112, 	0.000000000000000, 	
+2.518120645960652, 	0.000000000000000, 	1.040820431111488, 	0.000000000000000, 	-4.560583754742486, 	0.000000000000000, 	-0.226899614918836, 	0.000000000000000, 	
+1.713331231108959, 	0.000000000000000, 	-3.293941019163642, 	0.000000000000000, 	-1.113331444648290, 	0.000000000000000, 	-1.032308423149906, 	0.000000000000000, 	
+1.593774272982443, 	0.000000000000000, 	-1.246840475090529, 	0.000000000000000, 	-0.190344684920137, 	0.000000000000000, 	-1.719386356896355, 	0.000000000000000, 	
+-2.827721754659679, 	0.000000000000000, 	-0.092438285279020, 	0.000000000000000, 	-0.565844430675246, 	0.000000000000000, 	-1.077916121691716, 	0.000000000000000, 	
+-1.208665809504693, 	0.000000000000000, 	-2.996014266381254, 	0.000000000000000, 	2.888573323402423, 	0.000000000000000, 	2.829507048720695, 	0.000000000000000, 	
+-0.859177034120755, 	0.000000000000000, 	-1.969302377743254, 	0.000000000000000, 	0.777437674525362, 	0.000000000000000, 	-0.124910190157646, 	0.000000000000000, 	
+0.129875493115290, 	0.000000000000000, 	-4.192139262163992, 	0.000000000000000, 	3.023496047962126, 	0.000000000000000, 	1.149775163736637, 	0.000000000000000, 	
+2.038151304801731, 	0.000000000000000, 	3.016122489841263, 	0.000000000000000, 	-4.829481812137012, 	0.000000000000000, 	-1.668436615909279, 	0.000000000000000, 	
+0.958586784636918, 	0.000000000000000, 	1.550652410058678, 	0.000000000000000, 	-1.456305257976716, 	0.000000000000000, 	-0.079588392344731, 	0.000000000000000, 	
+-2.453213599392345, 	0.000000000000000, 	0.296795909127105, 	0.000000000000000, 	-0.253426616607643, 	0.000000000000000, 	1.418937160028195, 	0.000000000000000, 	
+-1.672949529066915, 	0.000000000000000, 	-1.620990298572947, 	0.000000000000000, 	-1.085103073196045, 	0.000000000000000, 	0.738606361195386, 	0.000000000000000, 	
+-2.097831202853255, 	0.000000000000000, 	2.711952282071310, 	0.000000000000000, 	1.498539238246888, 	0.000000000000000, 	1.317457282535915, 	0.000000000000000, 	
+-0.302765938349717, 	0.000000000000000, 	-0.044623707947201, 	0.000000000000000, 	2.337405215062395, 	0.000000000000000, 	-3.980689173859100, 	0.000000000000000, 	
+
+
+};
+

libs/CMSIS/DSP_Lib/Examples/arm_fft_bin_example/arm_fft_bin_example_f32.c

@@ -0,0 +1,152 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3  
+*  
+* Project: 	    CMSIS DSP Library  
+* Title:	    arm_fft_bin_example_f32.c		  
+*  
+* Description:	Example code demonstrating calculation of Max energy bin of  
+*				frequency domain of input signal. 
+* 
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup FrequencyBin Frequency Bin Example    
+ * 
+ * \par Description
+ * \par
+ * Demonstrates the calculation of the maximum energy bin in the frequency 
+ * domain of the input signal with the use of Complex FFT, Complex 
+ * Magnitude, and Maximum functions. 
+ * 
+ * \par Algorithm:
+ * \par
+ * The input test signal contains a 10 kHz signal with uniformly distributed white noise.  
+ * Calculating the FFT of the input signal will give us the maximum energy of the 
+ * bin corresponding to the input frequency of 10 kHz.  
+ * 
+ * \par Block Diagram:
+ * \image html FFTBin.gif "Block Diagram"
+ * \par
+ * The figure below shows the time domain signal of 10 kHz signal with 
+ * uniformly distributed white noise, and the next figure shows the input
+ * in the frequency domain. The bin with maximum energy corresponds to 10 kHz signal. 
+ * \par
+ * \image html FFTBinInput.gif "Input signal in Time domain" 
+ * \image html FFTBinOutput.gif "Input signal in Frequency domain"
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c testInput_f32_10khz points to the input data
+ * \li \c testOutput points to the output data
+ * \li \c fftSize length of FFT
+ * \li \c ifftFlag flag for the selection of CFFT/CIFFT
+ * \li \c doBitReverse Flag for selection of normal order or bit reversed order
+ * \li \c refIndex reference index value at which maximum energy of bin ocuurs
+ * \li \c testIndex calculated index value at which maximum energy of bin ocuurs
+ * 
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_cfft_radix4_init_f32()
+ * - arm_cfft_radix4_f32()
+ * - arm_cmplx_mag_f32()
+ * - arm_max_f32()
+ *
+ * <b> Refer  </b> 
+ * \link arm_fft_bin_example_f32.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_fft_bin_example_f32.c 
+  */  
+
+     
+#include "arm_math.h" 
+ 
+#define TEST_LENGTH_SAMPLES 2048 
+ 
+/* ------------------------------------------------------------------- 
+* External Input and Output buffer Declarations for FFT Bin Example 
+* ------------------------------------------------------------------- */ 
+extern float32_t testInput_f32_10khz[TEST_LENGTH_SAMPLES]; 
+static float32_t testOutput[TEST_LENGTH_SAMPLES/2]; 
+ 
+/* ------------------------------------------------------------------ 
+* Global variables for FFT Bin Example 
+* ------------------------------------------------------------------- */ 
+uint32_t fftSize = 1024; 
+uint32_t ifftFlag = 0; 
+uint32_t doBitReverse = 1; 
+ 
+/* Reference index at which max energy of bin ocuurs */ 
+uint32_t refIndex = 213, testIndex = 0; 
+ 
+/* ---------------------------------------------------------------------- 
+* Max magnitude FFT Bin test 
+* ------------------------------------------------------------------- */ 
+ 
+int32_t main(void) 
+{ 
+   
+	arm_status status; 
+	arm_cfft_radix4_instance_f32 S; 
+	float32_t maxValue; 
+	 
+	status = ARM_MATH_SUCCESS; 
+	 
+	/* Initialize the CFFT/CIFFT module */  
+	status = arm_cfft_radix4_init_f32(&S, fftSize,  
+	  								ifftFlag, doBitReverse); 
+	 
+	/* Process the data through the CFFT/CIFFT module */ 
+	arm_cfft_radix4_f32(&S, testInput_f32_10khz); 
+	 
+	 
+	/* Process the data through the Complex Magnitude Module for  
+	calculating the magnitude at each bin */ 
+	arm_cmplx_mag_f32(testInput_f32_10khz, testOutput,  
+	  				fftSize);  
+	 
+	/* Calculates maxValue and returns corresponding BIN value */ 
+	arm_max_f32(testOutput, fftSize, &maxValue, &testIndex); 
+	 
+	if(testIndex !=  refIndex) 
+	{ 
+		status = ARM_MATH_TEST_FAILURE; 
+	} 
+	 
+	/* ---------------------------------------------------------------------- 
+	** Loop here if the signals fail the PASS check. 
+	** This denotes a test failure 
+	** ------------------------------------------------------------------- */ 
+	 
+	if( status != ARM_MATH_SUCCESS) 
+	{ 
+		while(1); 
+	} 
+
+    while(1);                             /* main function does not return */
+} 
+ 
+ /** \endlink */ 
+ 
+ 
+ 

libs/CMSIS/DSP_Lib/Examples/arm_fir_example/arm_fir_data.c

@@ -0,0 +1,94 @@
+#include "arm_math.h"
+
+/* ----------------------------------------------------------------------
+** Test input signal contains 1000Hz + 15000 Hz
+** ------------------------------------------------------------------- */
+
+float32_t testInput_f32_1kHz_15kHz[320] =
+{
++0.0000000000f, +0.5924659585f, -0.0947343455f, +0.1913417162f, +1.0000000000f, +0.4174197128f, +0.3535533906f, +1.2552931065f, 
++0.8660254038f, +0.4619397663f, +1.3194792169f, +1.1827865776f, +0.5000000000f, +1.1827865776f, +1.3194792169f, +0.4619397663f, 
++0.8660254038f, +1.2552931065f, +0.3535533906f, +0.4174197128f, +1.0000000000f, +0.1913417162f, -0.0947343455f, +0.5924659585f, 
+-0.0000000000f, -0.5924659585f, +0.0947343455f, -0.1913417162f, -1.0000000000f, -0.4174197128f, -0.3535533906f, -1.2552931065f, 
+-0.8660254038f, -0.4619397663f, -1.3194792169f, -1.1827865776f, -0.5000000000f, -1.1827865776f, -1.3194792169f, -0.4619397663f, 
+-0.8660254038f, -1.2552931065f, -0.3535533906f, -0.4174197128f, -1.0000000000f, -0.1913417162f, +0.0947343455f, -0.5924659585f, 
++0.0000000000f, +0.5924659585f, -0.0947343455f, +0.1913417162f, +1.0000000000f, +0.4174197128f, +0.3535533906f, +1.2552931065f, 
++0.8660254038f, +0.4619397663f, +1.3194792169f, +1.1827865776f, +0.5000000000f, +1.1827865776f, +1.3194792169f, +0.4619397663f, 
++0.8660254038f, +1.2552931065f, +0.3535533906f, +0.4174197128f, +1.0000000000f, +0.1913417162f, -0.0947343455f, +0.5924659585f, 
++0.0000000000f, -0.5924659585f, +0.0947343455f, -0.1913417162f, -1.0000000000f, -0.4174197128f, -0.3535533906f, -1.2552931065f, 
+-0.8660254038f, -0.4619397663f, -1.3194792169f, -1.1827865776f, -0.5000000000f, -1.1827865776f, -1.3194792169f, -0.4619397663f, 
+-0.8660254038f, -1.2552931065f, -0.3535533906f, -0.4174197128f, -1.0000000000f, -0.1913417162f, +0.0947343455f, -0.5924659585f, 
++0.0000000000f, +0.5924659585f, -0.0947343455f, +0.1913417162f, +1.0000000000f, +0.4174197128f, +0.3535533906f, +1.2552931065f, 
++0.8660254038f, +0.4619397663f, +1.3194792169f, +1.1827865776f, +0.5000000000f, +1.1827865776f, +1.3194792169f, +0.4619397663f, 
++0.8660254038f, +1.2552931065f, +0.3535533906f, +0.4174197128f, +1.0000000000f, +0.1913417162f, -0.0947343455f, +0.5924659585f, 
++0.0000000000f, -0.5924659585f, +0.0947343455f, -0.1913417162f, -1.0000000000f, -0.4174197128f, -0.3535533906f, -1.2552931065f, 
+-0.8660254038f, -0.4619397663f, -1.3194792169f, -1.1827865776f, -0.5000000000f, -1.1827865776f, -1.3194792169f, -0.4619397663f, 
+-0.8660254038f, -1.2552931065f, -0.3535533906f, -0.4174197128f, -1.0000000000f, -0.1913417162f, +0.0947343455f, -0.5924659585f, 
+-0.0000000000f, +0.5924659585f, -0.0947343455f, +0.1913417162f, +1.0000000000f, +0.4174197128f, +0.3535533906f, +1.2552931065f, 
++0.8660254038f, +0.4619397663f, +1.3194792169f, +1.1827865776f, +0.5000000000f, +1.1827865776f, +1.3194792169f, +0.4619397663f, 
++0.8660254038f, +1.2552931065f, +0.3535533906f, +0.4174197128f, +1.0000000000f, +0.1913417162f, -0.0947343455f, +0.5924659585f, 
+-0.0000000000f, -0.5924659585f, +0.0947343455f, -0.1913417162f, -1.0000000000f, -0.4174197128f, -0.3535533906f, -1.2552931065f, 
+-0.8660254038f, -0.4619397663f, -1.3194792169f, -1.1827865776f, -0.5000000000f, -1.1827865776f, -1.3194792169f, -0.4619397663f, 
+-0.8660254038f, -1.2552931065f, -0.3535533906f, -0.4174197128f, -1.0000000000f, -0.1913417162f, +0.0947343455f, -0.5924659585f, 
++0.0000000000f, +0.5924659585f, -0.0947343455f, +0.1913417162f, +1.0000000000f, +0.4174197128f, +0.3535533906f, +1.2552931065f, 
++0.8660254038f, +0.4619397663f, +1.3194792169f, +1.1827865776f, +0.5000000000f, +1.1827865776f, +1.3194792169f, +0.4619397663f, 
++0.8660254038f, +1.2552931065f, +0.3535533906f, +0.4174197128f, +1.0000000000f, +0.1913417162f, -0.0947343455f, +0.5924659585f, 
++0.0000000000f, -0.5924659585f, +0.0947343455f, -0.1913417162f, -1.0000000000f, -0.4174197128f, -0.3535533906f, -1.2552931065f, 
+-0.8660254038f, -0.4619397663f, -1.3194792169f, -1.1827865776f, -0.5000000000f, -1.1827865776f, -1.3194792169f, -0.4619397663f, 
+-0.8660254038f, -1.2552931065f, -0.3535533906f, -0.4174197128f, -1.0000000000f, -0.1913417162f, +0.0947343455f, -0.5924659585f, 
+-0.0000000000f, +0.5924659585f, -0.0947343455f, +0.1913417162f, +1.0000000000f, +0.4174197128f, +0.3535533906f, +1.2552931065f, 
++0.8660254038f, +0.4619397663f, +1.3194792169f, +1.1827865776f, +0.5000000000f, +1.1827865776f, +1.3194792169f, +0.4619397663f, 
++0.8660254038f, +1.2552931065f, +0.3535533906f, +0.4174197128f, +1.0000000000f, +0.1913417162f, -0.0947343455f, +0.5924659585f, 
++0.0000000000f, -0.5924659585f, +0.0947343455f, -0.1913417162f, -1.0000000000f, -0.4174197128f, -0.3535533906f, -1.2552931065f, 
+-0.8660254038f, -0.4619397663f, -1.3194792169f, -1.1827865776f, -0.5000000000f, -1.1827865776f, -1.3194792169f, -0.4619397663f, 
+-0.8660254038f, -1.2552931065f, -0.3535533906f, -0.4174197128f, -1.0000000000f, -0.1913417162f, +0.0947343455f, -0.5924659585f, 
+-0.0000000000f, +0.5924659585f, -0.0947343455f, +0.1913417162f, +1.0000000000f, +0.4174197128f, +0.3535533906f, +1.2552931065f, 
++0.8660254038f, +0.4619397663f, +1.3194792169f, +1.1827865776f, +0.5000000000f, +1.1827865776f, +1.3194792169f, +0.4619397663f, 
++0.8660254038f, +1.2552931065f, +0.3535533906f, +0.4174197128f, +1.0000000000f, +0.1913417162f, -0.0947343455f, +0.5924659585f, 
++0.0000000000f, -0.5924659585f, +0.0947343455f, -0.1913417162f, -1.0000000000f, -0.4174197128f, -0.3535533906f, -1.2552931065f, 
+};
+
+float32_t refOutput[320] = 
+{
++0.0000000000f, -0.0010797829f, -0.0007681386f, -0.0001982932f, +0.0000644313f, +0.0020854271f, +0.0036891871f, +0.0015855941f, 
+-0.0026280805f, -0.0075907658f, -0.0119390538f, -0.0086665968f, +0.0088981202f, +0.0430539279f, +0.0974468742f, +0.1740405600f, 
++0.2681416601f, +0.3747720089f, +0.4893362230f, +0.6024154672f, +0.7058740791f, +0.7968348987f, +0.8715901940f, +0.9277881093f, 
++0.9682182661f, +0.9934674267f, +1.0012052245f, +0.9925859371f, +0.9681538347f, +0.9257026822f, +0.8679010068f, +0.7952493046f, 
++0.7085021596f, +0.6100062330f, +0.5012752767f, +0.3834386057f, +0.2592435399f, +0.1309866321f, -0.0000000000f, -0.1309866321f, 
+-0.2592435399f, -0.3834386057f, -0.5012752767f, -0.6100062330f, -0.7085021596f, -0.7952493046f, -0.8679010068f, -0.9257026822f, 
+-0.9681538347f, -0.9936657199f, -1.0019733630f, -0.9936657199f, -0.9681538347f, -0.9257026822f, -0.8679010068f, -0.7952493046f, 
+-0.7085021596f, -0.6100062330f, -0.5012752767f, -0.3834386057f, -0.2592435399f, -0.1309866321f, +0.0000000000f, +0.1309866321f, 
++0.2592435399f, +0.3834386057f, +0.5012752767f, +0.6100062330f, +0.7085021596f, +0.7952493046f, +0.8679010068f, +0.9257026822f, 
++0.9681538347f, +0.9936657199f, +1.0019733630f, +0.9936657199f, +0.9681538347f, +0.9257026822f, +0.8679010068f, +0.7952493046f, 
++0.7085021596f, +0.6100062330f, +0.5012752767f, +0.3834386057f, +0.2592435399f, +0.1309866321f, -0.0000000000f, -0.1309866321f, 
+-0.2592435399f, -0.3834386057f, -0.5012752767f, -0.6100062330f, -0.7085021596f, -0.7952493046f, -0.8679010068f, -0.9257026822f, 
+-0.9681538347f, -0.9936657199f, -1.0019733630f, -0.9936657199f, -0.9681538347f, -0.9257026822f, -0.8679010068f, -0.7952493046f, 
+-0.7085021596f, -0.6100062330f, -0.5012752767f, -0.3834386057f, -0.2592435399f, -0.1309866321f, +0.0000000000f, +0.1309866321f, 
++0.2592435399f, +0.3834386057f, +0.5012752767f, +0.6100062330f, +0.7085021596f, +0.7952493046f, +0.8679010068f, +0.9257026822f, 
++0.9681538347f, +0.9936657199f, +1.0019733630f, +0.9936657199f, +0.9681538347f, +0.9257026822f, +0.8679010068f, +0.7952493046f, 
++0.7085021596f, +0.6100062330f, +0.5012752767f, +0.3834386057f, +0.2592435399f, +0.1309866321f, -0.0000000000f, -0.1309866321f, 
+-0.2592435399f, -0.3834386057f, -0.5012752767f, -0.6100062330f, -0.7085021596f, -0.7952493046f, -0.8679010068f, -0.9257026822f, 
+-0.9681538347f, -0.9936657199f, -1.0019733630f, -0.9936657199f, -0.9681538347f, -0.9257026822f, -0.8679010068f, -0.7952493046f, 
+-0.7085021596f, -0.6100062330f, -0.5012752767f, -0.3834386057f, -0.2592435399f, -0.1309866321f, +0.0000000000f, +0.1309866321f, 
++0.2592435399f, +0.3834386057f, +0.5012752767f, +0.6100062330f, +0.7085021596f, +0.7952493046f, +0.8679010068f, +0.9257026822f, 
++0.9681538347f, +0.9936657199f, +1.0019733630f, +0.9936657199f, +0.9681538347f, +0.9257026822f, +0.8679010068f, +0.7952493046f, 
++0.7085021596f, +0.6100062330f, +0.5012752767f, +0.3834386057f, +0.2592435399f, +0.1309866321f, +0.0000000000f, -0.1309866321f, 
+-0.2592435399f, -0.3834386057f, -0.5012752767f, -0.6100062330f, -0.7085021596f, -0.7952493046f, -0.8679010068f, -0.9257026822f, 
+-0.9681538347f, -0.9936657199f, -1.0019733630f, -0.9936657199f, -0.9681538347f, -0.9257026822f, -0.8679010068f, -0.7952493046f, 
+-0.7085021596f, -0.6100062330f, -0.5012752767f, -0.3834386057f, -0.2592435399f, -0.1309866321f, +0.0000000000f, +0.1309866321f, 
++0.2592435399f, +0.3834386057f, +0.5012752767f, +0.6100062330f, +0.7085021596f, +0.7952493046f, +0.8679010068f, +0.9257026822f, 
++0.9681538347f, +0.9936657199f, +1.0019733630f, +0.9936657199f, +0.9681538347f, +0.9257026822f, +0.8679010068f, +0.7952493046f, 
++0.7085021596f, +0.6100062330f, +0.5012752767f, +0.3834386057f, +0.2592435399f, +0.1309866321f, +0.0000000000f, -0.1309866321f, 
+-0.2592435399f, -0.3834386057f, -0.5012752767f, -0.6100062330f, -0.7085021596f, -0.7952493046f, -0.8679010068f, -0.9257026822f, 
+-0.9681538347f, -0.9936657199f, -1.0019733630f, -0.9936657199f, -0.9681538347f, -0.9257026822f, -0.8679010068f, -0.7952493046f, 
+-0.7085021596f, -0.6100062330f, -0.5012752767f, -0.3834386057f, -0.2592435399f, -0.1309866321f, -0.0000000000f, +0.1309866321f, 
++0.2592435399f, +0.3834386057f, +0.5012752767f, +0.6100062330f, +0.7085021596f, +0.7952493046f, +0.8679010068f, +0.9257026822f, 
++0.9681538347f, +0.9936657199f, +1.0019733630f, +0.9936657199f, +0.9681538347f, +0.9257026822f, +0.8679010068f, +0.7952493046f, 
++0.7085021596f, +0.6100062330f, +0.5012752767f, +0.3834386057f, +0.2592435399f, +0.1309866321f, +0.0000000000f, -0.1309866321f, 
+-0.2592435399f, -0.3834386057f, -0.5012752767f, -0.6100062330f, -0.7085021596f, -0.7952493046f, -0.8679010068f, -0.9257026822f, 
+-0.9681538347f, -0.9936657199f, -1.0019733630f, -0.9936657199f, -0.9681538347f, -0.9257026822f, -0.8679010068f, -0.7952493046f, 
+-0.7085021596f, -0.6100062330f, -0.5012752767f, -0.3834386057f, -0.2592435399f, -0.1309866321f, +0.0000000000f, +0.1309866321f, 
++0.2592435399f, +0.3834386057f, +0.5012752767f, +0.6100062330f, +0.7085021596f, +0.7952493046f, +0.8679010068f, +0.9257026822f, 
++0.9681538347f, +0.9936657199f, +1.0019733630f, +0.9936657199f, +0.9681538347f, +0.9257026822f, +0.8679010068f, +0.7952493046f 
+};
+

libs/CMSIS/DSP_Lib/Examples/arm_fir_example/arm_fir_example_f32.c

@@ -0,0 +1,220 @@
+/* ---------------------------------------------------------------------- 
+ * Copyright (C) 2010 ARM Limited. All rights reserved.   
+ *  
+ * $Date:           29. November 2010  
+ * $Revision: 	    V1.0.3  
+ *  
+ * Project: 	    CMSIS DSP Library  
+ * Title:	        arm_fir_example_f32.c		  
+ *  
+ * Description:	Example code demonstrating how an FIR filter can be used
+ *               as a low pass filter.
+ * 
+ * Target Processor: Cortex-M4/Cortex-M3  
+ *
+ *
+ * Version 1.0.3 2010/11/29 
+ *    Re-organized the CMSIS folders and updated documentation. 
+ * 
+ * Version 1.0.1 2010/10/05 KK 
+ *    Production release and review comments incorporated.  
+ *
+ * Version 1.0.0 2010/09/20 KK
+ *    Production release and review comments incorporated.
+ * ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup FIRLPF FIR Lowpass Filter Example
+ * 
+ * \par Description: 
+ * \par
+ * Removes high frequency signal components from the input using an FIR lowpass filter.
+ * The example demonstrates how to configure an FIR filter and then pass data through
+ * it in a block-by-block fashion.
+ * \image html FIRLPF_signalflow.gif 
+ * 
+ * \par Algorithm:
+ * \par
+ * The input signal is a sum of two sine waves:  1 kHz and 15 kHz.
+ * This is processed by an FIR lowpass filter with cutoff frequency 6 kHz.
+ * The lowpass filter eliminates the 15 kHz signal leaving only the 1 kHz sine wave at the output.
+ * \par
+ * The lowpass filter was designed using MATLAB with a sample rate of 48 kHz and 
+ * a length of 29 points.
+ * The MATLAB code to generate the filter coefficients is shown below:
+ * <pre>
+ *     h = fir1(28, 6/24);
+ * </pre>
+ * The first argument is the "order" of the filter and is always one less than the desired length.
+ * The second argument is the normalized cutoff frequency.  This is in the range 0 (DC) to 1.0 (Nyquist).
+ * A 6 kHz cutoff with a Nyquist frequency of 24 kHz lies at a normalized frequency of 6/24 = 0.25.
+ * The CMSIS FIR filter function requires the coefficients to be in time reversed order.
+ * <pre>
+ *     fliplr(h)
+ * </pre>
+ * The resulting filter coefficients and are shown below.  
+ * Note that the filter is symmetric (a property of linear phase FIR filters)
+ * and the point of symmetry is sample 14.  Thus the filter will have a delay of
+ * 14 samples for all frequencies.
+ * \par
+ * \image html FIRLPF_coeffs.gif 
+ * \par
+ * The frequency response of the filter is shown next.  
+ * The passband gain of the filter is 1.0 and it reaches 0.5 at the cutoff frequency 6 kHz.
+ * \par
+ * \image html FIRLPF_response.gif 
+ * \par
+ * The input signal is shown below.
+ * The left hand side shows the signal in the time domain while the right hand side is a frequency domain representation.
+ * The two sine wave components can be clearly seen.
+ * \par
+ * \image html FIRLPF_input.gif 
+ * \par
+ * The output of the filter is shown below.  The 15 kHz component has been eliminated.
+ * \par
+ * \image html FIRLPF_output.gif 
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c testInput_f32_1kHz_15kHz points to the input data
+ * \li \c refOutput points to the reference output data
+ * \li \c testOutput points to the test output data
+ * \li \c firStateF32 points to state buffer
+ * \li \c firCoeffs32 points to coefficient buffer
+ * \li \c blockSize number of samples processed at a time
+ * \li \c numBlocks number of frames 
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_fir_init_f32()
+ * - arm_fir_f32() 
+ * 
+ * <b> Refer  </b> 
+ * \link arm_fir_example_f32.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_fir_example_f32.c 
+ */  
+ 
+/* ---------------------------------------------------------------------- 
+** Include Files  
+** ------------------------------------------------------------------- */ 
+
+#include "arm_math.h" 
+#include "math_helper.h" 
+ 
+/* ---------------------------------------------------------------------- 
+** Macro Defines  
+** ------------------------------------------------------------------- */ 
+
+#define TEST_LENGTH_SAMPLES 320 
+#define SNR_THRESHOLD_F32	140.0f 
+#define BLOCK_SIZE			32 
+#define NUM_TAPS			29 
+ 
+/* ------------------------------------------------------------------- 
+ * The input signal and reference output (computed with MATLAB)
+ * are defined externally in arm_fir_lpf_data.c.
+ * ------------------------------------------------------------------- */ 
+
+extern float32_t testInput_f32_1kHz_15kHz[TEST_LENGTH_SAMPLES]; 
+extern float32_t refOutput[TEST_LENGTH_SAMPLES]; 
+ 
+/* ------------------------------------------------------------------- 
+ * Declare Test output buffer 
+ * ------------------------------------------------------------------- */ 
+
+static float32_t testOutput[TEST_LENGTH_SAMPLES]; 
+ 
+/* ------------------------------------------------------------------- 
+ * Declare State buffer of size (numTaps + blockSize - 1) 
+ * ------------------------------------------------------------------- */ 
+
+static float32_t firStateF32[BLOCK_SIZE + NUM_TAPS - 1]; 
+ 
+/* ---------------------------------------------------------------------- 
+** FIR Coefficients buffer generated using fir1() MATLAB function. 
+** fir1(28, 6/24)
+** ------------------------------------------------------------------- */ 
+ 
+const float32_t firCoeffs32[NUM_TAPS] = { 
+-0.0018225230f, -0.0015879294f, +0.0000000000f, +0.0036977508f, +0.0080754303f, +0.0085302217f, -0.0000000000f, -0.0173976984f, 
+-0.0341458607f, -0.0333591565f, +0.0000000000f, +0.0676308395f, +0.1522061835f, +0.2229246956f, +0.2504960933f, +0.2229246956f, 
++0.1522061835f, +0.0676308395f, +0.0000000000f, -0.0333591565f, -0.0341458607f, -0.0173976984f, -0.0000000000f, +0.0085302217f, 
++0.0080754303f, +0.0036977508f, +0.0000000000f, -0.0015879294f, -0.0018225230f 
+}; 
+ 
+/* ------------------------------------------------------------------ 
+ * Global variables for FIR LPF Example 
+ * ------------------------------------------------------------------- */ 
+
+uint32_t blockSize = BLOCK_SIZE; 
+uint32_t numBlocks = TEST_LENGTH_SAMPLES/BLOCK_SIZE; 
+ 
+float32_t  snr; 
+ 
+/* ---------------------------------------------------------------------- 
+ * FIR LPF Example 
+ * ------------------------------------------------------------------- */ 
+ 
+int32_t main(void) 
+{ 
+  uint32_t i; 
+  arm_fir_instance_f32 S; 
+  arm_status status; 
+  float32_t  *inputF32, *outputF32; 
+ 
+  /* Initialize input and output buffer pointers */ 
+  inputF32 = &testInput_f32_1kHz_15kHz[0];	 
+  outputF32 = &testOutput[0]; 
+
+  /* Call FIR init function to initialize the instance structure. */
+  arm_fir_init_f32(&S, NUM_TAPS, (float32_t *)&firCoeffs32[0], &firStateF32[0], blockSize); 
+ 
+  /* ---------------------------------------------------------------------- 
+  ** Call the FIR process function for every blockSize samples  
+  ** ------------------------------------------------------------------- */ 
+
+  for(i=0; i < numBlocks; i++)  
+    {	 
+      arm_fir_f32(&S, inputF32 + (i * blockSize), outputF32 + (i * blockSize), blockSize);  
+    } 
+ 
+  /* ---------------------------------------------------------------------- 
+  ** Compare the generated output against the reference output computed
+  ** in MATLAB.
+  ** ------------------------------------------------------------------- */ 
+
+  snr = arm_snr_f32(&refOutput[0], &testOutput[0], TEST_LENGTH_SAMPLES); 
+ 
+  if (snr < SNR_THRESHOLD_F32) 
+    { 
+      status = ARM_MATH_TEST_FAILURE; 
+    } 
+  else
+    {
+      status = ARM_MATH_SUCCESS; 
+    }
+	 
+  /* ---------------------------------------------------------------------- 
+  ** Loop here if the signal does not match the reference output.
+  ** ------------------------------------------------------------------- */ 
+	 
+  if( status != ARM_MATH_SUCCESS) 
+    { 
+      while(1); 
+    } 
+
+    while(1);                             /* main function does not return */
+} 
+ 
+/** \endlink */ 
+ 
+ 
+ 

libs/CMSIS/DSP_Lib/Examples/arm_graphic_equalizer_example/arm_graphic_equalizer_data.c

@@ -0,0 +1,94 @@
+#include "arm_math.h"
+
+float32_t testRefOutput_f32[320] = {
+
+0.000000000000000000,	0.001898396760225296,	0.004215449094772339,	0.007432077080011368,	0.010948467999696732,	0.015026375651359558,	0.019191544502973557,	0.023574527353048325,	
+0.027919445186853409,	0.032277785241603851,	0.036551639437675476,	0.040732793509960175,	0.044799156486988068,	0.048710610717535019,	0.052476800978183746,	0.056059073656797409,	
+0.059482168406248093,	0.062726479023694992,	0.065821025520563126,	0.068763464689254761,	0.071577839553356171,	0.074270240962505341,	0.076856281608343124,	0.079344697296619415,	
+0.081745062023401260,	0.084067162126302719,	0.086318407207727432,	0.088509257882833481,	0.090647127479314804,	0.092742368578910828,	0.094802625477313995,	0.096837285906076431,	
+0.098853722214698792,	0.100859899073839190,	0.102862443774938580,	0.104867763817310330,	0.106881409883499150,	0.108908228576183320,	0.110952425748109820,	0.113017357885837550,	
+0.115105822682380680,	0.117219865322113040,	0.119361080229282380,	0.121530555188655850,	0.123729091137647630,	0.125957202166318890,	0.128215309232473370,	0.130503740161657330,	
+0.132822841405868530,	0.135173004120588300,	0.137554679065942760,	0.139968376606702800,	0.142414685338735580,	0.144894234836101530,	0.147407654672861100,	0.149955596774816510,	
+0.152538605034351350,	0.155157200992107390,	0.157811731100082400,	0.160502441227436070,	0.163229387253522870,	0.165992442518472670,	0.168791320174932480,	0.171625509858131410,	
+0.174494370818138120,	0.177397061139345170,	0.180332608520984650,	0.183299910277128220,	0.186297744512557980,	0.189324837177991870,	0.192379791289567950,	0.195461250841617580,	
+0.198567759245634080,	0.201697919517755510,	0.204850304871797560,	0.208023533225059510,	0.211216274648904800,	0.214427210390567780,	0.217655111104249950,	0.220898788422346120,	
+0.224157124757766720,	0.227429077029228210,	0.230713658034801480,	0.234009962528944020,	0.237317133694887160,	0.240634419023990630,	0.243961080908775330,	0.247296508401632310,	
+0.250640105456113820,	0.253991369158029560,	0.257349837571382520,	0.260715119540691380,	0.264086868613958360,	0.267464816570281980,	0.270848698914051060,	0.274238351732492450,	
+0.277633611112833020,	0.281034380197525020,	0.284440591931343080,	0.287852220237255100,	0.291269283741712570,	0.294691801071166990,	0.298119872808456420,	0.301553562283515930,	
+0.304993014782667160,	0.308438356965780260,	0.311889752745628360,	0.315347377210855480,	0.318811416625976560,	0.322282072156667710,	0.325759567320346830,	0.329244095832109450,	
+0.332735907286405560,	0.336235217750072480,	0.339742250740528110,	0.343257248401641850,	0.346780419349670410,	0.350311983376741410,	0.353852160274982450,	0.357401121407747270,	
+0.360959105193614960,	0.364526227116584780,	0.368102725595235820,	0.371688675135374070,	0.375284302979707720,	0.378889638930559160,	0.382504884153604510,	0.386130042374134060,	
+0.389765247702598570,	0.393410529941320420,	0.397065933793783190,	0.400731507688760760,	0.404407206922769550,	0.408093083649873730,	0.411789052188396450,	0.415495119988918300,	
+0.419211201369762420,	0.422937240451574330,	0.426673140376806260,	0.430418811738491060,	0.434174135327339170,	0.437938995659351350,	0.441713258624076840,	0.445496778935194020,	
+0.449289388954639430,	0.453090950846672060,	0.456901267170906070,	0.460720170289278030,	0.464547459036111830,	0.468382950872182850,	0.472226426005363460,	0.476077698171138760,	
+0.479936532676219940,	0.483802750706672670,	0.487676106393337250,	0.491556398570537570,	0.495443399995565410,	0.499336875975131990,	0.503236617892980580,	0.507142387330532070,	
+0.511053957045078280,	0.514971107244491580,	0.518893606960773470,	0.522821225225925450,	0.526753749698400500,	0.530690938234329220,	0.534632585942745210,	0.538578454405069350,	
+0.542528338730335240,	0.546481993049383160,	0.550439231097698210,	0.554399792104959490,	0.558363504707813260,	0.562330115586519240,	0.566299438476562500,	0.570271246135234830,	
+0.574245333671569820,	0.578221492469310760,	0.582199502736330030,	0.586179181933403020,	0.590160276740789410,	0.594142623245716090,	0.598125983029603960,	0.602110169827938080,	
+0.606094967573881150,	0.610080175101757050,	0.614065583795309070,	0.618050977587699890,	0.622036151587963100,	0.626020893454551700,	0.630004994571208950,	0.633988231420516970,	
+0.637970402836799620,	0.641951277852058410,	0.645930647850036620,	0.649908289313316350,	0.653883971273899080,	0.657857488840818410,	0.661828581243753430,	0.665797054767608640,	
+0.669762641191482540,	0.673725124448537830,	0.677684243768453600,	0.681639779359102250,	0.685591462999582290,	0.689539063721895220,	0.693482317030429840,	0.697420965880155560,	
+0.701354760676622390,	0.705283410847187040,	0.709206689149141310,	0.713124278932809830,	0.717035952955484390,	0.720941375941038130,	0.724840316921472550,	0.728732451796531680,	
+0.732617516070604320,	0.736495196819305420,	0.740365199744701390,	0.744227230548858640,	0.748080968856811520,	0.751926124095916750,	0.755762357264757160,	0.759589381515979770,	
+0.763406842947006230,	0.767214450985193250,	0.771011855453252790,	0.774798732250928880,	0.778574761003255840,	0.782339565455913540,	0.786092851310968400,	0.789834223687648770,	
+0.793563373386859890,	0.797279909253120420,	0.800983514636754990,	0.804673787206411360,	0.808350402861833570,	0.812012966722249980,	0.815661124885082240,	0.819294504821300510,	
+0.822912722826004030,	0.826515413820743560,	0.830102190375328060,	0.833672653883695600,	0.837226435542106630,	0.840763118118047710,	0.844282336533069610,	0.847783654928207400,	
+0.851266715675592420,	0.854731071740388870,	0.858176350593566890,	0.861602116376161580,	0.865007970482110980,	0.868393491953611370,	0.871758259832859040,	0.875101849436759950,	
+0.878423850983381270,	0.881723806262016300,	0.885001312941312790,	0.888255912810564040,	0.891487173736095430,	0.894694659858942030,	0.897877920418977740,	0.901036512106657030,	
+0.904169965535402300,	0.907277844846248630,	0.910359673202037810,	0.913415014743804930,	0.916443370282649990,	0.919444311410188670,	0.922417331486940380,	0.925361987203359600,	
+0.928277771919965740,	0.931164238601922990,	0.934020876884460450,	0.936847217381000520,	0.939642757177352910,	0.942407000809907910,	0.945139460265636440,	0.947839632630348210,	
+0.950507018715143200,	0.953141096979379650,	0.955741371959447860,	0.958307322114706040,	0.960838429629802700,	0.963334184139966960,	0.965794049203395840,	0.968217510730028150,	
+0.970604017376899720,	0.972953058779239650,	0.975264083594083790,	0.977536566555500030,	0.979769956320524220,	0.981963708996772770,	0.984117280691862110,	0.986230112612247470,	
+0.988301653414964680,	0.990331344306468960,	0.992318630218505860,	0.994262944906950000,	0.996163722127676010,	0.998020399361848830,	0.999832402914762500,	1.001599155366420700,	
+1.003320086747407900,	1.004994612187147100,	1.006622135639190700,	1.008202098309993700,	1.009733878076076500,	1.011216927319765100,	1.012650609016418500,	1.014034371823072400,	
+1.015367589890956900,	1.016649682074785200,	1.017880033701658200,	1.019058048725128200,	1.020183108747005500,	1.021254621446132700,	1.022271949797868700,	1.023234523832798000,	
+
+};
+/* ----------------------------------------------------------------------
+** Test input - logarithmic chirp signal
+** ------------------------------------------------------------------- */
+
+float32_t testInput_f32[320] =
+  {
+    0.000000000000000061,	0.002622410992047861,	0.005253663973466970,	0.007893770384930297,	0.010542741395035495,	0.013200587895525877,	0.015867320496454066,	0.018542949521290073,	
+0.021227485001971542,	0.023920936673895138,	0.026623313970853074,	0.029334626019908643,	0.032054881636210709,	0.034784089317753723,	0.037522257240071598,	0.040269393250875855,	
+0.043025504864628375,	0.045790599257054837,	0.048564683259595690,	0.051347763353792118,	0.054139845665610427,	0.056940935959702531,	0.059751039633601337,	0.062570161711849828,	
+0.065398306840066575,	0.068235479278943648,	0.071081682898178900,	0.073936921170339814,	0.076801197164660218,	0.079674513540768196,	0.082556872542344922,	0.085448275990715375,	
+0.088348725278367082,	0.091258221362398390,	0.094176764757897533,	0.097104355531246703,	0.100040993293358240,	0.102986677192832010,	0.105941405909045980,	0.108905177645166230,	
+0.111877990121087980,	0.114859840566297130,	0.117850725712659680,	0.120850641787131110,	0.123859584504392860,	0.126877549059407400,	0.129904530119898690,	0.132940521818751430,	
+0.135985517746334080,	0.139039510942737950,	0.142102493889940090,	0.145174458503884160,	0.148255396126476810,	0.151345297517508140,	0.154444152846483080,	0.157551951684374300,	
+0.160668682995289720,	0.163794335128054890,	0.166928895807713030,	0.170072352126936720,	0.173224690537355760,	0.176385896840798810,	0.179555956180445340,	0.182734853031894270,	
+0.185922571194139130,	0.189119093780459800,	0.192324403209221870,	0.195538481194587030,	0.198761308737133020,	0.201992866114384050,	0.205233132871247170,	0.208482087810360570,	
+0.211739708982344370,	0.215005973675965020,	0.218280858408200220,	0.221564338914212730,	0.224856390137231970,	0.228156986218334190,	0.231466100486134670,	0.234783705446379690,	
+0.238109772771442410,	0.241444273289723230,	0.244787176974952890,	0.248138452935395580,	0.251498069402956710,	0.254865993722190930,	0.258242192339209860,	0.261626630790492030,	
+0.265019273691591620,	0.268420084725748410,	0.271829026632395280,	0.275246061195565440,	0.278671149232197430,	0.282104250580339830,	0.285545324087251580,	0.288994327597401960,	
+0.292451217940364990,	0.295915950918612280,	0.299388481295203350,	0.302868762781368150,	0.306356748023990040,	0.309852388592980640,	0.313355634968552230,	0.316866436528383590,	
+0.320384741534681720,	0.323910497121136620,	0.327443649279772870,	0.330984142847692230,	0.334531921493712690,	0.338086927704900790,	0.341649102772995210,	0.345218386780727190,	
+0.348794718588032520,	0.352378035818156910,	0.355968274843654950,	0.359565370772282730,	0.363169257432780890,	0.366779867360555120,	0.370397131783246010,	0.374020980606193880,	
+0.377651342397795690,	0.381288144374756830,	0.384931312387234990,	0.388580770903877330,	0.392236442996751310,	0.395898250326170650,	0.399566113125414350,	0.403239950185338420,	
+0.406919678838884410,	0.410605214945482130,	0.414296472875345100,	0.417993365493664670,	0.421695804144698540,	0.425403698635752780,	0.429116957221065130,	0.432835486585582130,	
+0.436559191828633180,	0.440287976447505720,	0.444021742320914510,	0.447760389692375140,	0.451503817153472210,	0.455251921627031540,	0.459004598350192470,	0.462761740857380200,	
+0.466523240963184150,	0.470288988745136360,	0.474058872526396560,	0.477832778858340690,	0.481610592503056990,	0.485392196415748600,	0.489177471727042850,	0.492966297725213780,	
+0.496758551838309250,	0.500554109616195060,	0.504352844712508190,	0.508154628866524960,	0.511959331884944910,	0.515766821623591440,	0.519576963969030530,	0.523389622820107150,	
+0.527204660069405030,	0.531021935584629400,	0.534841307189911630,	0.538662630647041900,	0.542485759636628150,	0.546310545739186690,	0.550136838416161340,	0.553964484990880020,	
+0.557793330629441700,	0.561623218321546380,	0.565453988861259300,	0.569285480827721570,	0.573117530565801950,	0.576949972166696630,	0.580782637448476910,	0.584615355936589420,	
+0.588447954844309340,	0.592280259053150400,	0.596112091093235260,	0.599943271123626440,	0.603773616912622660,	0.607602943818024150,	0.611431064767369080,	0.615257790238142090,	
+0.619082928237961740,	0.622906284284749700,	0.626727661386881850,	0.630546860023327600,	0.634363678123782030,	0.638177911048790960,	0.641989351569874020,	0.645797789849653410,	
+0.649603013421986450,	0.653404807172108140,	0.657202953316791350,	0.660997231384523490,	0.664787418195706640,	0.668573287842887610,	0.672354611671016960,	0.676131158257749170,	
+0.679902693393781730,	0.683668980063242500,	0.687429778424128110,	0.691184845788802130,	0.694933936604551380,	0.698676802434213370,	0.702413191936877570,	0.706142850848662460,	
+0.709865521963579990,	0.713580945114492330,	0.717288857154159800,	0.720988991936399870,	0.724681080297347790,	0.728364850036839040,	0.732040025899910680,	0.735706329558433620,	
+0.739363479592880620,	0.743011191474238440,	0.746649177546067850,	0.750277147006723990,	0.753894805891742180,	0.757501857056394940,	0.761098000158428880,	0.764682931640995540,	
+0.768256344715771980,	0.771817929346292900,	0.775367372231492210,	0.778904356789468790,	0.782428563141483460,	0.785939668096195860,	0.789437345134148760,	0.792921264392515420,	
+0.796391092650110770,	0.799846493312681210,	0.803287126398485760,	0.806712648524170680,	0.810122712890953390,	0.813516969271127150,	0.816895063994893090,	0.820256639937531280,	
+0.823601336506926020,	0.826928789631450890,	0.830238631748229430,	0.833530491791779850,	0.836803995183058700,	0.840058763818912760,	0.843294416061954100,	0.846510566730867220,	
+0.849706827091166740,	0.852882804846411770,	0.856038104129895340,	0.859172325496819990,	0.862285065916973510,	0.865375918767918860,	0.868444473828712590,	0.871490317274166260,	
+0.874513031669661770,	0.877512195966544280,	0.880487385498096800,	0.883438171976119850,	0.886364123488128100,	0.889264804495180530,	0.892139775830360640,	0.894988594697921020,	
+0.897810814673113080,	0.900605985702712770,	0.903373654106265470,	0.906113362578062300,	0.908824650189867690,	0.911507052394417540,	0.914160101029702910,	0.916783324324059180,	
+0.919376246902079860,	0.921938389791372770,	0.924469270430179120,	0.926968402675872660,	0.929435296814361430,	0.931869459570409790,	0.934270394118903560,	0.936637600097074200,	
+0.938970573617708970,	0.941268807283364040,	0.943531790201601380,	0.945759008001275100,	0.947949942849885320,	0.950104073472023970,	0.952220875168933280,	0.954299819839202090,	
+0.956340376000621160,	0.958342008813221960,	0.960304180103520260,	0.962226348389994210,	0.964107968909812760,	0.965948493646846980,	0.967747371360983650,	0.969504047618768740,	
+0.971217964825405680,	0.972888562258134030,	0.974515276101013520,	0.976097539481141750,	0.977634782506330400,	0.979126432304266880,	0.980571913063189360,	0.981970646074102120,	
+0.983322049774557390,	0.984625539794035220,	0.985880529000944810,	0.987086427551279730,	0.988242642938953360,	0.989348580047844540,	0.990403641205582440,	0.991407226239099710,	
+0.992358732531984260,	0.993257555083659870,	0.994103086570423680,	0.994894717408374870,	0.995631835818261310,	0.996313827892278070,	0.996940077662846650,	0.997509967173408010,	
+
+  };

libs/CMSIS/DSP_Lib/Examples/arm_graphic_equalizer_example/arm_graphic_equalizer_example_q31.c

@@ -0,0 +1,395 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:         29. November 2010  
+* $Revision: 	  V1.0.3 
+*  
+* Project: 	  CMSIS DSP Library  
+* Title:	      arm_graphic_equalizer_example_q31.c		  
+*  
+* Description:	Example showing an audio graphic equalizer constructed
+*              out of Biquad filters.
+* 
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup GEQ5Band Graphic Audio Equalizer Example
+ * 
+ * \par Description: 
+ * \par
+ * This example demonstrates how a 5-band graphic equalizer can be constructed
+ * using the Biquad cascade functions.  
+ * A graphic equalizer is used in audio applications to vary the tonal quality
+ * of the audio.
+ *
+ * \par Block Diagram:
+ * \par
+ * The design is based on a cascade of 5 filter sections.
+ * \image html GEQ_signalflow.gif 
+ * Each filter section is 4th order and consists of a cascade of two Biquads.
+ * Each filter has a nominal gain of 0 dB (1.0 in linear units) and
+ * boosts or cuts signals within a specific frequency range.
+ * The edge frequencies between the 5 bands are 100, 500, 2000, and 6000 Hz.
+ * Each band has an adjustable boost or cut in the range of +/- 9 dB.
+ * For example, the band that extends from 500 to 2000 Hz has the response shown below:
+ * \par
+ * \image html GEQ_bandresponse.gif 
+ * \par
+ * With 1 dB steps, each filter has a total of 19 different settings.
+ * The filter coefficients for all possible 19 settings were precomputed
+ * in MATLAB and stored in a table.  With 5 different tables, there are
+ * a total of 5 x 19 = 95 different 4th order filters. 
+ * All 95 responses are shown below:
+ * \par
+ * \image html GEQ_allbandresponse.gif 
+ * \par
+ * Each 4th order filter has 10 coefficents for a grand total of 950 different filter
+ * coefficients that must be tabulated. The input and output data is in Q31 format.
+ * For better noise performance, the two low frequency bands are implemented using the high 
+ * precision 32x64-bit Biquad filters. The remaining 3 high frequency bands use standard 
+ * 32x32-bit Biquad filters. The input signal used in the example is a logarithmic chirp.
+ * \par
+ * \image html GEQ_inputchirp.gif
+ * \par
+ * The array <code>bandGains</code> specifies the gain in dB to apply in each band.
+ * For example, if <code>bandGains={0, -3, 6, 4, -6};</code> then the output signal will be:
+ * \par
+ * \image html GEQ_outputchirp.gif
+ * \par
+ * \note The output chirp signal follows the gain or boost of each band.
+ * \par
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c testInput_f32 points to the input data
+ * \li \c testRefOutput_f32 points to the reference output data
+ * \li \c testOutput points to the test output data
+ * \li \c inputQ31 temporary input buffer
+ * \li \c outputQ31 temporary output buffer 
+ * \li \c biquadStateBand1Q31 points to state buffer for band1
+ * \li \c biquadStateBand2Q31 points to state buffer for band2
+ * \li \c biquadStateBand3Q31 points to state buffer for band3
+ * \li \c biquadStateBand4Q31 points to state buffer for band4
+ * \li \c biquadStateBand5Q31 points to state buffer for band5
+ * \li \c coeffTable points to coefficient buffer for all bands
+ * \li \c gainDB gain buffer which has gains applied for all the bands
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_biquad_cas_df1_32x64_init_q31()
+ * - arm_biquad_cas_df1_32x64_q31()
+ * - arm_biquad_cascade_df1_init_q31()
+ * - arm_biquad_cascade_df1_q31()
+ * - arm_scale_q31()
+ * - arm_scale_f32()
+ * - arm_float_to_q31()
+ * - arm_q31_to_float()
+ *
+ * <b> Refer  </b> 
+ * \link arm_graphic_equalizer_example_q31.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_graphic_equalizer_example_q31.c 
+ */  
+ 
+     
+#include "arm_math.h" 
+#include "math_helper.h"
+
+/* Length of the overall data in the test */ 
+#define TESTLENGTH 320
+
+/* Block size for the underlying processing */
+#define BLOCKSIZE 32
+
+/* Total number of blocks to run */
+#define NUMBLOCKS (TESTLENGTH/BLOCKSIZE)
+
+/* Number of 2nd order Biquad stages per filter */
+#define NUMSTAGES 2
+
+#define SNR_THRESHOLD_F32  98
+ 
+/* ------------------------------------------------------------------- 
+ * External Declarations for Input and Output buffers 
+ * ------------------------------------------------------------------- */
+ 
+extern float32_t testInput_f32[TESTLENGTH]; 
+static float32_t testOutput[TESTLENGTH]; 
+
+extern float32_t testRefOutput_f32[TESTLENGTH];
+
+/* ----------------------------------------------------------------------  
+** Q31 state buffers for Band1, Band2, Band3, Band4, Band5  
+** ------------------------------------------------------------------- */  
+   
+static q63_t biquadStateBand1Q31[4 * 2];   
+static q63_t biquadStateBand2Q31[4 * 2];   
+static q31_t biquadStateBand3Q31[4 * 2];   
+static q31_t biquadStateBand4Q31[4 * 2];   
+static q31_t biquadStateBand5Q31[4 * 2];   
+ 
+/* ----------------------------------------------------------------------  
+** Q31 input and output buffers  
+** ------------------------------------------------------------------- */  
+
+q31_t inputQ31[BLOCKSIZE];   
+q31_t outputQ31[BLOCKSIZE];  
+ 
+/* ----------------------------------------------------------------------
+** Entire coefficient table.  There are 10 coefficients per 4th order Biquad
+** cascade filter.  The first 10 coefficients correspond to the -9 dB gain
+** setting of band 1; the next 10 coefficient correspond to the -8 dB gain
+** setting of band 1; and so on.  There are 10*19=190 coefficients in total
+** for band 1 (gains = -9, -8, -7, ..., 9).  After this come the 190 coefficients
+** for band 2.
+**
+** The coefficients are in Q29 format and require a postShift of 2.
+** ------------------------------------------------------------------- */
+
+const q31_t coeffTable[950] = {
+
+	/* Band 1, -9 dB gain */
+	535576962, -1071153923, 535576962, 1073741824, -536870912, 535576962, -1063501998, 527979313, 1060865294, -524146981, 
+	/* Band 1, -8 dB gain */
+	535723226, -1071446451, 535723226, 1073741824, -536870912, 535723226, -1063568947, 527903217, 1061230578, -524503778, 
+	535868593, -1071737186, 535868593, 1073741824, -536870912, 535868593, -1063627467, 527819780, 1061585502, -524850686, 
+	536013181, -1072026363, 536013181, 1073741824, -536870912, 536013181, -1063677598, 527728935, 1061930361, -525187972, 
+	536157109, -1072314217, 536157109, 1073741824, -536870912, 536157109, -1063719372, 527630607, 1062265438, -525515897, 
+	536300492, -1072600983, 536300492, 1073741824, -536870912, 536300492, -1063752815, 527524720, 1062591011, -525834716, 
+	536443447, -1072886894, 536443447, 1073741824, -536870912, 536443447, -1063777945, 527411186, 1062907350, -526144676, 
+	536586091, -1073172183, 536586091, 1073741824, -536870912, 536586091, -1063794775, 527289917, 1063214717, -526446017, 
+	536728541, -1073457082, 536728541, 1073741824, -536870912, 536728541, -1063803308, 527160815, 1063513366, -526738975, 
+	536870912, -1073741824, 536870912, 1073741824, -536870912, 536870912, -1063803543, 527023777, 1063803543, -527023777, 
+	537013321, -1074026642, 537013321, 1073741824, -536870912, 537013321, -1063795470, 526878696, 1064085490, -527300648, 
+	537155884, -1074311768, 537155884, 1073741824, -536870912, 537155884, -1063779073, 526725455, 1064359439, -527569803, 
+	537298718, -1074597435, 537298718, 1073741824, -536870912, 537298718, -1063754328, 526563934, 1064625617, -527831454, 
+	537441939, -1074883878, 537441939, 1073741824, -536870912, 537441939, -1063721205, 526394005, 1064884245, -528085806, 
+	537585666, -1075171331, 537585666, 1073741824, -536870912, 537585666, -1063679666, 526215534, 1065135536, -528333059, 
+	537730015, -1075460030, 537730015, 1073741824, -536870912, 537730015, -1063629666, 526028380, 1065379699, -528573409, 
+	537875106, -1075750212, 537875106, 1073741824, -536870912, 537875106, -1063571152, 525832396, 1065616936, -528807045, 
+	538021057, -1076042114, 538021057, 1073741824, -536870912, 538021057, -1063504065, 525627429, 1065847444, -529034151, 
+	538167989, -1076335977, 538167989, 1073741824, -536870912, 538167989, -1063428338, 525413317, 1066071412, -529254907, 
+	
+	/* Band 2, -9 dB gain */
+	531784976, -1055497692, 523873415, 1066213307, -529420241, 531784976, -1040357886, 509828014, 1028908252, -494627367,
+	/* Band 2, -8 dB gain */ 
+	532357636, -1056601982, 524400080, 1066115844, -529326645, 532357636, -1040623406, 509562600, 1030462237, -496062122, 
+	532927392, -1057707729, 524931110, 1066024274, -529239070, 532927392, -1040848253, 509262081, 1031969246, -497457090, 
+	533494678, -1058816094, 525467240, 1065939047, -529157961, 533494678, -1041032161, 508925950, 1033429976, -498812573, 
+	534059929, -1059928204, 526009170, 1065860582, -529083734, 534059929, -1041174868, 508553717, 1034845124, -500128887, 
+	534623580, -1061045148, 526557561, 1065789260, -529016764, 534623580, -1041276126, 508144920, 1036215393, -501406373, 
+	535186068, -1062167969, 527113032, 1065725420, -528957385, 535186068, -1041335703, 507699125, 1037541500, -502645399, 
+	535747827, -1063297666, 527676151, 1065669351, -528905879, 535747827, -1041353386, 507215934, 1038824183, -503846368, 
+	536309295, -1064435183, 528247436, 1065621289, -528862476, 536309295, -1041328990, 506694984, 1040064203, -505009724, 
+	536870912, -1065581413, 528827349, 1065581413, -528827349, 536870912, -1041262354, 506135953, 1041262354, -506135953, 
+	537433117, -1066737194, 529416295, 1065549847, -528800610, 537433117, -1041153346, 505538564, 1042419457, -507225588, 
+	537996352, -1067903307, 530014622, 1065526651, -528782316, 537996352, -1041001864, 504902578, 1043536370, -508279208, 
+	538561061, -1069080480, 530622620, 1065511830, -528772462, 538561061, -1040807833, 504227800, 1044613981, -509297437, 
+	539127690, -1070269387, 531240527, 1065505333, -528770987, 539127690, -1040571205, 503514074, 1045653211, -510280946, 
+	539696690, -1071470656, 531868525, 1065507054, -528777778, 539696690, -1040291951, 502761277, 1046655011, -511230450, 
+	540268512, -1072684867, 532506750, 1065516837, -528792672, 540268512, -1039970063, 501969320, 1047620358, -512146700, 
+	540843613, -1073912567, 533155297, 1065534483, -528815459, 540843613, -1039605542, 501138139, 1048550251, -513030484, 
+	541422451, -1075154268, 533814224, 1065559750, -528845892, 541422451, -1039198394, 500267687, 1049445708, -513882621, 
+	542005489, -1076410460, 534483561, 1065592362, -528883686, 542005489, -1038748624, 499357932, 1050307760, -514703956, 
+	518903861, -1001986830, 486725277, 1037235801, -502367695, 518903861, -945834422, 446371043, 902366163, -400700571, 
+	520899989, -1005630916, 488289126, 1036926846, -502147311, 520899989, -946490935, 445581846, 907921945, -404936158, 
+	522893209, -1009290002, 489869792, 1036650484, -501961419, 522893209, -947006359, 444685310, 913306106, -409075225, 
+	524884763, -1012968199, 491470256, 1036407567, -501810737, 524884763, -947377809, 443679533, 918521018, -413116221, 
+	526875910, -1016669649, 493093518, 1036198712, -501695739, 526875910, -947602324, 442562672, 923569247, -417057897, 
+	528867927, -1020398503, 494742575, 1036024293, -501616651, 528867927, -947676875, 441332970, 928453558, -420899319, 
+	530862111, -1024158905, 496420407, 1035884447, -501573457, 530862111, -947598385, 439988777, 933176909, -424639872, 
+	532859778, -1027954970, 498129955, 1035779077, -501565907, 532859778, -947363742, 438528571, 937742446, -428279254, 
+	534862260, -1031790763, 499874098, 1035707863, -501593525, 534862260, -946969823, 436950987, 942153486, -431817474, 
+	536870912, -1035670279, 501655630, 1035670279, -501655630, 536870912, -946413508, 435254839, 946413508, -435254839, 
+	538887107, -1039597419, 503477238, 1035665609, -501751354, 538887107, -945691703, 433439146, 950526127, -438591937, 
+	540912240, -1043575967, 505341475, 1035692963, -501879659, 540912240, -944801359, 431503152, 954495080, -441829621, 
+	542947726, -1047609569, 507250741, 1035751307, -502039364, 542947726, -943739490, 429446349, 958324201, -444968987, 
+	544995000, -1051701717, 509207261, 1035839473, -502229165, 544995000, -942503190, 427268492, 962017400, -448011351, 
+	547055523, -1055855728, 511213065, 1035956193, -502447657, 547055523, -941089647, 424969617, 965578640, -450958226, 
+	549130774, -1060074734, 513269973, 1036100110, -502693359, 549130774, -939496155, 422550049, 969011913, -453811298, 
+	551222259, -1064361672, 515379585, 1036269804, -502964731, 551222259, -937720119, 420010407, 972321228, -456572401, 
+	553331507, -1068719280, 517543273, 1036463810, -503260192, 553331507, -935759057, 417351601, 975510582, -459243495, 
+	555460072, -1073150100, 519762181, 1036680633, -503578144, 555460072, -933610600, 414574832, 978583948, -461826644, 
+	494084017, -851422604, 404056273, 930151631, -423619864, 494084017, -673714108, 339502486, 561843007, -265801750, 
+	498713542, -859177141, 406587077, 929211656, -423786402, 498713542, -673274906, 338185129, 573719128, -272222942, 
+	503369016, -867012190, 409148384, 928362985, -424054784, 503369016, -672533059, 336693984, 585290277, -278599028, 
+	508052536, -874935599, 411746438, 927604291, -424422151, 508052536, -671478538, 335026905, 596558312, -284920289, 
+	512766286, -882955583, 414387826, 926933782, -424885216, 512766286, -670100998, 333182045, 607525792, -291177811, 
+	517512534, -891080712, 417079474, 926349262, -425440318, 517512534, -668389789, 331157902, 618195914, -297363485, 
+	522293635, -899319903, 419828635, 925848177, -426083491, 522293635, -666333963, 328953368, 628572440, -303470012, 
+	527112032, -907682405, 422642886, 925427679, -426810526, 527112032, -663922286, 326567785, 638659631, -309490882, 
+	531970251, -916177781, 425530105, 925084675, -427617023, 531970251, -661143261, 324000998, 648462180, -315420352, 
+	536870912, -924815881, 428498454, 924815881, -428498454, 536870912, -657985147, 321253420, 657985147, -321253420, 
+	541816719, -933606817, 431556352, 924617870, -429450209, 541816719, -654435997, 318326093, 667233900, -326985786, 
+	546810467, -942560921, 434712438, 924487114, -430467639, 546810467, -650483688, 315220754, 676214053, -332613816, 
+	551855042, -951688708, 437975532, 924420027, -431546101, 551855042, -646115970, 311939896, 684931422, -338134495, 
+	556953421, -961000826, 441354588, 924413001, -432680993, 556953421, -641320513, 308486839, 693391970, -343545389, 
+	562108672, -970508005, 444858642, 924462435, -433867780, 562108672, -636084967, 304865786, 701601770, -348844597, 
+	567323959, -980220994, 448496743, 924564764, -435102022, 567323959, -630397020, 301081886, 709566963, -354030710, 
+	572602539, -990150500, 452277894, 924716482, -436379394, 572602539, -624244471, 297141281, 717293726, -359102767, 
+	577947763, -1000307125, 456210977, 924914158, -437695705, 577947763, -617615296, 293051155, 724788245, -364060214, 
+	583363084, -1010701292, 460304674, 925154455, -439046908, 583363084, -610497723, 288819761, 732056685, -368902865, 
+	387379495, -506912469, 196933274, 840112184, -347208270, 387379495, 506912469, 196933274, -840112184, -347208270, 
+	401658082, -532275898, 207149427, 833765363, -343175316, 401658082, 532275898, 207149427, -833765363, -343175316, 
+	416472483, -558722695, 217902617, 827270154, -339107319, 416472483, 558722695, 217902617, -827270154, -339107319, 
+	431841949, -586290861, 229212798, 820624988, -335007540, 431841949, 586290861, 229212798, -820624988, -335007540, 
+	447786335, -615019650, 241100489, 813828443, -330879528, 447786335, 615019650, 241100489, -813828443, -330879528, 
+	464326111, -644949597, 253586805, 806879270, -326727141, 464326111, 644949597, 253586805, -806879270, -326727141, 
+	481482377, -676122557, 266693475, 799776409, -322554559, 481482377, 676122557, 266693475, -799776409, -322554559, 
+	499276882, -708581728, 280442865, 792519013, -318366296, 499276882, 708581728, 280442865, -792519013, -318366296, 
+	517732032, -742371685, 294857996, 785106465, -314167221, 517732032, 742371685, 294857996, -785106465, -314167221, 
+	536870912, -777538408, 309962566, 777538408, -309962566, 536870912, 777538408, 309962566, -777538408, -309962566, 
+	556717294, -814129313, 325780968, 769814766, -305757943, 556717294, 814129313, 325780968, -769814766, -305757943, 
+	577295658, -852193284, 342338310, 761935777, -301559360, 577295658, 852193284, 342338310, -761935777, -301559360, 
+	598631206, -891780698, 359660433, 753902014, -297373230, 598631206, 891780698, 359660433, -753902014, -297373230, 
+	620749877, -932943463, 377773927, 745714425, -293206383, 620749877, 932943463, 377773927, -745714425, -293206383, 
+	643678365, -975735041, 396706151, 737374355, -289066077, 643678365, 975735041, 396706151, -737374355, -289066077, 
+	667444134, -1020210487, 416485252, 728883588, -284960004, 667444134, 1020210487, 416485252, -728883588, -284960004, 
+	692075438, -1066426476, 437140179, 720244375, -280896294, 692075438, 1066426476, 437140179, -720244375, -280896294, 
+	717601336, -1114441339, 458700704, 711459472, -276883515, 717601336, 1114441339, 458700704, -711459472, -276883515, 
+	744051710, -1164315096, 481197437, 702532174, -272930673, 744051710, 1164315096, 481197437, -702532174, -272930673 
+
+};
+
+/* ----------------------------------------------------------------------
+** Desired gains, in dB, per band
+** ------------------------------------------------------------------- */
+
+int gainDB[5] = {0, -3, 6, 4, -6};
+
+float32_t snr;
+
+
+/* ---------------------------------------------------------------------- 
+ * Graphic equalizer Example 
+ * ------------------------------------------------------------------- */ 
+ 
+int32_t main(void) 
+{ 
+  float32_t  *inputF32, *outputF32;  
+  arm_biquad_cas_df1_32x64_ins_q31 S1; 
+  arm_biquad_cas_df1_32x64_ins_q31 S2; 
+  arm_biquad_casd_df1_inst_q31 S3; 
+  arm_biquad_casd_df1_inst_q31 S4; 
+  arm_biquad_casd_df1_inst_q31 S5; 
+  int i;
+  int32_t status;
+	 
+  inputF32 = &testInput_f32[0];	 
+  outputF32 = &testOutput[0]; 
+	 
+  /* Initialize the state and coefficient buffers for all Biquad sections */
+
+  arm_biquad_cas_df1_32x64_init_q31(&S1, NUMSTAGES, 
+				    (q31_t *) &coeffTable[190*0 + 10*(gainDB[0] + 9)],
+				    &biquadStateBand1Q31[0], 2);
+
+  arm_biquad_cas_df1_32x64_init_q31(&S2, NUMSTAGES, 
+				    (q31_t *) &coeffTable[190*1 + 10*(gainDB[1] + 9)],
+				    &biquadStateBand2Q31[0], 2);
+	 
+  arm_biquad_cascade_df1_init_q31(&S3, NUMSTAGES, 
+				  (q31_t *) &coeffTable[190*2 + 10*(gainDB[2] + 9)],
+				  &biquadStateBand3Q31[0], 2);
+
+  arm_biquad_cascade_df1_init_q31(&S4, NUMSTAGES, 
+				  (q31_t *) &coeffTable[190*3 + 10*(gainDB[3] + 9)],
+				  &biquadStateBand4Q31[0], 2); 
+	 
+  arm_biquad_cascade_df1_init_q31(&S5, NUMSTAGES, 
+				  (q31_t *) &coeffTable[190*4 + 10*(gainDB[4] + 9)],
+				  &biquadStateBand5Q31[0], 2); 
+	 
+ 
+  /* Call the process functions and needs to change filter coefficients  
+     for varying the gain of each band */ 
+ 
+  for(i=0; i < NUMBLOCKS; i++) 
+    {	 
+
+      /* ---------------------------------------------------------------------- 
+      ** Convert block of input data from float to Q31 
+      ** ------------------------------------------------------------------- */ 
+
+      arm_float_to_q31(inputF32 + (i*BLOCKSIZE), inputQ31, BLOCKSIZE);	   
+	  	 
+      /* ----------------------------------------------------------------------
+      ** Scale down by 1/8.  This provides additional headroom so that the
+      ** graphic EQ can apply gain.
+      ** ------------------------------------------------------------------- */
+
+      arm_scale_q31(inputQ31, 0x7FFFFFFF, -3, inputQ31, BLOCKSIZE);
+
+      /* ----------------------------------------------------------------------
+      ** Call the Q31 Biquad Cascade DF1 32x64 process function for band1, band2
+      ** ------------------------------------------------------------------- */
+
+      arm_biquad_cas_df1_32x64_q31(&S1, inputQ31, outputQ31, BLOCKSIZE); 
+      arm_biquad_cas_df1_32x64_q31(&S2, outputQ31, outputQ31, BLOCKSIZE); 
+
+      /* ---------------------------------------------------------------------- 
+      ** Call the Q31 Biquad Cascade DF1 process function for band3, band4, band5
+      ** ------------------------------------------------------------------- */		   
+
+      arm_biquad_cascade_df1_q31(&S3, outputQ31, outputQ31, BLOCKSIZE); 
+      arm_biquad_cascade_df1_q31(&S4, outputQ31, outputQ31, BLOCKSIZE);	 
+      arm_biquad_cascade_df1_q31(&S5, outputQ31, outputQ31, BLOCKSIZE); 
+ 
+      /* ---------------------------------------------------------------------- 
+      ** Convert Q31 result back to float 
+      ** ------------------------------------------------------------------- */ 
+
+      arm_q31_to_float(outputQ31, outputF32 + (i * BLOCKSIZE), BLOCKSIZE);
+
+      /* ---------------------------------------------------------------------- 
+      ** Scale back up
+      ** ------------------------------------------------------------------- */ 
+
+      arm_scale_f32(outputF32 + (i * BLOCKSIZE), 8.0f, outputF32 + (i * BLOCKSIZE), BLOCKSIZE);
+    }; 
+
+	snr = arm_snr_f32(testRefOutput_f32, testOutput, TESTLENGTH);
+
+	if (snr < SNR_THRESHOLD_F32) 
+	{ 
+	    status = ARM_MATH_TEST_FAILURE; 
+	} 
+	else
+	{
+	    status = ARM_MATH_SUCCESS; 
+	}
+		 
+  /* ---------------------------------------------------------------------- 
+  ** Loop here if the signal does not match the reference output.
+  ** ------------------------------------------------------------------- */ 
+	 
+  if( status != ARM_MATH_SUCCESS) 
+    { 
+      while(1); 
+    } 
+
+    while(1);                             /* main function does not return */
+} 
+ 
+/** \endlink */ 
+ 
+ 
+ 

libs/CMSIS/DSP_Lib/Examples/arm_linear_interp_example/arm_linear_interp_example_f32.c

@@ -0,0 +1,188 @@
+/* ----------------------------------------------------------------------
+* Copyright (C) 2010 ARM Limited. All rights reserved.
+*
+* $Date:        29. November 2010
+* $Revision:    V1.0.3
+*
+* Project:      CMSIS DSP Library
+* Title:        arm_linear_interp_example_f32.c
+*
+* Description:  Example code demonstrating usage of sin function
+*               and uses linear interpolation to get higher precision
+*
+* Target Processor: Cortex-M4/Cortex-M3
+*
+*
+* Version 1.0.3 2010/11/29
+*    Re-organized the CMSIS folders and updated documentation.
+*
+* Version 1.0.1 2010/10/05 KK
+*    Production release and review comments incorporated.
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */
+
+/**
+ * @ingroup groupExamples
+ */
+
+/**
+ * @defgroup LinearInterpExample Linear Interpolate Example
+ *
+ * <b> CMSIS DSP Software Library -- Linear Interpolate Example  </b>
+ *
+ * <b> Description </b>
+ * This example demonstrates usage of linear interpolate modules and fast math modules.
+ * Method 1 uses fast math sine function to calculate sine values using cubic interpolation and method 2 uses
+ * linear interpolation function and results are compared to reference output.
+ * Example shows linear interpolation function can be used to get higher precision compared to fast math sin calculation.
+ *
+ * \par Block Diagram:
+ * \par
+ * \image html linearInterpExampleMethod1.gif "Method 1: Sine caluclation using fast math"
+ * \par
+ * \image html linearInterpExampleMethod2.gif "Method 2: Sine caluclation using interpolation function"
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c testInputSin_f32         points to the input values for sine calculation
+ * \li \c testRefSinOutput32_f32   points to the reference values caculated from sin() matlab function
+ * \li \c testOutput               points to output buffer calculation from cubic interpolation
+ * \li \c testLinIntOutput         points to output buffer calculation from linear interpolation
+ * \li \c snr1                     Signal to noise ratio for reference and cubic interpolation output
+ * \li \c snr2                     Signal to noise ratio for reference and linear interpolation output
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_sin_f32()
+ * - arm_linear_interp_f32()
+ *
+ * <b> Refer  </b>
+ * \link arm_linear_interp_example_f32.c \endlink
+ *
+ */
+
+
+/** \example arm_linear_interp_example_f32.c
+  */
+
+#include "arm_math.h"
+#include "math_helper.h"
+
+#define SNR_THRESHOLD           90
+#define TEST_LENGTH_SAMPLES     10
+#define XSPACING               (0.00005f)
+
+/* ----------------------------------------------------------------------
+* Test input data for F32 SIN function
+* Generated by the MATLAB rand() function
+* randn('state', 0)
+* xi = (((1/4.18318581819710)* randn(blockSize, 1) * 2* pi));
+* --------------------------------------------------------------------*/
+float32_t testInputSin_f32[TEST_LENGTH_SAMPLES] =
+{
+   -0.649716504673081170, -2.501723745497831200,
+    0.188250329003310100,  0.432092748487532540,
+   -1.722010988459680800,  1.788766476323060600,
+    1.786136060975809500, -0.056525543169408797,
+    0.491596272728153760,  0.262309671126153390
+};
+
+/*------------------------------------------------------------------------------
+*  Reference out of SIN F32 function for Block Size = 10
+*  Calculated from sin(testInputSin_f32)
+*------------------------------------------------------------------------------*/
+float32_t testRefSinOutput32_f32[TEST_LENGTH_SAMPLES] =
+{
+   -0.604960695383043530, -0.597090287967934840,
+    0.187140422442966500,  0.418772124875992690,
+   -0.988588831792106880,  0.976338412038794010,
+    0.976903856413481100, -0.056495446835214236,
+    0.472033731854734240,  0.259311907228582830
+};
+
+/*------------------------------------------------------------------------------
+*  Method 1: Test out Buffer Calculated from Cubic Interpolation
+*------------------------------------------------------------------------------*/
+float32_t testOutput[TEST_LENGTH_SAMPLES];
+
+/*------------------------------------------------------------------------------
+*  Method 2: Test out buffer Calculated from Linear Interpolation
+*------------------------------------------------------------------------------*/
+float32_t testLinIntOutput[TEST_LENGTH_SAMPLES];
+
+/*------------------------------------------------------------------------------
+*  External table used for linear interpolation
+*------------------------------------------------------------------------------*/
+extern const float arm_linear_interep_table[188495];
+
+/* ----------------------------------------------------------------------
+* Global Variables for caluclating SNR's for Method1 & Method 2
+* ------------------------------------------------------------------- */
+float32_t snr1;
+float32_t snr2;
+
+/* ----------------------------------------------------------------------------
+* Calculation of Sine values from Cubic Interpolation and Linear interpolation
+* ---------------------------------------------------------------------------- */
+int32_t main(void)
+{
+   uint32_t i;
+   arm_status status;
+
+   arm_linear_interp_instance_f32 S = {188495, -3.141592653589793238, XSPACING, (float32_t *)&arm_linear_interep_table[0]};
+
+   /*------------------------------------------------------------------------------
+   *  Method 1: Test out Calculated from Cubic Interpolation
+   *------------------------------------------------------------------------------*/
+   for(i=0; i< TEST_LENGTH_SAMPLES; i++)
+   {
+      testOutput[i] = arm_sin_f32(testInputSin_f32[i]);
+   }
+
+   /*------------------------------------------------------------------------------
+   *  Method 2: Test out Calculated from Cubic Interpolation and Linear interpolation
+   *------------------------------------------------------------------------------*/
+
+   for(i=0; i< TEST_LENGTH_SAMPLES; i++)
+   {
+     	testLinIntOutput[i] = arm_linear_interp_f32(&S, testInputSin_f32[i]);
+   }
+
+   /*------------------------------------------------------------------------------
+   *  SNR calculation for method 1
+   *------------------------------------------------------------------------------*/
+   snr1 = arm_snr_f32(testRefSinOutput32_f32, testOutput, 2);
+
+   /*------------------------------------------------------------------------------
+   *  SNR calculation for method 2
+   *------------------------------------------------------------------------------*/
+   snr2 = arm_snr_f32(testRefSinOutput32_f32, testLinIntOutput, 2);
+
+   /*------------------------------------------------------------------------------
+   *  					Initialise status depending on SNR calculations
+   *------------------------------------------------------------------------------*/
+   if( snr2 > snr1)
+   {
+      status = ARM_MATH_SUCCESS;
+   }
+   else
+   {
+      status = ARM_MATH_TEST_FAILURE;
+   }
+
+   /* ----------------------------------------------------------------------
+   ** Loop here if the signals fail the PASS check.
+   ** This denotes a test failure
+   ** ------------------------------------------------------------------- */
+   if( status != ARM_MATH_SUCCESS)
+   {
+      while(1);
+   }
+
+   while(1);                             /* main function does not return */
+}
+
+ /** \endlink */
+

libs/CMSIS/DSP_Lib/Examples/arm_matrix_example/arm_matrix_example_f32.c

@@ -0,0 +1,218 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3
+*  
+* Project: 	    CMSIS DSP Library  
+* Title:	    arm_matrix_example_f32.c		  
+*  
+* Description:	Example code demonstrating least square fit to data  
+*				using matrix functions  
+*				 
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup MatrixExample Matrix Example    
+ * 
+ * \par Description: 
+ * \par
+ * Demonstrates the use of Matrix Transpose, Matrix Muliplication, and Matrix Inverse 
+ * functions to apply least squares fitting to input data. Least squares fitting is 
+ * the procedure for finding the best-fitting curve that minimizes the sum of the 
+ * squares of the offsets (least square error) from a given set of data.
+ *
+ * \par Algorithm:
+ * \par
+ * The linear combination of parameters considered is as follows: 
+ * \par 
+ * <code>A * X = B</code>, where \c X is the unknown value and can be estimated 
+ * from \c A & \c B.
+ * \par
+ * The least squares estimate \c X is given by the following equation:
+ * \par
+ * <code>X = Inverse(A<sup>T</sup> * A) *  A<sup>T</sup> * B</code>
+ *
+ * \par Block Diagram:
+ * \par
+ * \image html matrixExample.gif
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c A_f32 input matrix in the linear combination equation
+ * \li \c B_f32 output matrix in the linear combination equation
+ * \li \c X_f32 unknown matrix estimated using \c A_f32 & \c B_f32 matrices
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_mat_init_f32()
+ * - arm_mat_trans_f32()
+ * - arm_mat_mult_f32()
+ * - arm_mat_inverse_f32() 
+ * 
+ * <b> Refer  </b> 
+ * \link arm_matrix_example_f32.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_matrix_example_f32.c 
+  */  
+     
+#include "arm_math.h" 
+#include "math_helper.h" 
+ 
+#define SNR_THRESHOLD 	90 
+ 
+/* -------------------------------------------------------------------------------- 
+* Test input data(Cycles) taken from FIR Q15 module for differant cases of blockSize  
+* and tapSize 
+* --------------------------------------------------------------------------------- */ 
+ 
+const float32_t B_f32[4] =  
+{    
+	782.0, 7577.0, 470.0, 4505.0 
+}; 
+ 
+/* -------------------------------------------------------------------------------- 
+* Formula to fit is  C1 + C2 * numTaps + C3 * blockSize + C4 * numTaps * blockSize 
+* -------------------------------------------------------------------------------- */ 
+ 
+const float32_t A_f32[16] =  
+{ 
+	/* Const, 	numTaps, 	blockSize, 	numTaps*blockSize */    
+	1.0, 		32.0, 		4.0, 		128.0,  
+	1.0, 		32.0, 		64.0, 		2048.0, 
+	1.0, 		16.0, 		4.0, 		64.0, 
+	1.0, 		16.0, 		64.0, 		1024.0, 
+};  
+ 
+ 
+/* ---------------------------------------------------------------------- 
+* Temporary buffers  for storing intermediate values 
+* ------------------------------------------------------------------- */ 
+/* Transpose of A Buffer */ 
+float32_t AT_f32[16]; 
+/* (Transpose of A * A) Buffer */ 
+float32_t ATMA_f32[16]; 
+/* Inverse(Transpose of A * A)  Buffer */ 
+float32_t ATMAI_f32[16]; 
+/* Test Output Buffer */ 
+float32_t X_f32[4]; 
+ 
+/* ---------------------------------------------------------------------- 
+* Reference ouput buffer C1, C2, C3 and C4 taken from MATLAB  
+* ------------------------------------------------------------------- */ 
+const float32_t xRef_f32[4] = {73.0, 8.0, 21.25, 2.875}; 
+ 
+float32_t snr; 
+ 
+ 
+/* ---------------------------------------------------------------------- 
+* Max magnitude FFT Bin test 
+* ------------------------------------------------------------------- */ 
+ 
+int32_t main(void) 
+{ 
+ 
+	arm_matrix_instance_f32 A;		/* Matrix A Instance */ 
+	arm_matrix_instance_f32 AT;		/* Matrix AT(A transpose) instance */ 
+	arm_matrix_instance_f32 ATMA;	/* Matrix ATMA( AT multiply with A) instance */ 
+	arm_matrix_instance_f32 ATMAI;	/* Matrix ATMAI(Inverse of ATMA) instance */ 
+	arm_matrix_instance_f32 B;		/* Matrix B instance */ 
+	arm_matrix_instance_f32 X;		/* Matrix X(Unknown Matrix) instance */ 
+ 
+	uint32_t srcRows, srcColumns;	/* Temporary variables */
+	arm_status status; 
+ 
+	/* Initialise A Matrix Instance with numRows, numCols and data array(A_f32) */ 
+	srcRows = 4; 
+    srcColumns = 4; 
+	arm_mat_init_f32(&A, srcRows, srcColumns, (float32_t *)A_f32); 
+ 
+	/* Initialise Matrix Instance AT with numRows, numCols and data array(AT_f32) */ 
+	srcRows = 4; 
+    srcColumns = 4; 
+	arm_mat_init_f32(&AT, srcRows, srcColumns, AT_f32); 
+ 
+	/* calculation of A transpose */ 
+	status = arm_mat_trans_f32(&A, &AT); 
+	 
+ 
+	/* Initialise ATMA Matrix Instance with numRows, numCols and data array(ATMA_f32) */ 
+	srcRows = 4; 
+    srcColumns = 4; 
+	arm_mat_init_f32(&ATMA, srcRows, srcColumns, ATMA_f32); 
+ 
+	/* calculation of AT Multiply with A */ 
+	status = arm_mat_mult_f32(&AT, &A, &ATMA); 
+ 
+	/* Initialise ATMAI Matrix Instance with numRows, numCols and data array(ATMAI_f32) */ 
+	srcRows = 4; 
+    srcColumns = 4; 
+	arm_mat_init_f32(&ATMAI, srcRows, srcColumns, ATMAI_f32); 
+ 
+	/* calculation of Inverse((Transpose(A) * A) */ 
+	status = arm_mat_inverse_f32(&ATMA, &ATMAI); 
+ 
+	/* calculation of (Inverse((Transpose(A) * A)) *  Transpose(A)) */ 
+	status = arm_mat_mult_f32(&ATMAI, &AT, &ATMA); 
+ 
+	/* Initialise B Matrix Instance with numRows, numCols and data array(B_f32) */ 
+	srcRows = 4; 
+    srcColumns = 1; 
+	arm_mat_init_f32(&B, srcRows, srcColumns, (float32_t *)B_f32);  
+ 
+	/* Initialise X Matrix Instance with numRows, numCols and data array(X_f32) */ 
+	srcRows = 4; 
+    srcColumns = 1; 
+	arm_mat_init_f32(&X, srcRows, srcColumns, X_f32); 
+ 
+	/* calculation ((Inverse((Transpose(A) * A)) *  Transpose(A)) * B) */ 
+	status = arm_mat_mult_f32(&ATMA, &B, &X); 
+	 
+	/* Comparison of reference with test output */	   
+	snr = arm_snr_f32((float32_t *)xRef_f32, X_f32, 4); 
+ 
+	/*------------------------------------------------------------------------------ 
+	*  					Initialise status depending on SNR calculations 
+	*------------------------------------------------------------------------------*/  
+	if( snr > SNR_THRESHOLD) 
+	{ 
+		status = ARM_MATH_SUCCESS; 
+	} 
+	else 
+	{ 
+		status = ARM_MATH_TEST_FAILURE; 
+	} 
+ 
+	 
+	/* ---------------------------------------------------------------------- 
+	** Loop here if the signals fail the PASS check. 
+	** This denotes a test failure 
+	** ------------------------------------------------------------------- */	 
+	if( status != ARM_MATH_SUCCESS) 
+	{ 
+	  while(1); 
+	} 
+
+    while(1);                             /* main function does not return */
+} 
+ 
+ /** \endlink */ 
+ 

libs/CMSIS/DSP_Lib/Examples/arm_signal_converge_example/arm_signal_converge_data.c

@@ -0,0 +1,229 @@
+#include "arm_math.h"
+
+/* ----------------------------------------------------------------------
+** Test input data for Floating point LMS Norm FIR filter
+** Generated by the MATLAB randn() function
+** ------------------------------------------------------------------- */
+
+float32_t testInput_f32[1536] = 
+{   
+-0.432565,	-1.665584,	0.125332,	0.287676,	-1.146471,	1.190915,	1.189164,	-0.037633,	
+0.327292,	0.174639,	-0.186709,	0.725791,	-0.588317,	2.183186,	-0.136396,	0.113931,	
+1.066768,	0.059281,	-0.095648,	-0.832349,	0.294411,	-1.336182,	0.714325,	1.623562,	
+-0.691776,	0.857997,	1.254001,	-1.593730,	-1.440964,	0.571148,	-0.399886,	0.689997,	
+0.815622,	0.711908,	1.290250,	0.668601,	1.190838,	-1.202457,	-0.019790,	-0.156717,	
+-1.604086,	0.257304,	-1.056473,	1.415141,	-0.805090,	0.528743,	0.219321,	-0.921902,	
+-2.170674,	-0.059188,	-1.010634,	0.614463,	0.507741,	1.692430,	0.591283,	-0.643595,	
+0.380337,	-1.009116,	-0.019511,	-0.048221,	0.000043,	-0.317859,	1.095004,	-1.873990,	
+0.428183,	0.895638,	0.730957,	0.577857,	0.040314,	0.677089,	0.568900,	-0.255645,	
+-0.377469,	-0.295887,	-1.475135,	-0.234004,	0.118445,	0.314809,	1.443508,	-0.350975,	
+0.623234,	0.799049,	0.940890,	-0.992092,	0.212035,	0.237882,	-1.007763,	-0.742045,	
+1.082295,	-0.131500,	0.389880,	0.087987,	-0.635465,	-0.559573,	0.443653,	-0.949904,	
+0.781182,	0.568961,	-0.821714,	-0.265607,	-1.187777,	-2.202321,	0.986337,	-0.518635,	
+0.327368,	0.234057,	0.021466,	-1.003944,	-0.947146,	-0.374429,	-1.185886,	-1.055903,	
+1.472480,	0.055744,	-1.217317,	-0.041227,	-1.128344,	-1.349278,	-0.261102,	0.953465,	
+0.128644,	0.656468,	-1.167819,	-0.460605,	-0.262440,	-1.213152,	-1.319437,	0.931218,	
+0.011245,	-0.645146,	0.805729,	0.231626,	-0.989760,	1.339586,	0.289502,	1.478917,	
+1.138028,	-0.684139,	-1.291936,	-0.072926,	-0.330599,	-0.843628,	0.497770,	1.488490,	
+-0.546476,	-0.846758,	-0.246337,	0.663024,	-0.854197,	-1.201315,	-0.119869,	-0.065294,	
+0.485296,	-0.595491,	-0.149668,	-0.434752,	-0.079330,	1.535152,	-0.606483,	-1.347363,	
+0.469383,	-0.903567,	0.035880,	-0.627531,	0.535398,	0.552884,	-0.203690,	-2.054325,	
+0.132561,	1.592941,	1.018412,	-1.580402,	-0.078662,	-0.681657,	-1.024553,	-1.234353,	
+0.288807,	-0.429303,	0.055801,	-0.367874,	-0.464973,	0.370961,	0.728283,	2.112160,	
+-1.357298,	-1.022610,	1.037834,	-0.389800,	-1.381266,	0.315543,	1.553243,	0.707894,	
+1.957385,	0.504542,	1.864529,	-0.339812,	-1.139779,	-0.211123,	1.190245,	-1.116209,	
+0.635274,	-0.601412,	0.551185,	-1.099840,	0.085991,	-2.004563,	-0.493088,	0.462048,	
+-0.321005,	1.236556,	-0.631280,	-2.325211,	-1.231637,	1.055648,	-0.113224,	0.379224,	
+0.944200,	-2.120427,	-0.644679,	-0.704302,	-1.018137,	-0.182082,	1.521013,	-0.038439,	
+1.227448,	-0.696205,	0.007524,	-0.782893,	0.586939,	-0.251207,	0.480136,	0.668155,	
+-0.078321,	0.889173,	2.309287,	0.524639,	-0.011787,	0.913141,	0.055941,	-1.107070,	
+0.485498,	-0.005005,	-0.276218,	1.276452,	1.863401,	-0.522559,	0.103424,	-0.807649,	
+0.680439,	-2.364590,	0.990115,	0.218899,	0.261662,	1.213444,	-0.274667,	-0.133134,	
+-1.270500,	-1.663606,	-0.703554,	0.280880,	-0.541209,	-1.333531,	1.072686,	-0.712085,	
+-0.011286,	-0.000817,	-0.249436,	0.396575,	-0.264013,	-1.664011,	-1.028975,	0.243095,	
+-1.256590,	-0.347183,	-0.941372,	-1.174560,	-1.021142,	-0.401667,	0.173666,	-0.116118,	
+1.064119,	-0.245386,	-1.517539,	0.009734,	0.071373,	0.316536,	0.499826,	1.278084,	
+-0.547816,	0.260808,	-0.013177,	-0.580264,	2.136308,	-0.257617,	-1.409528,	1.770101,	
+0.325546,	-1.119040,	0.620350,	1.269782,	-0.896043,	0.135175,	-0.139040,	-1.163395,	
+1.183720,	-0.015430,	0.536219,	-0.716429,	-0.655559,	0.314363,	0.106814,	1.848216,	
+-0.275106,	2.212554,	1.508526,	-1.945079,	-1.680543,	-0.573534,	-0.185817,	0.008934,	
+0.836950,	-0.722271,	-0.721490,	-0.201181,	-0.020464,	0.278890,	1.058295,	0.621673,	
+-1.750615,	0.697348,	0.811486,	0.636345,	1.310080,	0.327098,	-0.672993,	-0.149327,	
+-2.449018,	0.473286,	0.116946,	-0.591104,	-0.654708,	-1.080662,	-0.047731,	0.379345,	
+-0.330361,	-0.499898,	-0.035979,	-0.174760,	-0.957265,	1.292548,	0.440910,	1.280941,	
+-0.497730,	-1.118717,	0.807650,	0.041200,	-0.756209,	-0.089129,	-2.008850,	1.083918,	
+-0.981191,	-0.688489,	1.339479,	-0.909243,	-0.412858,	-0.506163,	1.619748,	0.080901,	
+-1.081056,	-1.124518,	1.735676,	1.937459,	1.635068,	-1.255940,	-0.213538,	-0.198932,	
+0.307499,	-0.572325,	-0.977648,	-0.446809,	1.082092,	2.372648,	0.229288,	-0.266623,	
+0.701672,	-0.487590,	1.862480,	1.106851,	-1.227566,	-0.669885,	1.340929,	0.388083,	
+0.393059,	-1.707334,	0.227859,	0.685633,	-0.636790,	-1.002606,	-0.185621,	-1.054033,	
+-0.071539,	0.279198,	1.373275,	0.179841,	-0.542017,	1.634191,	0.825215,	0.230761,	
+0.671634,	-0.508078,	0.856352,	0.268503,	0.624975,	-1.047338,	1.535670,	0.434426,	
+-1.917136,	0.469940,	1.274351,	0.638542,	1.380782,	1.319843,	-0.909429,	-2.305605,	
+1.788730,	0.390798,	0.020324,	-0.405977,	-1.534895,	0.221373,	-1.374479,	-0.839286,	
+-0.208643,	0.755913,	0.375734,	-1.345413,	1.481876,	0.032736,	1.870453,	-1.208991,	
+-0.782632,	-0.767299,	-0.107200,	-0.977057,	-0.963988,	-2.379172,	-0.838188,	0.257346,	
+-0.183834,	-0.167615,	-0.116989,	0.168488,	-0.501206,	-0.705076,	0.508165,	-0.420922,	
+0.229133,	-0.959497,	-0.146043,	0.744538,	-0.890496,	0.139062,	-0.236144,	-0.075459,	
+-0.358572,	-2.077635,	-0.143546,	1.393341,	0.651804,	-0.377134,	-0.661443,	0.248958,	
+-0.383516,	-0.528480,	0.055388,	1.253769,	-2.520004,	0.584856,	-1.008064,	0.944285,	
+-2.423957,	-0.223831,	0.058070,	-0.424614,	-0.202918,	-1.513077,	-1.126352,	-0.815002,	
+0.366614,	-0.586107,	1.537409,	0.140072,	-1.862767,	-0.454193,	-0.652074,	0.103318,	
+-0.220632,	-0.279043,	-0.733662,	-0.064534,	-1.444004,	0.612340,	-1.323503,	-0.661577,	
+-0.146115,	0.248085,	-0.076633,	1.738170,	1.621972,	0.626436,	0.091814,	-0.807607,	
+-0.461337,	-1.405969,	-0.374530,	-0.470911,	1.751296,	0.753225,	0.064989,	-0.292764,	
+0.082823,	0.766191,	2.236850,	0.326887,	0.863304,	0.679387,	0.554758,	1.001630,	
+1.259365,	0.044151,	-0.314138,	0.226708,	0.996692,	1.215912,	-0.542702,	0.912228,	
+-0.172141,	-0.335955,	0.541487,	0.932111,	-0.570253,	-1.498605,	-0.050346,	0.553025,	
+0.083498,	1.577524,	-0.330774,	0.795155,	-0.784800,	-1.263121,	0.666655,	-1.392632,	
+-1.300562,	-0.605022,	-1.488565,	0.558543,	-0.277354,	-1.293685,	-0.888435,	-0.986520,	
+-0.071618,	-2.414591,	-0.694349,	-1.391389,	0.329648,	0.598544,	0.147175,	-0.101439,	
+-2.634981,	0.028053,	-0.876310,	-0.265477,	-0.327578,	-1.158247,	0.580053,	0.239756,	
+-0.350885,	0.892098,	1.578299,	-1.108174,	-0.025931,	-1.110628,	0.750834,	0.500167,	
+-0.517261,	-0.559209,	-0.753371,	0.925813,	-0.248520,	-0.149835,	-1.258415,	0.312620,	
+2.690277,	0.289696,	-1.422803,	0.246786,	-1.435773,	0.148573,	-1.693073,	0.719188,	
+1.141773,	1.551936,	1.383630,	-0.758092,	0.442663,	0.911098,	-1.074086,	0.201762,	
+0.762863,	-1.288187,	-0.952962,	0.778175,	-0.006331,	0.524487,	1.364272,	0.482039,	
+-0.787066,	0.751999,	-0.166888,	-0.816228,	2.094065,	0.080153,	-0.937295,	0.635739,	
+1.682028,	0.593634,	0.790153,	0.105254,	-0.158579,	0.870907,	-0.194759,	0.075474,	
+-0.526635,	-0.685484,	-0.268388,	-1.188346,	0.248579,	0.102452,	-0.041007,	-2.247582,	
+-0.510776,	0.249243,	0.369197,	0.179197,	-0.037283,	-1.603310,	0.339372,	-0.131135,	
+0.485190,	0.598751,	-0.086031,	0.325292,	-0.335143,	-0.322449,	-0.382374,	-0.953371,	
+0.233576,	1.235245,	-0.578532,	-0.501537,	0.722864,	0.039498,	1.541279,	-1.701053,	
+-1.033741,	-0.763708,	2.176426,	0.431612,	-0.443765,	0.029996,	-0.315671,	0.977846,	
+0.018295,	0.817963,	0.702341,	-0.231271,	-0.113690,	0.127941,	-0.799410,	-0.238612,	
+-0.089463,	-1.023264,	0.937538,	-1.131719,	-0.710702,	-1.169501,	1.065437,	-0.680394,	
+-1.725773,	0.813200,	1.441867,	0.672272,	0.138665,	-0.859534,	-0.752251,	1.229615,	
+1.150754,	-0.608025,	0.806158,	0.217133,	-0.373461,	-0.832030,	0.286866,	-1.818892,	
+-1.573051,	2.015666,	-0.071982,	2.628909,	-0.243317,	0.173276,	0.923207,	-0.178553,	
+-0.521705,	1.431962,	-0.870117,	0.807542,	-0.510635,	0.743514,	0.847898,	-0.829901,	
+0.532994,	1.032848,	-1.052024,	0.362114,	-0.036787,	-1.227636,	-0.275099,	-0.160435,	
+-1.083575,	-1.954213,	-0.909487,	-0.005579,	-1.723490,	1.263077,	-0.600433,	-2.063925,	
+0.110911,	1.487614,	0.053002,	0.161981,	-0.026878,	0.173576,	0.882168,	0.182294,	
+0.755295,	0.508035,	0.131880,	0.280104,	-0.982848,	-0.944087,	-0.013058,	0.354345,	
+-0.894709,	0.812111,	0.109537,	2.731644,	0.411079,	-1.306862,	0.383806,	0.499504,	
+-0.510786,	0.234922,	-0.597825,	0.020771,	0.419443,	1.191104,	0.771214,	-2.644222,	
+0.285430,	0.826093,	-0.008122,	0.858438,	0.774788,	1.305945,	1.231503,	0.958564,	
+-1.654548,	-0.990396,	0.685236,	-0.974870,	-0.606726,	0.686794,	0.020049,	1.063801,	
+-1.341050,	0.479510,	-1.633974,	-1.442665,	0.293781,	-0.140364,	-1.130341,	-0.292538,	
+-0.582536,	-0.896348,	0.248601,	-1.489663,	0.313509,	-2.025084,	0.528990,	0.343471,	
+0.758193,	-0.691940,	0.680179,	-1.072541,	0.899772,	-2.123092,	0.284712,	-0.733323,	
+-0.773376,	0.151842,	-0.336843,	0.970761,	-0.107236,	1.013492,	-0.475347,	0.068948,	
+0.398592,	1.116326,	0.620451,	-0.287674,	-1.371773,	-0.685868,	0.331685,	-0.997722,	
+0.291418,	1.107078,	0.244959,	0.164976,	0.406231,	1.215981,	1.448424,	-1.025137,	
+0.205418,	0.588882,	-0.264024,	2.495318,	0.855948,	-0.850954,	0.811879,	0.700242,	
+0.759938,	-1.712909,	1.537021,	-1.609847,	1.109526,	-1.109704,	0.385469,	0.965231,	
+0.818297,	0.037049,	-0.926012,	-0.111919,	-0.803030,	-1.665006,	-0.901401,	0.588350,	
+0.554159,	-0.415173,	0.061795,	0.457432,	0.199014,	0.257558,	2.080730,	-2.277237,	
+0.339022,	0.289894,	0.662261,	-0.580860,	0.887752,	0.171871,	0.848821,	0.963769,	
+1.321918,	-0.064345,	1.317053,	0.228017,	-1.429637,	-0.149701,	-0.504968,	-1.729141,	
+-0.417472,	-0.614969,	0.720777,	0.339364,	0.882845,	0.284245,	-0.145541,	-0.089646,	
+0.289161,	1.164831,	0.805729,	-1.355643,	0.120893,	-0.222178,	0.571732,	-0.300140,	
+1.134277,	-0.179356,	-1.467067,	1.395346,	0.440836,	0.565384,	-0.693623,	0.833869,	
+-2.237378,	1.097644,	-0.001617,	-1.614573,	-1.228727,	0.207405,	0.220942,	-1.006073,	
+-0.453067,	1.399453,	-0.461964,	0.032716,	0.798783,	0.896816,	0.137892,	-1.619146,	
+-1.646606,	0.428707,	-0.737231,	0.564926,	-1.384167,	0.460268,	0.629384,	0.379847,	
+-1.013330,	-0.347243,	0.441912,	-1.590240,	-0.701417,	-1.077601,	1.002220,	1.729481,	
+0.709032,	-0.747897,	0.228862,	-0.223497,	-0.853275,	0.345627,	0.109764,	-1.133039,	
+-0.683124,	-0.277856,	0.654790,	-1.248394,	-0.597539,	-0.481813,	0.983372,	1.762121,	
+1.427402,	0.911763,	0.326823,	0.069619,	-1.499763,	-0.418223,	-0.021037,	0.228425,	
+-1.008196,	-0.664622,	0.558177,	-1.188542,	-0.775481,	0.271042,	1.534976,	-1.052283,	
+0.625559,	-0.797626,	-0.313522,	-0.602210,	1.259060,	0.858484,	-2.105292,	-0.360937,	
+0.553557,	-1.556384,	-0.206666,	-0.425568,	0.493778,	-0.870908,	0.079828,	-0.521619,	
+-1.413861,	-0.384293,	-0.457922,	-0.291471,	-0.301224,	-1.588594,	1.094287,	1.324167,	
+-0.126480,	-0.737164,	0.213719,	-0.400529,	0.064938,	-1.757996,	1.686748,	0.327400,	
+0.715967,	1.598648,	-2.064741,	-0.743632,	0.176185,	0.527839,	-0.553153,	0.298280,	
+-1.226607,	-0.189676,	-0.301713,	0.956956,	-0.533366,	-0.901082,	-0.892552,	0.278717,	
+-0.745807,	1.603464,	0.574270,	0.320655,	-0.151383,	0.315762,	1.343703,	-2.237832,	
+1.292906,	-0.378459,	0.002521,	0.884641,	0.582450,	-1.614244,	-1.503666,	0.573586,	
+-0.910537,	-1.631277,	-0.359138,	-0.397616,	-1.161307,	-1.109838,	0.290672,	-1.910239,	
+1.314768,	0.665319,	-0.275115,	-0.023022,	-0.907976,	-1.043657,	0.373516,	0.901532,	
+1.278539,	-0.128456,	0.612821,	1.956518,	2.266326,	-0.373959,	2.238039,	-0.159580,	
+-0.703281,	0.563477,	-0.050296,	1.163593,	0.658808,	-1.550089,	-3.029118,	0.540578,	
+-1.008998,	0.908047,	1.582303,	-0.979088,	1.007902,	0.158491,	-0.586927,	1.574082,	
+-0.516649,	1.227800,	1.583876,	-2.088950,	2.949545,	1.356125,	1.050068,	-0.767170,	
+-0.257653,	-1.371845,	-1.267656,	-0.894948,	0.589089,	1.842629,	1.347967,	-0.491253,	
+-2.177568,	0.237000,	-0.735411,	-1.779419,	0.448030,	0.581214,	0.856607,	-0.266263,	
+-0.417470,	-0.205806,	-0.174323,	0.217577,	1.684295,	0.119528,	0.650667,	2.080061,	
+-0.339225,	0.730113,	0.293969,	-0.849109,	-2.533858,	-2.378941,	-0.346276,	-0.610937,	
+-0.408192,	-1.415611,	0.227122,	0.207974,	-0.719718,	0.757762,	-1.643135,	-1.056813,	
+-0.251662,	-1.298441,	1.233255,	1.494625,	0.235938,	-1.404359,	0.658791,	-2.556613,	
+-0.534945,	3.202525,	0.439198,	-1.149901,	0.886765,	-0.283386,	1.035336,	-0.364878,	
+1.341987,	1.008872,	0.213874,	-0.299264,	0.255849,	-0.190826,	-0.079060,	0.699851,	
+-0.796540,	-0.801284,	-0.007599,	-0.726810,	-1.490902,	0.870335,	-0.265675,	-1.566695,	
+-0.394636,	-0.143855,	-2.334247,	-1.357539,	-1.815689,	1.108422,	-0.142115,	1.112757,	
+0.559264,	0.478370,	-0.679385,	0.284967,	-1.332935,	-0.723980,	-0.663600,	0.198443,	
+-1.794868,	-1.387673,	0.197768,	1.469328,	0.366493,	-0.442775,	-0.048563,	0.077709,	
+1.957910,	-0.072848,	0.938810,	-0.079608,	-0.800959,	0.309424,	1.051826,	-1.664211,	
+-1.090792,	-0.191731,	0.463401,	-0.924147,	-0.649657,	0.622893,	-1.335107,	1.047689,	
+0.863327,	-0.642411,	0.660010,	1.294116,	0.314579,	0.859573,	0.128670,	0.016568,	
+-0.072801,	-0.994310,	-0.747358,	-0.030814,	0.988355,	-0.599017,	1.476644,	-0.813801,	
+0.645040,	-1.309919,	-0.867425,	-0.474233,	0.222417,	1.871323,	0.110001,	-0.411341,	
+0.511242,	-1.199117,	-0.096361,	0.445817,	-0.295825,	-0.167996,	0.179543,	0.421118,	
+1.677678,	1.996949,	0.696964,	-1.366382,	0.363045,	-0.567044,	-1.044154,	0.697139,	
+0.484026,	-0.193751,	-0.378095,	-0.886374,	-1.840197,	-1.628195,	-1.173789,	-0.415411,	
+0.175088,	0.229433,	-1.240889,	0.700004,	0.426877,	1.454803,	-0.510186,	-0.006657,	
+-0.525496,	0.717698,	1.088374,	0.500552,	2.771790,	-0.160309,	0.429489,	-1.966817,	
+-0.546019,	-1.888395,	-0.107952,	-1.316144,	-0.672632,	-0.902365,	-0.154798,	0.947242,	
+1.550375,	0.429040,	-0.560795,	0.179304,	-0.771509,	-0.943390,	-1.407569,	-1.906131,	
+-0.065293,	0.672149,	0.206147,	-0.008124,	0.020042,	-0.558447,	1.886079,	-0.219975,	
+-1.414395,	-0.302811,	-0.569574,	-0.121495,	-0.390171,	-0.844287,	-1.737757,	-0.449520,	
+-1.547933,	-0.095776,	0.907714,	2.369602,	0.519768,	0.410525,	1.052585,	0.428784,	
+1.295088,	-0.186053,	0.130733,	-0.657627,	-0.759267,	-0.595170,	0.812400,	0.069541,	
+-1.833687,	1.827363,	0.654075,	-1.544769,	-0.375109,	0.207688,	-0.765615,	-0.106355,	
+0.338769,	1.033461,	-1.404822,	-1.030570,	-0.643372,	0.170787,	1.344839,	1.936273,	
+0.741336,	0.811980,	-0.142808,	-0.099858,	-0.800131,	0.493249,	1.237574,	1.295951,	
+-0.278196,	0.217127,	0.630728,	-0.548549,	0.229632,	0.355311,	0.521284,	-0.615971,	
+1.345803,	0.974922,	-2.377934,	-1.092319,	-0.325710,	-2.012228,	1.567660,	0.233337,	
+0.646420,	-1.129412,	0.197038,	1.696870,	0.726034,	0.792526,	0.603357,	-0.058405,	
+-1.108666,	2.144229,	-1.352821,	0.457021,	0.391175,	2.073013,	-0.323318,	1.468132,	
+-0.502399,	0.209593,	0.754800,	-0.948189,	0.613157,	1.760503,	0.088762,	2.595570,	
+-0.675470,	2.786804,	-0.016827,	0.271651,	-0.914102,	-1.951371,	-0.317418,	0.588333,	
+0.828996,	-1.674851,	-1.922293,	-0.436662,	0.044974,	2.416609,	-0.309892,	0.187583,	
+0.947699,	-0.525703,	-1.115605,	-1.592320,	1.174844,	0.485144,	1.645480,	-0.454233,	
+1.008768,	2.049403,	0.602020,	0.017860,	-1.610426,	1.238752,	0.683587,	-0.780716,	
+0.530979,	2.134498,	0.354361,	0.231700,	1.287980,	-0.013488,	-1.333345,	-0.556343,	
+0.755597,	-0.911854,	1.371684,	0.245580,	0.118845,	0.384690,	-0.070152,	-0.578309,	
+0.469308,	1.299687,	1.634798,	-0.702809,	0.807253,	-1.027451,	1.294496,	0.014930,	
+0.218705,	1.713188,	-2.078805,	0.112917,	-1.086491,	-1.558311,	0.637406,	-0.404576,	
+-0.403325,	0.084076,	-0.435349,	-0.562623,	0.878062,	-0.814650,	-0.258363,	0.493299,	
+-0.802694,	-0.008329,	0.627571,	0.154382,	2.580735,	-1.306246,	1.023526,	0.777795,	
+-0.833884,	-0.586663,	0.065664,	-0.012342,	-0.076987,	-1.558587,	1.702607,	-0.468984,	
+0.094619,	0.287071,	0.919354,	0.510136,	0.245440,	-1.400519,	0.969571,	1.593698,	
+-1.437917,	-1.534230,	-0.074710,	0.081459,	-0.843240,	-0.564640,	-0.028207,	-1.243702,	
+0.733039,	0.059580,	0.149144,	1.595857,	-0.777250,	1.550277,	1.055002,	-0.166654,	
+0.314484,	1.419571,	0.327348,	0.475653,	0.398754,	-0.072770,	1.314784,	0.978279,	
+1.722114,	-0.412302,	0.565133,	0.739851,	0.220138,	1.312807,	0.629152,	-1.107987,	
+-0.447001,	-0.725993,	0.354045,	-0.506772,	-2.103747,	-0.664684,	1.450110,	-0.329805,	
+2.701872,	-1.634939,	-0.536325,	0.547223,	1.492603,	-0.455243,	-0.496416,	1.235260,	
+0.040926,	0.748467,	1.230764,	0.304903,	1.077771,	0.765151,	-1.319580,	-0.509191,	
+0.555116,	-1.957625,	-0.760453,	-2.443886,	-0.659366,	-0.114779,	0.300079,	-0.583996,	
+-3.073745,	1.551042,	-0.407369,	1.428095,	-1.353242,	0.903970,	0.541671,	-0.465020
+};
+
+
+
+/* ----------------------------------------------------------------------
+** Coefficients for 32-tap filter for Floating point LMS FIR filter
+*  FIR high pass filter with cutoff freq 9.6kHz (transition 9.6KHz to 11.52KHz) 
+** ------------------------------------------------------------------- */  
+float32_t lmsNormCoeff_f32[32] = {
+-0.004240,	0.002301,	0.008860,	-0.000000,	-0.019782,	-0.010543,	0.032881,	0.034736,	
+-0.037374,	-0.069586,	0.022397,	0.102169,	0.014185,	-0.115908,	-0.061648,	0.101018,	
+0.101018,	-0.061648,	-0.115908,	0.014185,	0.102169,	0.022397,	-0.069586,	-0.037374,	
+0.034736,	0.032881,	-0.010543,	-0.019782,	-0.000000,	0.008860,	0.002301,	-0.004240	
+
+};
+
+/* ----------------------------------------------------------------------
+** Coefficients for 32-tap filter for Floating point FIR filter
+*  FIR low pass filter with cutoff freq 24Hz (transition 24Hz to 240Hz) 
+** ------------------------------------------------------------------- */  
+const float32_t FIRCoeff_f32[32] = {
+0.004502,	0.005074,	0.006707,	0.009356,	0.012933,	0.017303,	0.022298,	0.027717,	
+0.033338,	0.038930,	0.044258,	0.049098,	0.053243,	0.056519,	0.058784,	0.059941,	
+0.059941,	0.058784,	0.056519,	0.053243,	0.049098,	0.044258,	0.038930,	0.033338,	
+0.027717,	0.022298,	0.017303,	0.012933,	0.009356,	0.006707,	0.005074,	0.004502
+
+};
+

libs/CMSIS/DSP_Lib/Examples/arm_signal_converge_example/arm_signal_converge_example_f32.c

@@ -0,0 +1,246 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3
+*  
+* Project: 	    CMSIS DSP Library  
+* Title:	    arm_signal_converge_example_f32.c		  
+*  
+* Description:	Example code demonstrating convergence of an adaptive 
+*               filter. 
+* 
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup SignalConvergence Signal Convergence Example    
+ * 
+ * \par Description: 
+ * \par
+ * Demonstrates the ability of an adaptive filter to "learn" the transfer function of 
+ * a FIR lowpass filter using the Normalized LMS Filter, Finite Impulse 
+ * Response (FIR) Filter, and Basic Math Functions.
+ * 
+ * \par Algorithm:
+ * \par
+ * The figure below illustrates the signal flow in this example. Uniformly distributed white 
+ * noise is passed through an FIR lowpass filter. The output of the FIR filter serves as the 
+ * reference input of the adaptive filter (normalized LMS filter). The white noise is input 
+ * to the adaptive filter. The adaptive filter learns the transfer function of the FIR filter.
+ * The filter outputs two signals: (1) the output of the internal adaptive FIR filter, and 
+ * (2) the error signal which is the difference between the adaptive filter and the reference 
+ * output of the FIR filter. Over time as the adaptive filter learns the transfer function 
+ * of the FIR filter, the first output approaches the reference output of the FIR filter,
+ * and the error signal approaches zero. 
+ * \par
+ * The adaptive filter converges properly even if the input signal has a large dynamic 
+ * range (i.e., varies from small to large values). The coefficients of the adaptive filter 
+ * are initially zero, and then converge over 1536 samples. The internal function test_signal_converge() 
+ * implements the stopping condition. The function checks if all of the values of the error signal have a 
+ * magnitude below a threshold DELTA. 
+ * 
+ * \par Block Diagram:
+ * \par
+ * \image html SignalFlow.gif 
+ *
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c testInput_f32 points to the input data
+ * \li \c firStateF32 points to FIR state buffer
+ * \li \c lmsStateF32 points to Normalised Least mean square FIR filter state buffer
+ * \li \c FIRCoeff_f32 points to coefficient buffer
+ * \li \c lmsNormCoeff_f32 points to Normalised Least mean square FIR filter coefficient buffer
+ * \li \c wire1, wir2, wire3 temporary buffers
+ * \li \c errOutput, err_signal temporary error buffers 
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_lms_norm_init_f32()
+ * - arm_fir_init_f32()
+ * - arm_fir_f32()
+ * - arm_lms_norm_f32()
+ * - arm_scale_f32()
+ * - arm_abs_f32()
+ * - arm_sub_f32()
+ * - arm_min_f32()
+ * - arm_copy_f32()
+ *
+ * <b> Refer  </b> 
+ * \link arm_signal_converge_example_f32.c \endlink
+ * 
+ */  
+ 
+ 
+/** \example arm_signal_converge_example_f32.c 
+  */  
+     
+#include "arm_math.h" 
+#include "math_helper.h" 
+ 
+/* ---------------------------------------------------------------------- 
+** Global defines for the simulation 
+* ------------------------------------------------------------------- */ 
+ 
+#define TEST_LENGTH_SAMPLES 1536 
+#define NUMTAPS 			32 
+#define BLOCKSIZE 			32 
+#define DELTA_ERROR         0.000001f 
+#define DELTA_COEFF         0.0001f 
+#define MU 					0.5f 
+ 
+#define NUMFRAMES (TEST_LENGTH_SAMPLES / BLOCKSIZE) 
+ 
+/* ---------------------------------------------------------------------- 
+* Declare FIR state buffers and structure  
+* ------------------------------------------------------------------- */ 
+  
+float32_t firStateF32[NUMTAPS + BLOCKSIZE];  
+arm_fir_instance_f32 LPF_instance; 
+ 
+/* ---------------------------------------------------------------------- 
+* Declare LMSNorm state buffers and structure  
+* ------------------------------------------------------------------- */ 
+  
+float32_t lmsStateF32[NUMTAPS + BLOCKSIZE];  
+float32_t errOutput[TEST_LENGTH_SAMPLES]; 
+arm_lms_norm_instance_f32 lmsNorm_instance; 
+ 
+ 
+/* ---------------------------------------------------------------------- 
+* Function Declarations for Signal Convergence Example  
+* ------------------------------------------------------------------- */ 
+ 
+arm_status test_signal_converge_example( void ); 
+ 
+ 
+/* ---------------------------------------------------------------------- 
+* Internal functions 
+* ------------------------------------------------------------------- */ 
+arm_status test_signal_converge(float32_t* err_signal, 
+			       			     uint32_t blockSize); 
+ 
+void getinput(float32_t* input, 
+		 uint32_t fr_cnt,  
+   	     uint32_t blockSize);  
+ 
+/* ---------------------------------------------------------------------- 
+* External Declarations for FIR F32 module Test 
+* ------------------------------------------------------------------- */ 
+extern float32_t testInput_f32[TEST_LENGTH_SAMPLES]; 
+extern float32_t lmsNormCoeff_f32[32]; 
+extern const float32_t FIRCoeff_f32[32]; 
+extern arm_lms_norm_instance_f32 lmsNorm_instance; 
+ 
+/* ---------------------------------------------------------------------- 
+* Declare I/O buffers  
+* ------------------------------------------------------------------- */ 
+ 
+float32_t wire1[BLOCKSIZE]; 
+float32_t wire2[BLOCKSIZE]; 
+float32_t wire3[BLOCKSIZE]; 
+float32_t err_signal[BLOCKSIZE]; 
+ 
+/* ---------------------------------------------------------------------- 
+* Signal converge test 
+* ------------------------------------------------------------------- */ 
+ 
+int32_t main(void) 
+{ 
+  uint32_t i; 
+  arm_status status; 
+  uint32_t index; 
+  float32_t minValue; 
+ 
+  /* Initialize the LMSNorm data structure */ 
+  arm_lms_norm_init_f32(&lmsNorm_instance, NUMTAPS, lmsNormCoeff_f32, lmsStateF32, MU, BLOCKSIZE); 
+ 
+  /* Initialize the FIR data structure */ 
+  arm_fir_init_f32(&LPF_instance, NUMTAPS, (float32_t *)FIRCoeff_f32, firStateF32, BLOCKSIZE); 
+ 
+  /* ---------------------------------------------------------------------- 
+  * Loop over the frames of data and execute each of the processing 
+  * functions in the system. 
+  * ------------------------------------------------------------------- */ 
+ 
+  for(i=0; i < NUMFRAMES; i++)  
+    { 
+      /* Read the input data - uniformly distributed random noise - into wire1 */  
+      arm_copy_f32(testInput_f32 + (i * BLOCKSIZE), wire1, BLOCKSIZE); 
+ 
+      /* Execute the FIR processing function.  Input wire1 and output wire2 */  
+      arm_fir_f32(&LPF_instance, wire1, wire2, BLOCKSIZE); 
+       
+      /* Execute the LMS Norm processing function*/  
+ 
+      arm_lms_norm_f32(&lmsNorm_instance, /* LMSNorm instance */ 
+		       wire1,                     /* Input signal */  
+		       wire2,			          /* Reference Signal */ 
+		       wire3, 			          /* Converged Signal */ 
+		       err_signal, 		          /* Error Signal, this will become small as the signal converges */ 
+		       BLOCKSIZE);		          /* BlockSize */ 
+ 
+      /* apply overall gain */  
+      arm_scale_f32(wire3, 5, wire3, BLOCKSIZE);	 /* in-place buffer */  
+    } 
+ 
+  status = ARM_MATH_SUCCESS; 
+ 
+  /* ------------------------------------------------------------------------------- 
+  * Test whether the error signal has reached towards 0. 
+  * ----------------------------------------------------------------------------- */ 
+ 
+  arm_abs_f32(err_signal, err_signal, BLOCKSIZE); 
+  arm_min_f32(err_signal, BLOCKSIZE, &minValue, &index); 
+ 
+  if (minValue > DELTA_ERROR) 
+  { 
+      status = ARM_MATH_TEST_FAILURE; 
+  } 
+ 
+  /* ---------------------------------------------------------------------- 
+  * Test whether the filter coefficients have converged. 
+  * ------------------------------------------------------------------- */ 
+ 
+  arm_sub_f32((float32_t *)FIRCoeff_f32, lmsNormCoeff_f32, lmsNormCoeff_f32, NUMTAPS); 
+ 
+  arm_abs_f32(lmsNormCoeff_f32, lmsNormCoeff_f32, NUMTAPS); 
+  arm_min_f32(lmsNormCoeff_f32, NUMTAPS, &minValue, &index); 
+ 
+  if (minValue > DELTA_COEFF) 
+  { 
+      status = ARM_MATH_TEST_FAILURE; 
+  } 
+ 
+  /* ---------------------------------------------------------------------- 
+  * Loop here if the signals did not pass the convergence check. 
+  * This denotes a test failure 
+  * ------------------------------------------------------------------- */ 
+ 
+  if( status != ARM_MATH_SUCCESS) 
+  { 
+      while(1); 
+  } 
+
+    while(1);                             /* main function does not return */
+} 
+ 
+ /** \endlink */ 
+		 
+ 
+		 

libs/CMSIS/DSP_Lib/Examples/arm_sin_cos_example/arm_sin_cos_example_f32.c

@@ -0,0 +1,146 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*  
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3
+*  
+* Project: 	    CMSIS DSP Library  
+* Title:	    arm_sin_cos_example_f32.c		  
+*  
+* Description:	Example code demonstrating sin and cos calculation of input signal. 
+* 
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */ 
+ 
+/** 
+ * @ingroup groupExamples 
+ */ 
+ 
+/**    
+ * @defgroup SinCosExample SineCosine Example    
+ * 
+ * \par Description:
+ * \par
+ * Demonstrates the Pythagorean trignometric identity with the use of Cosine, Sine, Vector
+ * Multiplication, and Vector Addition functions.
+ *
+ * \par Algorithm:
+ * \par
+ * Mathematically, the Pythagorean trignometric identity is defined by the following equation:
+ *  <pre>sin(x) * sin(x) + cos(x) * cos(x) = 1</pre> 
+ * where \c x is the angle in radians. 
+ *
+ * \par Block Diagram:
+ * \par
+ * \image html sinCos.gif 
+ * 
+ * \par Variables Description:
+ * \par
+ * \li \c testInput_f32 array of input angle in radians
+ * \li \c testOutput stores sum of the squares of sine and cosine values of input angle
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_cos_f32()
+ * - arm_sin_f32()
+ * - arm_mult_f32()
+ * - arm_add_f32()
+ * 
+ * <b> Refer  </b> 
+ * \link arm_sin_cos_example_f32.c \endlink
+ * 
+ */ 
+ 
+ 
+/** \example arm_sin_cos_example_f32.c 
+  */  
+ 
+#include <math.h>     
+#include "arm_math.h" 
+ 
+/* ---------------------------------------------------------------------- 
+* Defines each of the tests performed 
+* ------------------------------------------------------------------- */ 
+#define MAX_BLOCKSIZE	32 
+#define DELTA           (0.000001f) 
+ 
+ 
+/* ---------------------------------------------------------------------- 
+* Test input data for Floating point sin_cos example for 32-blockSize 
+* Generated by the MATLAB randn() function 
+* ------------------------------------------------------------------- */ 
+ 
+const float32_t testInput_f32[MAX_BLOCKSIZE] =  
+{    
+	-1.244916875853235400,	-4.793533929171324800,	0.360705030233248850,	0.827929644170887320,	-3.299532218312426900,	3.427441903227623800,	3.422401784294607700,	-0.108308165334010680,	 
+	0.941943896490312180,	0.502609575000365850,	-0.537345278736373500,	2.088817392965764500,	-1.693168684143455700,	6.283185307179590700,	-0.392545884746175080,	0.327893095115825040,	 
+	3.070147440456292300,	0.170611405884662230,	-0.275275082396073010,	-2.395492805446796300,	0.847311163536506600,	-3.845517018083148800,	2.055818378415868300,	4.672594161978930800,	 
+	-1.990923030266425800,	2.469305197656249500,	3.609002606064021000,	-4.586736582331667500,	-4.147080139136136300,	1.643756718868359500,	-1.150866392366494800,	1.985805026477433800 
+ 
+ 
+};  
+ 
+const float32_t testRefOutput_f32 = 1.000000000; 
+ 
+/* ---------------------------------------------------------------------- 
+* Declare Global variables  
+* ------------------------------------------------------------------- */ 
+uint32_t blockSize = 32; 
+float32_t  testOutput;  
+float32_t  cosOutput;  
+float32_t  sinOutput;  
+float32_t  cosSquareOutput;  
+float32_t  sinSquareOutput; 
+ 
+/* ---------------------------------------------------------------------- 
+* Max magnitude FFT Bin test 
+* ------------------------------------------------------------------- */ 
+
+arm_status status; 
+ 
+int32_t main(void) 
+{ 
+	float32_t diff; 
+	uint32_t i; 
+ 
+	for(i=0; i< blockSize; i++) 
+    { 
+        cosOutput = arm_cos_f32(testInput_f32[i]); 
+		sinOutput = arm_sin_f32(testInput_f32[i]); 
+ 
+		arm_mult_f32(&cosOutput, &cosOutput, &cosSquareOutput, 1); 
+		arm_mult_f32(&sinOutput, &sinOutput, &sinSquareOutput, 1); 
+ 
+		arm_add_f32(&cosSquareOutput, &sinSquareOutput, &testOutput, 1);
+ 
+		/* absolute value of difference between ref and test */ 
+	    diff = fabsf(testRefOutput_f32 - testOutput); 
+	 
+	    /* Comparison of sin_cos value with reference */ 
+	    if(diff > DELTA) 
+	    { 
+		   status = ARM_MATH_TEST_FAILURE; 
+	    } 
+		 
+	    if( status == ARM_MATH_TEST_FAILURE) 
+	    { 
+	       while(1); 
+	    } 
+ 
+    } 
+
+    while(1);                             /* main function does not return */
+} 
+ 
+ /** \endlink */ 
+ 

libs/CMSIS/DSP_Lib/Examples/arm_variance_example/arm_variance_example_f32.c

@@ -0,0 +1,189 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.     
+*    
+* $Date:        29. November 2010  
+* $Revision: 	V1.0.3
+*     
+* Project: 	    CMSIS DSP Library  
+* Title:	    arm_variance_example_f32.c		 
+* 
+* Description:	Example code demonstrating variance calculation of input sequence.
+*     
+* Target Processor: Cortex-M4/Cortex-M3  
+*
+*
+* Version 1.0.3 2010/11/29 
+*    Re-organized the CMSIS folders and updated documentation. 
+* 
+* Version 1.0.1 2010/10/05 KK 
+*    Production release and review comments incorporated.  
+*
+* Version 1.0.0 2010/09/20 KK
+*    Production release and review comments incorporated.
+* ------------------------------------------------------------------- */
+
+/**
+ * @ingroup groupExamples
+ */
+
+/**   
+ * @defgroup VarianceExample Variance Example   
+ *
+ * \par Description: 
+ * \par
+ * Demonstrates the use of Basic Math and Support Functions to calculate the variance of an 
+ * input sequence with N samples. Uniformly distributed white noise is taken as input. 
+ * 
+ * \par Algorithm:
+ * \par
+ * The variance of a sequence is the mean of the squared deviation of the sequence from its mean.
+ * \par
+ * This is denoted by the following equation: 
+ * <pre> variance = ((x[0] - x') * (x[0] - x') + (x[1] - x') * (x[1] - x') + ... + * (x[n-1] - x') * (x[n-1] - x')) / (N-1)</pre>
+ * where, <code>x[n]</code> is the input sequence, <code>N</code> is the number of input samples, and
+ * <code>x'</code> is the mean value of the input sequence, <code>x[n]</code>.
+ * \par
+ * The mean value <code>x'</code> is defined as:
+ * <pre> x' = (x[0] + x[1] + ... + x[n-1]) / N</pre>
+ *
+ * \par Block Diagram:
+ * \par
+ * \image html Variance.gif
+ *
+ *
+ * \par Variables Description:
+ * \par
+ * \li \c testInput_f32 points to the input data
+ * \li \c wire1, \c wir2, \c wire3 temporary buffers
+ * \li \c blockSize number of samples processed at a time
+ * \li \c refVarianceOut reference variance value 
+ *
+ * \par CMSIS DSP Software Library Functions Used:
+ * \par
+ * - arm_dot_prod_f32()
+ * - arm_mult_f32()
+ * - arm_sub_f32()
+ * - arm_fill_f32()
+ * - arm_copy_f32()
+ *
+ * <b> Refer  </b>
+ * \link arm_variance_example_f32.c \endlink
+ *
+ */
+
+
+/** \example arm_variance_example_f32.c
+  */ 
+#include <math.h>    
+#include "arm_math.h"
+
+/* ----------------------------------------------------------------------
+* Defines each of the tests performed
+* ------------------------------------------------------------------- */
+#define MAX_BLOCKSIZE	32
+#define DELTA           (0.000001f)
+
+
+/* ----------------------------------------------------------------------
+* Declare I/O buffers 
+* ------------------------------------------------------------------- */
+float32_t wire1[MAX_BLOCKSIZE];
+float32_t wire2[MAX_BLOCKSIZE];
+float32_t wire3[MAX_BLOCKSIZE];
+
+/* ----------------------------------------------------------------------
+* Test input data for Floating point Variance example for 32-blockSize
+* Generated by the MATLAB randn() function
+* ------------------------------------------------------------------- */
+
+float32_t testInput_f32[32] = 
+{ 
+-0.432564811528221, 	-1.665584378238097, 	0.125332306474831, 		0.287676420358549, 	
+-1.146471350681464, 	1.190915465642999, 		1.189164201652103, 		-0.037633276593318, 	
+0.327292361408654, 		0.174639142820925, 		-0.186708577681439, 	0.725790548293303, 	
+-0.588316543014189, 	2.183185818197101, 		-0.136395883086596, 	0.113931313520810, 	
+1.066768211359189, 		0.059281460523605, 		-0.095648405483669, 	-0.832349463650022, 	
+0.294410816392640, 		-1.336181857937804, 	0.714324551818952, 		1.623562064446271, 	
+-0.691775701702287, 	0.857996672828263, 		1.254001421602532, 		-1.593729576447477, 	
+-1.440964431901020, 	0.571147623658178, 		-0.399885577715363, 	0.689997375464345
+  
+};
+
+/* ----------------------------------------------------------------------
+* Declare Global variables 
+* ------------------------------------------------------------------- */
+uint32_t blockSize = 32;
+float32_t  refVarianceOut = 0.903941793931839; 
+
+/* ----------------------------------------------------------------------
+* Variance calculation test
+* ------------------------------------------------------------------- */
+
+int32_t main(void)
+{
+	arm_status status;
+	float32_t mean, oneByBlockSize;
+	float32_t variance;
+	float32_t diff;
+	
+	status = ARM_MATH_SUCCESS;
+	
+	/* Calculation of mean value of input */
+	
+	/* x' = 1/blockSize * (x(0)* 1 + x(1) * 1 + ... + x(n-1) * 1) */
+	
+	/* Fill wire1 buffer with 1.0 value */
+	arm_fill_f32(1.0,  wire1, blockSize);
+	
+	/* Calculate the dot product of wire1 and wire2 */
+	/* (x(0)* 1 + x(1) * 1 + ...+ x(n-1) * 1) */
+	arm_dot_prod_f32(testInput_f32, wire1, blockSize, &mean);
+	
+	/* Calculation of 1/blockSize */
+	oneByBlockSize = 1.0 / (blockSize);
+	
+	/* 1/blockSize * (x(0)* 1 + x(1) * 1 + ... + x(n-1) * 1)  */
+	arm_mult_f32(&mean, &oneByBlockSize, &mean, 1);
+	
+	
+	/* Calculation of variance value of input */
+	
+	/* (1/blockSize) * (x(0) - x') * (x(0) - x') + (x(1) - x') * (x(1) - x') + ... + (x(n-1) - x') * (x(n-1) - x') */
+	
+	/* Fill wire2 with mean value x' */
+	arm_fill_f32(mean,  wire2, blockSize);
+	
+	/* wire3 contains (x-x') */		
+	arm_sub_f32(testInput_f32, wire2, wire3, blockSize);
+	
+	/* wire2 contains (x-x') */				
+	arm_copy_f32(wire3, wire2, blockSize);
+	
+	/* (x(0) - x') * (x(0) - x') + (x(1) - x') * (x(1) - x') + ... + (x(n-1) - x') * (x(n-1) - x') */
+	arm_dot_prod_f32(wire2, wire3, blockSize, &variance); 
+
+    /* Calculation of 1/blockSize */
+	oneByBlockSize = 1.0 / (blockSize - 1);
+
+	/* Calculation of variance */		
+	arm_mult_f32(&variance, &oneByBlockSize, &variance, 1);
+	
+	/* absolute value of difference between ref and test */
+	diff = fabsf(refVarianceOut - variance);
+	
+	/* Comparison of variance value with reference */
+	if(diff > DELTA)
+	{
+		status = ARM_MATH_TEST_FAILURE;
+	}
+		
+	if( status != ARM_MATH_SUCCESS)
+	{
+	  while(1);
+	}
+
+    while(1);                             /* main function does not return */
+}
+
+ /** \endlink */
+

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_f32.c

@@ -0,0 +1,159 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_f32.c    
+*    
+* Description:	Vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include <math.h>
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicAbs Vector Absolute Value        
+ *        
+ * Computes the absolute value of a vector on an element-by-element basis.        
+ *        
+ * <pre>        
+ *     pDst[n] = abs(pSrcA[n]),   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * The operation can be done in-place by setting the input and output pointers to the same buffer.        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup BasicAbs        
+ * @{        
+ */
+
+/**        
+ * @brief Floating-point vector absolute value.        
+ * @param[in]       *pSrc points to the input buffer        
+ * @param[out]      *pDst points to the output buffer        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_abs_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;                  /* temporary variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute and then store the results in the destination buffer. */
+    /* read sample from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+    in3 = *(pSrc + 2);
+
+    /* find absolute value */
+    in1 = fabsf(in1);
+
+    /* read sample from source */
+    in4 = *(pSrc + 3);
+
+    /* find absolute value */
+    in2 = fabsf(in2);
+
+    /* read sample from source */
+    *pDst = in1;
+
+    /* find absolute value */
+    in3 = fabsf(in3);
+
+    /* find absolute value */
+    in4 = fabsf(in4);
+
+    /* store result to destination */
+    *(pDst + 1) = in2;
+
+    /* store result to destination */
+    *(pDst + 2) = in3;
+
+    /* store result to destination */
+    *(pDst + 3) = in4;
+
+
+    /* Update source pointer to process next sampels */
+    pSrc += 4u;
+
+    /* Update destination pointer to process next sampels */
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /*   #ifndef ARM_MATH_CM0   */
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute and then store the results in the destination buffer. */
+    *pDst++ = fabsf(*pSrc++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicAbs group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q15.c

@@ -0,0 +1,173 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_q15.c    
+*    
+* Description:	Q15 vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAbs    
+ * @{    
+ */
+
+/**    
+ * @brief Q15 vector absolute value.    
+ * @param[in]       *pSrc points to the input buffer    
+ * @param[out]      *pDst points to the output buffer    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.    
+ */
+
+void arm_abs_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q15_t in1;                                     /* Input value1 */
+  q15_t in2;                                     /* Input value2 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read two inputs */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+
+
+    /* Store the Absolute result in the destination buffer by packing the two values, in a single cycle */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+    *__SIMD32(pDst)++ =
+      __PKHBT(((in1 > 0) ? in1 : __QSUB16(0, in1)),
+              ((in2 > 0) ? in2 : __QSUB16(0, in2)), 16);
+
+#else
+
+
+    *__SIMD32(pDst)++ =
+      __PKHBT(((in2 > 0) ? in2 : __QSUB16(0, in2)),
+              ((in1 > 0) ? in1 : __QSUB16(0, in1)), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+    *__SIMD32(pDst)++ =
+      __PKHBT(((in1 > 0) ? in1 : __QSUB16(0, in1)),
+              ((in2 > 0) ? in2 : __QSUB16(0, in2)), 16);
+
+#else
+
+
+    *__SIMD32(pDst)++ =
+      __PKHBT(((in2 > 0) ? in2 : __QSUB16(0, in2)),
+              ((in1 > 0) ? in1 : __QSUB16(0, in1)), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read the input */
+    in1 = *pSrc++;
+
+    /* Calculate absolute value of input and then store the result in the destination buffer. */
+    *pDst++ = (in1 > 0) ? in1 : __QSUB16(0, in1);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  q15_t in;                                      /* Temporary input variable */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read the input */
+    in = *pSrc++;
+
+    /* Calculate absolute value of input and then store the result in the destination buffer. */
+    *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of BasicAbs group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q31.c

@@ -0,0 +1,125 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_q31.c    
+*    
+* Description:	Q31 vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAbs    
+ * @{    
+ */
+
+
+/**    
+ * @brief Q31 vector absolute value.    
+ * @param[in]       *pSrc points to the input buffer    
+ * @param[out]      *pDst points to the output buffer    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.    
+ */
+
+void arm_abs_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in;                                      /* Input value */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute of input (if -1 then saturated to 0x7fffffff) and then store the results in the destination buffer. */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    *pDst++ = (in1 > 0) ? in1 : __QSUB(0, in1);
+    *pDst++ = (in2 > 0) ? in2 : __QSUB(0, in2);
+    *pDst++ = (in3 > 0) ? in3 : __QSUB(0, in3);
+    *pDst++ = (in4 > 0) ? in4 : __QSUB(0, in4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /*   #ifndef ARM_MATH_CM0   */
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute value of the input (if -1 then saturated to 0x7fffffff) and then store the results in the destination buffer. */
+    in = *pSrc++;
+    *pDst++ = (in > 0) ? in : ((in == 0x80000000) ? 0x7fffffff : -in);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+}
+
+/**    
+ * @} end of BasicAbs group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q7.c

@@ -0,0 +1,152 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_q7.c    
+*    
+* Description:	Q7 vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @addtogroup BasicAbs        
+ * @{        
+ */
+
+/**        
+ * @brief Q7 vector absolute value.        
+ * @param[in]       *pSrc points to the input buffer        
+ * @param[out]      *pDst points to the output buffer        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ *    
+ * \par Conditions for optimum performance    
+ *  Input and output buffers should be aligned by 32-bit    
+ *    
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.        
+ */
+
+void arm_abs_q7(
+  q7_t * pSrc,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q7_t in;                                       /* Input value1 */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;                      /* temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* temporary output variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read inputs */
+    in1 = (q31_t) * pSrc;
+    in2 = (q31_t) * (pSrc + 1);
+    in3 = (q31_t) * (pSrc + 2);
+
+    /* find absolute value */
+    out1 = (in1 > 0) ? in1 : __QSUB8(0, in1);
+
+    /* read input */
+    in4 = (q31_t) * (pSrc + 3);
+
+    /* find absolute value */
+    out2 = (in2 > 0) ? in2 : __QSUB8(0, in2);
+
+    /* store result to destination */
+    *pDst = (q7_t) out1;
+
+    /* find absolute value */
+    out3 = (in3 > 0) ? in3 : __QSUB8(0, in3);
+
+    /* find absolute value */
+    out4 = (in4 > 0) ? in4 : __QSUB8(0, in4);
+
+    /* store result to destination */
+    *(pDst + 1) = (q7_t) out2;
+
+    /* store result to destination */
+    *(pDst + 2) = (q7_t) out3;
+
+    /* store result to destination */
+    *(pDst + 3) = (q7_t) out4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = blockSize;
+
+#endif //      #define ARM_MATH_CM0
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read the input */
+    in = *pSrc++;
+
+    /* Store the Absolute result in the destination buffer */
+    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? 0x7f : -in);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicAbs group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_f32.c

@@ -0,0 +1,145 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_f32.c    
+*    
+* Description:	Floating-point vector addition.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicAdd Vector Addition        
+ *        
+ * Element-by-element addition of two vectors.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrcA[n] + pSrcB[n],   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup BasicAdd        
+ * @{        
+ */
+
+/**        
+ * @brief Floating-point vector addition.        
+ * @param[in]       *pSrcA points to the first input vector        
+ * @param[in]       *pSrcB points to the second input vector        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_add_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* temporary input variabels */
+  float32_t inB1, inB2, inB3, inB4;              /* temporary input variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+
+    /* read four inputs from sourceA and four inputs from sourceB */
+    inA1 = *pSrcA;
+    inB1 = *pSrcB;
+    inA2 = *(pSrcA + 1);
+    inB2 = *(pSrcB + 1);
+    inA3 = *(pSrcA + 2);
+    inB3 = *(pSrcB + 2);
+    inA4 = *(pSrcA + 3);
+    inB4 = *(pSrcB + 3);
+
+    /* C = A + B */
+    /* add and store result to destination */
+    *pDst = inA1 + inB1;
+    *(pDst + 1) = inA2 + inB2;
+    *(pDst + 2) = inA3 + inB3;
+    *(pDst + 3) = inA4 + inB4;
+
+    /* update pointers to process next samples */
+    pSrcA += 4u;
+    pSrcB += 4u;
+    pDst += 4u;
+
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicAdd group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c

@@ -0,0 +1,135 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_q15.c    
+*    
+* Description:	Q15 vector addition    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAdd    
+ * @{    
+ */
+
+/**    
+ * @brief Q15 vector addition.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_add_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inB1, inB2;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    inA1 = *__SIMD32(pSrcA)++;
+    inA2 = *__SIMD32(pSrcA)++;
+    inB1 = *__SIMD32(pSrcB)++;
+    inB2 = *__SIMD32(pSrcB)++;
+
+    *__SIMD32(pDst)++ = __QADD16(inA1, inB1);
+    *__SIMD32(pDst)++ = __QADD16(inA2, inB2);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __QADD16(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ + *pSrcB++), 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+}
+
+/**    
+ * @} end of BasicAdd group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q31.c

@@ -0,0 +1,143 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_q31.c    
+*    
+* Description:	Q31 vector addition.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAdd    
+ * @{    
+ */
+
+
+/**    
+ * @brief Q31 vector addition.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_add_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;
+  q31_t inB1, inB2, inB3, inB4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    *pDst++ = __QADD(inA1, inB1);
+    *pDst++ = __QADD(inA2, inB2);
+    *pDst++ = __QADD(inA3, inB3);
+    *pDst++ = __QADD(inA4, inB4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrcA++ + *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of BasicAdd group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q7.c

@@ -0,0 +1,129 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_q7.c    
+*    
+* Description:	Q7 vector addition.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAdd    
+ * @{    
+ */
+
+/**    
+ * @brief Q7 vector addition.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
+ */
+
+void arm_add_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT(*pSrcA++ + *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ + *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+}
+
+/**    
+ * @} end of BasicAdd group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_f32.c

@@ -0,0 +1,125 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_f32.c    
+*    
+* Description:	Floating-point dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @defgroup dot_prod Vector Dot Product    
+ *    
+ * Computes the dot product of two vectors.    
+ * The vectors are multiplied element-by-element and then summed.    
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of floating-point vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ */
+
+
+void arm_dot_prod_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  uint32_t blockSize,
+  float32_t * result)
+{
+  float32_t sum = 0.0f;                          /* Temporary result storage */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer */
+    sum += (*pSrcA++) * (*pSrcB++);
+    sum += (*pSrcA++) * (*pSrcB++);
+    sum += (*pSrcA++) * (*pSrcB++);
+    sum += (*pSrcA++) * (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    sum += (*pSrcA++) * (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+  /* Store the result back in the destination buffer */
+  *result = sum;
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_q15.c

@@ -0,0 +1,135 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_q15.c    
+*    
+* Description:	Q15 dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of Q15 vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The intermediate multiplications are in 1.15 x 1.15 = 2.30 format and these    
+ * results are added to a 64-bit accumulator in 34.30 format.    
+ * Nonsaturating additions are used and given that there are 33 guard bits in the accumulator    
+ * there is no risk of overflow.    
+ * The return result is in 34.30 format.    
+ */
+
+void arm_dot_prod_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  uint32_t blockSize,
+  q63_t * result)
+{
+  q63_t sum = 0;                                 /* Temporary result storage */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
+    sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the results in a temporary buffer. */
+    sum = __SMLALD(*pSrcA++, *pSrcB++, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the results in a temporary buffer. */
+    sum += (q63_t) ((q31_t) * pSrcA++ * *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  /* Store the result in the destination buffer in 34.30 format */
+  *result = sum;
+
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_q31.c

@@ -0,0 +1,138 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_q31.c    
+*    
+* Description:	Q31 dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of Q31 vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The intermediate multiplications are in 1.31 x 1.31 = 2.62 format and these    
+ * are truncated to 2.48 format by discarding the lower 14 bits.    
+ * The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format.    
+ * There are 15 guard bits in the accumulator and there is no risk of overflow as long as    
+ * the length of the vectors is less than 2^16 elements.    
+ * The return result is in 16.48 format.    
+ */
+
+void arm_dot_prod_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  uint32_t blockSize,
+  q63_t * result)
+{
+  q63_t sum = 0;                                 /* Temporary result storage */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;
+  q31_t inB1, inB2, inB3, inB4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    sum += ((q63_t) inA1 * inB1) >> 14u;
+    sum += ((q63_t) inA2 * inB2) >> 14u;
+    sum += ((q63_t) inA3 * inB3) >> 14u;
+    sum += ((q63_t) inA4 * inB4) >> 14u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    sum += ((q63_t) * pSrcA++ * *pSrcB++) >> 14u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* Store the result in the destination buffer in 16.48 format */
+  *result = sum;
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_q7.c

@@ -0,0 +1,154 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_q7.c    
+*    
+* Description:	Q7 dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of Q7 vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The intermediate multiplications are in 1.7 x 1.7 = 2.14 format and these    
+ * results are added to an accumulator in 18.14 format.    
+ * Nonsaturating additions are used and there is no danger of wrap around as long as    
+ * the vectors are less than 2^18 elements long.    
+ * The return result is in 18.14 format.    
+ */
+
+void arm_dot_prod_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  uint32_t blockSize,
+  q31_t * result)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+  q31_t sum = 0;                                 /* Temporary variables to store output */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q31_t input1, input2;                          /* Temporary variables to store input */
+  q31_t inA1, inA2, inB1, inB2;                  /* Temporary variables to store input */
+
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read 4 samples at a time from sourceA */
+    input1 = *__SIMD32(pSrcA)++;
+    /* read 4 samples at a time from sourceB */
+    input2 = *__SIMD32(pSrcB)++;
+
+    /* extract two q7_t samples to q15_t samples */
+    inA1 = __SXTB16(__ROR(input1, 8));
+    /* extract reminaing two samples */
+    inA2 = __SXTB16(input1);
+    /* extract two q7_t samples to q15_t samples */
+    inB1 = __SXTB16(__ROR(input2, 8));
+    /* extract reminaing two samples */
+    inB2 = __SXTB16(input2);
+
+    /* multiply and accumulate two samples at a time */
+    sum = __SMLAD(inA1, inB1, sum);
+    sum = __SMLAD(inA2, inB2, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Dot product and then store the results in a temporary buffer. */
+    sum = __SMLAD(*pSrcA++, *pSrcB++, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Dot product and then store the results in a temporary buffer. */
+    sum += (q31_t) ((q15_t) * pSrcA++ * *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+  /* Store the result in the destination buffer in 18.14 format */
+  *result = sum;
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_f32.c

@@ -0,0 +1,172 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_f32.c    
+*    
+* Description:	Floating-point vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.5  2010/04/26     
+*    incorporated review comments and updated with latest CMSIS layer    
+*    
+* Version 0.0.3  2010/03/10     
+*    Initial version    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicMult Vector Multiplication        
+ *        
+ * Element-by-element multiplication of two vectors.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrcA[n] * pSrcB[n],   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup BasicMult        
+ * @{        
+ */
+
+/**        
+ * @brief Floating-point vector multiplication.        
+ * @param[in]       *pSrcA points to the first input vector        
+ * @param[in]       *pSrcB points to the second input vector        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_mult_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* temporary input variables */
+  float32_t inB1, inB2, inB3, inB4;              /* temporary input variables */
+  float32_t out1, out2, out3, out4;              /* temporary output variables */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the results in output buffer */
+    /* read sample from sourceA */
+    inA1 = *pSrcA;
+    /* read sample from sourceB */
+    inB1 = *pSrcB;
+    /* read sample from sourceA */
+    inA2 = *(pSrcA + 1);
+    /* read sample from sourceB */
+    inB2 = *(pSrcB + 1);
+
+    /* out = sourceA * sourceB */
+    out1 = inA1 * inB1;
+
+    /* read sample from sourceA */
+    inA3 = *(pSrcA + 2);
+    /* read sample from sourceB */
+    inB3 = *(pSrcB + 2);
+
+    /* out = sourceA * sourceB */
+    out2 = inA2 * inB2;
+
+    /* read sample from sourceA */
+    inA4 = *(pSrcA + 3);
+
+    /* store result to destination buffer */
+    *pDst = out1;
+
+    /* read sample from sourceB */
+    inB4 = *(pSrcB + 3);
+
+    /* out = sourceA * sourceB */
+    out3 = inA3 * inB3;
+
+    /* store result to destination buffer */
+    *(pDst + 1) = out2;
+
+    /* out = sourceA * sourceB */
+    out4 = inA4 * inB4;
+    /* store result to destination buffer */
+    *(pDst + 2) = out3;
+    /* store result to destination buffer */
+    *(pDst + 3) = out4;
+
+
+    /* update pointers to process next samples */
+    pSrcA += 4u;
+    pSrcB += 4u;
+    pDst += 4u;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the results in output buffer */
+    *pDst++ = (*pSrcA++) * (*pSrcB++);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicMult group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q15.c

@@ -0,0 +1,152 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_q15.c    
+*    
+* Description:	Q15 vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.5  2010/04/26     
+*    incorporated review comments and updated with latest CMSIS layer    
+*    
+* Version 0.0.3  2010/03/10     
+*    Initial version    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief           Q15 vector multiplication    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_mult_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inB1, inB2;                  /* temporary input variables */
+  q15_t out1, out2, out3, out4;                  /* temporary output variables */
+  q31_t mul1, mul2, mul3, mul4;                  /* temporary variables */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read two samples at a time from sourceA */
+    inA1 = *__SIMD32(pSrcA)++;
+    /* read two samples at a time from sourceB */
+    inB1 = *__SIMD32(pSrcB)++;
+    /* read two samples at a time from sourceA */
+    inA2 = *__SIMD32(pSrcA)++;
+    /* read two samples at a time from sourceB */
+    inB2 = *__SIMD32(pSrcB)++;
+
+    /* multiply mul = sourceA * sourceB */
+    mul1 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
+    mul2 = (q31_t) ((q15_t) inA1 * (q15_t) inB1);
+    mul3 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB2 >> 16));
+    mul4 = (q31_t) ((q15_t) inA2 * (q15_t) inB2);
+
+    /* saturate result to 16 bit */
+    out1 = (q15_t) __SSAT(mul1 >> 15, 16);
+    out2 = (q15_t) __SSAT(mul2 >> 15, 16);
+    out3 = (q15_t) __SSAT(mul3 >> 15, 16);
+    out4 = (q15_t) __SSAT(mul4 >> 15, 16);
+
+    /* store the result */
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
+    *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
+
+#else
+
+    *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
+    *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
+
+#endif //      #ifndef ARM_MATH_BIG_ENDIAN
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the result in the destination buffer */
+    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of BasicMult group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q31.c

@@ -0,0 +1,143 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_q31.c    
+*    
+* Description:	Q31 vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.5  2010/04/26     
+*    incorporated review comments and updated with latest CMSIS layer    
+*    
+* Version 0.0.3  2010/03/10     
+*    Initial version    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicMult    
+ * @{    
+ */
+
+/**    
+ * @brief Q31 vector multiplication.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_mult_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;                  /* temporary input variables */
+  q31_t inB1, inB2, inB3, inB4;                  /* temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* temporary output variables */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and then store the results in the destination buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB2) >> 32;
+    out3 = ((q63_t) inA3 * inB3) >> 32;
+    out4 = ((q63_t) inA4 * inB4) >> 32;
+
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+    out3 = __SSAT(out3, 31);
+    out4 = __SSAT(out4, 31);
+
+    *pDst++ = out1 << 1u;
+    *pDst++ = out2 << 1u;
+    *pDst++ = out3 << 1u;
+    *pDst++ = out4 << 1u;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and then store the results in the destination buffer. */
+    *pDst++ =
+      (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of BasicMult group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c

@@ -0,0 +1,128 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_q7.c    
+*    
+* Description:	Q7 vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+*    
+* Version 0.0.5  2010/04/26     
+*    incorporated review comments and updated with latest CMSIS layer    
+*    
+* Version 0.0.3  2010/03/10 DP    
+*    Initial version    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicMult    
+ * @{    
+ */
+
+/**    
+ * @brief           Q7 vector multiplication    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
+ */
+
+void arm_mult_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q7_t out1, out2, out3, out4;                   /* Temporary variables to store the product */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the results in temporary variables */
+    out1 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out2 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out3 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out4 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+
+    /* Store the results of 4 inputs in the destination buffer in single cycle by packing */
+    *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the result in the destination buffer */
+    *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of BasicMult group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_f32.c

@@ -0,0 +1,137 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_f32.c    
+*    
+* Description:	Negates floating-point vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup negate Vector Negate        
+ *        
+ * Negates the elements of a vector.        
+ *        
+ * <pre>        
+ *     pDst[n] = -pSrc[n],   0 <= n < blockSize.        
+ * </pre>        
+ */
+
+/**        
+ * @addtogroup negate        
+ * @{        
+ */
+
+/**        
+ * @brief  Negates the elements of a floating-point vector.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ */
+
+void arm_negate_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;                  /* temporary variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read inputs from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+    in3 = *(pSrc + 2);
+    in4 = *(pSrc + 3);
+
+    /* negate the input */
+    in1 = -in1;
+    in2 = -in2;
+    in3 = -in3;
+    in4 = -in4;
+
+    /* store the result to destination */
+    *pDst = in1;
+    *(pDst + 1) = in2;
+    *(pDst + 2) = in3;
+    *(pDst + 3) = in4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the results in the destination buffer. */
+    *pDst++ = -*pSrc++;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of negate group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_q15.c

@@ -0,0 +1,137 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_q15.c    
+*    
+* Description:	Negates Q15 vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @addtogroup negate        
+ * @{        
+ */
+
+/**        
+ * @brief  Negates the elements of a Q15 vector.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ *    
+ * \par Conditions for optimum performance    
+ *  Input and output buffers should be aligned by 32-bit    
+ *    
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.        
+ */
+
+void arm_negate_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q15_t in;
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q31_t in1, in2;                                /* Temporary variables */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Read two inputs at a time */
+    in1 = _SIMD32_OFFSET(pSrc);
+    in2 = _SIMD32_OFFSET(pSrc + 2);
+
+    /* negate two samples at a time */
+    in1 = __QSUB16(0, in1);
+
+    /* negate two samples at a time */
+    in2 = __QSUB16(0, in2);
+
+    /* store the result to destination 2 samples at a time */
+    _SIMD32_OFFSET(pDst) = in1;
+    /* store the result to destination 2 samples at a time */
+    _SIMD32_OFFSET(pDst + 2) = in2;
+
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the result in the destination buffer. */
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? 0x7fff : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of negate group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_q31.c

@@ -0,0 +1,124 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_q31.c    
+*    
+* Description:	Negates Q31 vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup negate    
+ * @{    
+ */
+
+/**    
+ * @brief  Negates the elements of a Q31 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.    
+ */
+
+void arm_negate_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  q31_t in;                                      /* Temporary variable */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the results in the destination buffer. */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    *pDst++ = __QSUB(0, in1);
+    *pDst++ = __QSUB(0, in2);
+    *pDst++ = __QSUB(0, in3);
+    *pDst++ = __QSUB(0, in4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the result in the destination buffer. */
+    in = *pSrc++;
+    *pDst++ = (in == 0x80000000) ? 0x7fffffff : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of negate group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_q7.c

@@ -0,0 +1,120 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_q7.c    
+*    
+* Description:	Negates Q7 vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup negate    
+ * @{    
+ */
+
+/**    
+ * @brief  Negates the elements of a Q7 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.    
+ */
+
+void arm_negate_q7(
+  q7_t * pSrc,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q7_t in;
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t input;                                   /* Input values1-4 */
+  q31_t zero = 0x00000000;
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Read four inputs */
+    input = *__SIMD32(pSrc)++;
+
+    /* Store the Negated results in the destination buffer in a single cycle by packing the results */
+    *__SIMD32(pDst)++ = __QSUB8(zero, input);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the results in the destination buffer. */ \
+      in = *pSrc++;
+    *pDst++ = (in == (q7_t) 0x80) ? 0x7f : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of negate group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_f32.c

@@ -0,0 +1,158 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_f32.c    
+*    
+* Description:	Floating-point vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup offset Vector Offset        
+ *        
+ * Adds a constant offset to each element of a vector.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrc[n] + offset,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup offset        
+ * @{        
+ */
+
+/**        
+ * @brief  Adds a constant offset to a floating-point vector.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[in]  offset is the offset to be added        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ */
+
+
+void arm_offset_f32(
+  float32_t * pSrc,
+  float32_t offset,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    /* read samples from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+
+    /* add offset to input */
+    in1 = in1 + offset;
+
+    /* read samples from source */
+    in3 = *(pSrc + 2);
+
+    /* add offset to input */
+    in2 = in2 + offset;
+
+    /* read samples from source */
+    in4 = *(pSrc + 3);
+
+    /* add offset to input */
+    in3 = in3 + offset;
+
+    /* store result to destination */
+    *pDst = in1;
+
+    /* add offset to input */
+    in4 = in4 + offset;
+
+    /* store result to destination */
+    *(pDst + 1) = in2;
+
+    /* store result to destination */
+    *(pDst + 2) = in3;
+
+    /* store result to destination */
+    *(pDst + 3) = in4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (*pSrc++) + offset;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of offset group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_q15.c

@@ -0,0 +1,131 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_q15.c    
+*    
+* Description:	Q15 vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup offset    
+ * @{    
+ */
+
+/**    
+ * @brief  Adds a constant offset to a Q15 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  offset is the offset to be added    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.    
+ */
+
+void arm_offset_q15(
+  q15_t * pSrc,
+  q15_t offset,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t offset_packed;                           /* Offset packed to 32 bit */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Offset is packed to 32 bit in order to use SIMD32 for addition */
+  offset_packed = __PKHBT(offset, offset, 16);
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer, 2 samples at a time. */
+    *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed);
+    *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __QADD16(*pSrc++, offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrc++ + offset), 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of offset group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_q31.c

@@ -0,0 +1,135 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_q31.c    
+*    
+* Description:	Q31 vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup offset    
+ * @{    
+ */
+
+/**    
+ * @brief  Adds a constant offset to a Q31 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  offset is the offset to be added    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.    
+ */
+
+void arm_offset_q31(
+  q31_t * pSrc,
+  q31_t offset,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    *pDst++ = __QADD(in1, offset);
+    *pDst++ = __QADD(in2, offset);
+    *pDst++ = __QADD(in3, offset);
+    *pDst++ = __QADD(in4, offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = __QADD(*pSrc++, offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrc++ + offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of offset group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_q7.c

@@ -0,0 +1,130 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_q7.c    
+*    
+* Description:	Q7 vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup offset    
+ * @{    
+ */
+
+/**    
+ * @brief  Adds a constant offset to a Q7 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  offset is the offset to be added    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] are saturated.    
+ */
+
+void arm_offset_q7(
+  q7_t * pSrc,
+  q7_t offset,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t offset_packed;                           /* Offset packed to 32 bit */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Offset is packed to 32 bit in order to use SIMD32 for addition */
+  offset_packed = __PACKq7(offset, offset, offset, offset);
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination bufferfor 4 samples at a time. */
+    *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrc)++, offset_packed);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) * pSrc++ + offset, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of offset group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_f32.c

@@ -0,0 +1,161 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_f32.c    
+*    
+* Description:	Multiplies a floating-point vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup scale Vector Scale        
+ *        
+ * Multiply a vector by a scalar value.  For floating-point data, the algorithm used is:        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrc[n] * scale,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * In the fixed-point Q7, Q15, and Q31 functions, <code>scale</code> is represented by        
+ * a fractional multiplication <code>scaleFract</code> and an arithmetic shift <code>shift</code>.        
+ * The shift allows the gain of the scaling operation to exceed 1.0.        
+ * The algorithm used with fixed-point data is:        
+ *        
+ * <pre>        
+ *     pDst[n] = (pSrc[n] * scaleFract) << shift,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * The overall scale factor applied to the fixed-point data is        
+ * <pre>        
+ *     scale = scaleFract * 2^shift.        
+ * </pre>        
+ */
+
+/**        
+ * @addtogroup scale        
+ * @{        
+ */
+
+/**        
+ * @brief Multiplies a floating-point vector by a scalar.        
+ * @param[in]       *pSrc points to the input vector        
+ * @param[in]       scale scale factor to be applied        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in the vector        
+ * @return none.        
+ */
+
+
+void arm_scale_f32(
+  float32_t * pSrc,
+  float32_t scale,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;                  /* temporary variabels */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the results in the destination buffer. */
+    /* read input samples from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+
+    /* multiply with scaling factor */
+    in1 = in1 * scale;
+
+    /* read input sample from source */
+    in3 = *(pSrc + 2);
+
+    /* multiply with scaling factor */
+    in2 = in2 * scale;
+
+    /* read input sample from source */
+    in4 = *(pSrc + 3);
+
+    /* multiply with scaling factor */
+    in3 = in3 * scale;
+    in4 = in4 * scale;
+    /* store the result to destination */
+    *pDst = in1;
+    *(pDst + 1) = in2;
+    *(pDst + 2) = in3;
+    *(pDst + 3) = in4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (*pSrc++) * scale;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of scale group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_q15.c

@@ -0,0 +1,157 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_q15.c    
+*    
+* Description:	Multiplies a Q15 vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup scale    
+ * @{    
+ */
+
+/**    
+ * @brief Multiplies a Q15 vector by a scalar.    
+ * @param[in]       *pSrc points to the input vector    
+ * @param[in]       scaleFract fractional portion of the scale value    
+ * @param[in]       shift number of bits to shift the result by    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.    
+ * These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.    
+ */
+
+
+void arm_scale_q15(
+  q15_t * pSrc,
+  q15_t scaleFract,
+  int8_t shift,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  int8_t kShift = 15 - shift;                    /* shift to apply after scaling */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q15_t in1, in2, in3, in4;
+  q31_t inA1, inA2;                              /* Temporary variables */
+  q31_t out1, out2, out3, out4;
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* Reading 2 inputs from memory */
+    inA1 = *__SIMD32(pSrc)++;
+    inA2 = *__SIMD32(pSrc)++;
+
+    /* C = A * scale */
+    /* Scale the inputs and then store the 2 results in the destination buffer        
+     * in single cycle by packing the outputs */
+    out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract);
+    out2 = (q31_t) ((q15_t) inA1 * scaleFract);
+    out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract);
+    out4 = (q31_t) ((q15_t) inA2 * scaleFract);
+
+    /* apply shifting */
+    out1 = out1 >> kShift;
+    out2 = out2 >> kShift;
+    out3 = out3 >> kShift;
+    out4 = out4 >> kShift;
+
+    /* saturate the output */
+    in1 = (q15_t) (__SSAT(out1, 16));
+    in2 = (q15_t) (__SSAT(out2, 16));
+    in3 = (q15_t) (__SSAT(out3, 16));
+    in4 = (q15_t) (__SSAT(out4, 16));
+
+    /* store the result to destination */
+    *__SIMD32(pDst)++ = __PKHBT(in2, in1, 16);
+    *__SIMD32(pDst)++ = __PKHBT(in4, in3, 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 16));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) (__SSAT(((q31_t) * pSrc++ * scaleFract) >> kShift, 16));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of scale group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_q31.c

@@ -0,0 +1,221 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_q31.c    
+*    
+* Description:	Multiplies a Q31 vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**       
+ * @ingroup groupMath       
+ */
+
+/**       
+ * @addtogroup scale       
+ * @{       
+ */
+
+/**       
+ * @brief Multiplies a Q31 vector by a scalar.       
+ * @param[in]       *pSrc points to the input vector       
+ * @param[in]       scaleFract fractional portion of the scale value       
+ * @param[in]       shift number of bits to shift the result by       
+ * @param[out]      *pDst points to the output vector       
+ * @param[in]       blockSize number of samples in the vector       
+ * @return none.       
+ *       
+ * <b>Scaling and Overflow Behavior:</b>       
+ * \par       
+ * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.       
+ * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.       
+ */
+
+void arm_scale_q31(
+  q31_t * pSrc,
+  q31_t scaleFract,
+  int8_t shift,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  int8_t kShift = shift + 1;                     /* Shift to apply after scaling */
+  int8_t sign = (kShift & 0x80);
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in, out;
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q31_t in1, in2, in3, in4;                      /* temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* temporary output variabels */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.       
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* read four inputs from source */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* multiply input with scaler value */
+      in1 = ((q63_t) in1 * scaleFract) >> 32;
+      in2 = ((q63_t) in2 * scaleFract) >> 32;
+      in3 = ((q63_t) in3 * scaleFract) >> 32;
+      in4 = ((q63_t) in4 * scaleFract) >> 32;
+
+      /* apply shifting */
+      out1 = in1 << kShift;
+      out2 = in2 << kShift;
+
+      /* saturate the results. */
+      if(in1 != (out1 >> kShift))
+        out1 = 0x7FFFFFFF ^ (in1 >> 31);
+
+      if(in2 != (out2 >> kShift))
+        out2 = 0x7FFFFFFF ^ (in2 >> 31);
+
+      out3 = in3 << kShift;
+      out4 = in4 << kShift;
+
+      *pDst = out1;
+      *(pDst + 1) = out2;
+
+      if(in3 != (out3 >> kShift))
+        out3 = 0x7FFFFFFF ^ (in3 >> 31);
+
+      if(in4 != (out4 >> kShift))
+        out4 = 0x7FFFFFFF ^ (in4 >> 31);
+
+      /* Store result destination */
+      *(pDst + 2) = out3;
+      *(pDst + 3) = out4;
+
+      /* Update pointers to process next sampels */
+      pSrc += 4u;
+      pDst += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+  }
+  else
+  {
+    kShift = -kShift;
+
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.       
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* read four inputs from source */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* multiply input with scaler value */
+      in1 = ((q63_t) in1 * scaleFract) >> 32;
+      in2 = ((q63_t) in2 * scaleFract) >> 32;
+      in3 = ((q63_t) in3 * scaleFract) >> 32;
+      in4 = ((q63_t) in4 * scaleFract) >> 32;
+
+      /* apply shifting */
+      out1 = in1 >> kShift;
+      out2 = in2 >> kShift;
+
+      out3 = in3 >> kShift;
+      out4 = in4 >> kShift;
+
+      /* Store result destination */
+      *pDst = out1;
+      *(pDst + 1) = out2;
+
+      *(pDst + 2) = out3;
+      *(pDst + 3) = out4;
+
+      /* Update pointers to process next sampels */
+      pSrc += 4u;
+      pDst += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.       
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    in = *pSrc++;
+    in = ((q63_t) in * scaleFract) >> 32;
+
+    if(sign == 0)
+    {
+      out = in << kShift;
+      if(in != (out >> kShift))
+        out = 0x7FFFFFFF ^ (in >> 31);
+    }
+    else
+    {
+      out = in >> kShift;
+    }
+
+    *pDst++ = out;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**       
+ * @} end of scale group       
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_q7.c

@@ -0,0 +1,144 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_q7.c    
+*    
+* Description:	Multiplies a Q7 vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup scale    
+ * @{    
+ */
+
+/**    
+ * @brief Multiplies a Q7 vector by a scalar.    
+ * @param[in]       *pSrc points to the input vector    
+ * @param[in]       scaleFract fractional portion of the scale value    
+ * @param[in]       shift number of bits to shift the result by    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.7 format.    
+ * These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format.    
+ */
+
+void arm_scale_q7(
+  q7_t * pSrc,
+  q7_t scaleFract,
+  int8_t shift,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  int8_t kShift = 7 - shift;                     /* shift to apply after scaling */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q7_t in1, in2, in3, in4, out1, out2, out3, out4;      /* Temporary variables to store input & output */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* Reading 4 inputs from memory */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    /* C = A * scale */
+    /* Scale the inputs and then store the results in the temporary variables. */
+    out1 = (q7_t) (__SSAT(((in1) * scaleFract) >> kShift, 8));
+    out2 = (q7_t) (__SSAT(((in2) * scaleFract) >> kShift, 8));
+    out3 = (q7_t) (__SSAT(((in3) * scaleFract) >> kShift, 8));
+    out4 = (q7_t) (__SSAT(((in4) * scaleFract) >> kShift, 8));
+
+    /* Packing the individual outputs into 32bit and storing in    
+     * destination buffer in single write */
+    *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 8));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) (__SSAT((((q15_t) * pSrc++ * scaleFract) >> kShift), 8));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of scale group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q15.c

@@ -0,0 +1,243 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_shift_q15.c    
+*    
+* Description:	Shifts the elements of a Q15 vector by a specified number of bits.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup shift    
+ * @{    
+ */
+
+/**    
+ * @brief  Shifts the elements of a Q15 vector a specified number of bits.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_shift_q15(
+  q15_t * pSrc,
+  int8_t shiftBits,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  uint8_t sign;                                  /* Sign of shiftBits */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q15_t in1, in2;                                /* Temporary variables */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* Read 2 inputs */
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+      /* C = A << shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
+                                  __SSAT((in2 << shiftBits), 16), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
+                                  __SSAT((in1 << shiftBits), 16), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
+                                  __SSAT((in2 << shiftBits), 16), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
+                                  __SSAT((in1 << shiftBits), 16), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift and then store the results in the destination buffer. */
+      *pDst++ = __SSAT((*pSrc++ << shiftBits), 16);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* Read 2 inputs */
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+
+      /* C = A >> shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
+                                  (in2 >> -shiftBits), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
+                                  (in1 >> -shiftBits), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
+                                  (in2 >> -shiftBits), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
+                                  (in1 >> -shiftBits), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift and then store the results in the destination buffer. */
+      *pDst++ = __SSAT(((q31_t) * pSrc++ << shiftBits), 16);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of shift group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q31.c

@@ -0,0 +1,195 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_shift_q31.c    
+*    
+* Description:	Shifts the elements of a Q31 vector by a specified number of bits.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+/**        
+ * @defgroup shift Vector Shift        
+ *        
+ * Shifts the elements of a fixed-point vector by a specified number of bits.        
+ * There are separate functions for Q7, Q15, and Q31 data types.        
+ * The underlying algorithm used is:        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrc[n] << shift,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * If <code>shift</code> is positive then the elements of the vector are shifted to the left.        
+ * If <code>shift</code> is negative then the elements of the vector are shifted to the right.        
+ */
+
+/**        
+ * @addtogroup shift        
+ * @{        
+ */
+
+/**        
+ * @brief  Shifts the elements of a Q31 vector a specified number of bits.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ *        
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.        
+ */
+
+void arm_shift_q31(
+  q31_t * pSrc,
+  int8_t shiftBits,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  uint8_t sign = (shiftBits & 0x80);             /* Sign of shiftBits */
+
+#ifndef ARM_MATH_CM0
+
+  q31_t in1, in2, in3, in4;                      /* Temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* Temporary output variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A  << shiftBits */
+      /* Shift the input and then store the results in the destination buffer. */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      out1 = in1 << shiftBits;
+      in3 = *(pSrc + 2);
+      out2 = in2 << shiftBits;
+      in4 = *(pSrc + 3);
+      if(in1 != (out1 >> shiftBits))
+        out1 = 0x7FFFFFFF ^ (in1 >> 31);
+
+      if(in2 != (out2 >> shiftBits))
+        out2 = 0x7FFFFFFF ^ (in2 >> 31);
+
+      *pDst = out1;
+      out3 = in3 << shiftBits;
+      *(pDst + 1) = out2;
+      out4 = in4 << shiftBits;
+
+      if(in3 != (out3 >> shiftBits))
+        out3 = 0x7FFFFFFF ^ (in3 >> 31);
+
+      if(in4 != (out4 >> shiftBits))
+        out4 = 0x7FFFFFFF ^ (in4 >> 31);
+
+      *(pDst + 2) = out3;
+      *(pDst + 3) = out4;
+
+      /* Update destination pointer to process next sampels */
+      pSrc += 4u;
+      pDst += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A >>  shiftBits */
+      /* Shift the input and then store the results in the destination buffer. */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      *pDst = (in1 >> -shiftBits);
+      *(pDst + 1) = (in2 >> -shiftBits);
+      *(pDst + 2) = (in3 >> -shiftBits);
+      *(pDst + 3) = (in4 >> -shiftBits);
+
+
+      pSrc += 4u;
+      pDst += 4u;
+
+      blkCnt--;
+    }
+
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A (>> or <<) shiftBits */
+    /* Shift the input and then store the result in the destination buffer. */
+    *pDst++ = (sign == 0u) ? clip_q63_to_q31((q63_t) * pSrc++ << shiftBits) :
+      (*pSrc++ >> -shiftBits);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+
+}
+
+/**        
+ * @} end of shift group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c

@@ -0,0 +1,215 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_shift_q7.c    
+*    
+* Description:	Processing function for the Q7 Shifting    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @addtogroup shift        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Shifts the elements of a Q7 vector a specified number of bits.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ *    
+ * \par Conditions for optimum performance    
+ *  Input and output buffers should be aligned by 32-bit    
+ *    
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * Results outside of the allowable Q7 range [0x8 0x7F] will be saturated.        
+ */
+
+void arm_shift_q7(
+  q7_t * pSrc,
+  int8_t shiftBits,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  uint8_t sign;                                  /* Sign of shiftBits */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q7_t in1;                                      /* Input value1 */
+  q7_t in2;                                      /* Input value2 */
+  q7_t in3;                                      /* Input value3 */
+  q7_t in4;                                      /* Input value4 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Read 4 inputs */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
+      *__SIMD32(pDst)++ = __PACKq7(__SSAT((in1 << shiftBits), 8),
+                                   __SSAT((in2 << shiftBits), 8),
+                                   __SSAT((in3 << shiftBits), 8),
+                                   __SSAT((in4 << shiftBits), 8));
+      /* Update source pointer to process next sampels */
+      pSrc += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      *pDst++ = (q7_t) __SSAT((*pSrc++ << shiftBits), 8);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    shiftBits = -shiftBits;
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Read 4 inputs */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
+      *__SIMD32(pDst)++ = __PACKq7((in1 >> shiftBits), (in2 >> shiftBits),
+                                   (in3 >> shiftBits), (in4 >> shiftBits));
+
+
+      pSrc += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      in1 = *pSrc++;
+      *pDst++ = (in1 >> shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      *pDst++ = (q7_t) __SSAT(((q15_t) * pSrc++ << shiftBits), 8);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+}
+
+/**        
+ * @} end of shift group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_f32.c

@@ -0,0 +1,145 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_f32.c    
+*    
+* Description:	Floating-point vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicSub Vector Subtraction        
+ *        
+ * Element-by-element subtraction of two vectors.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrcA[n] - pSrcB[n],   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup BasicSub        
+ * @{        
+ */
+
+
+/**        
+ * @brief Floating-point vector subtraction.        
+ * @param[in]       *pSrcA points to the first input vector        
+ * @param[in]       *pSrcB points to the second input vector        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_sub_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* temporary variables */
+  float32_t inB1, inB2, inB3, inB4;              /* temporary variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer. */
+    /* Read 4 input samples from sourceA and sourceB */
+    inA1 = *pSrcA;
+    inB1 = *pSrcB;
+    inA2 = *(pSrcA + 1);
+    inB2 = *(pSrcB + 1);
+    inA3 = *(pSrcA + 2);
+    inB3 = *(pSrcB + 2);
+    inA4 = *(pSrcA + 3);
+    inB4 = *(pSrcB + 3);
+
+    /* dst = srcA - srcB */
+    /* subtract and store the result */
+    *pDst = inA1 - inB1;
+    *(pDst + 1) = inA2 - inB2;
+    *(pDst + 2) = inA3 - inB3;
+    *(pDst + 3) = inA4 - inB4;
+
+
+    /* Update pointers to process next sampels */
+    pSrcA += 4u;
+    pSrcB += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer. */
+    *pDst++ = (*pSrcA++) - (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicSub group        
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_q15.c

@@ -0,0 +1,135 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_q15.c    
+*    
+* Description:	Q15 vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicSub    
+ * @{    
+ */
+
+/**    
+ * @brief Q15 vector subtraction.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_sub_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2;
+  q31_t inB1, inB2;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer two samples at a time. */
+    inA1 = *__SIMD32(pSrcA)++;
+    inA2 = *__SIMD32(pSrcA)++;
+    inB1 = *__SIMD32(pSrcB)++;
+    inB2 = *__SIMD32(pSrcB)++;
+
+    *__SIMD32(pDst)++ = __QSUB16(inA1, inB1);
+    *__SIMD32(pDst)++ = __QSUB16(inA2, inB2);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) __QSUB16(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ - *pSrcB++), 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+}
+
+/**    
+ * @} end of BasicSub group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_q31.c

@@ -0,0 +1,141 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_q31.c    
+*    
+* Description:	Q31 vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicSub    
+ * @{    
+ */
+
+/**    
+ * @brief Q31 vector subtraction.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_sub_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;
+  q31_t inB1, inB2, inB3, inB4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    *pDst++ = __QSUB(inA1, inB1);
+    *pDst++ = __QSUB(inA2, inB2);
+    *pDst++ = __QSUB(inA3, inB3);
+    *pDst++ = __QSUB(inA4, inB4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = __QSUB(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrcA++ - *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of BasicSub group    
+ */

libs/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_q7.c

@@ -0,0 +1,126 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_q7.c    
+*    
+* Description:	Q7 vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicSub    
+ * @{    
+ */
+
+/**    
+ * @brief Q7 vector subtraction.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
+ */
+
+void arm_sub_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer 4 samples at a time. */
+    *__SIMD32(pDst)++ = __QSUB8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = __SSAT(*pSrcA++ - *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ - *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+
+}
+
+/**    
+ * @} end of BasicSub group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_conj_f32.c

@@ -0,0 +1,174 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_conj_f32.c    
+*    
+* Description:	Floating-point complex conjugate.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup cmplx_conj Complex Conjugate        
+ *        
+ * Conjugates the elements of a complex data vector.        
+ *       
+ * The <code>pSrc</code> points to the source data and        
+ * <code>pDst</code> points to the where the result should be written.        
+ * <code>numSamples</code> specifies the number of complex samples        
+ * and the data in each array is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * Each array has a total of <code>2*numSamples</code> values.        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pDst[(2*n)+0)] = pSrc[(2*n)+0];     // real part        
+ *     pDst[(2*n)+1)] = -pSrc[(2*n)+1];    // imag part        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup cmplx_conj        
+ * @{        
+ */
+
+/**        
+ * @brief  Floating-point complex conjugate.        
+ * @param  *pSrc points to the input vector        
+ * @param  *pDst points to the output vector        
+ * @param  numSamples number of complex samples in each vector        
+ * @return none.        
+ */
+
+void arm_cmplx_conj_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inR1, inR2, inR3, inR4;
+  float32_t inI1, inI2, inI3, inI4;
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    /* read real input samples */
+    inR1 = pSrc[0];
+    /* store real samples to destination */
+    pDst[0] = inR1;
+    inR2 = pSrc[2];
+    pDst[2] = inR2;
+    inR3 = pSrc[4];
+    pDst[4] = inR3;
+    inR4 = pSrc[6];
+    pDst[6] = inR4;
+
+    /* read imaginary input samples */
+    inI1 = pSrc[1];
+    inI2 = pSrc[3];
+
+    /* conjugate input */
+    inI1 = -inI1;
+
+    /* read imaginary input samples */
+    inI3 = pSrc[5];
+
+    /* conjugate input */
+    inI2 = -inI2;
+
+    /* read imaginary input samples */
+    inI4 = pSrc[7];
+
+    /* conjugate input */
+    inI3 = -inI3;
+
+    /* store imaginary samples to destination */
+    pDst[1] = inI1;
+    pDst[3] = inI2;
+
+    /* conjugate input */
+    inI4 = -inI4;
+
+    /* store imaginary samples to destination */
+    pDst[5] = inI3;
+
+    /* increment source pointer by 8 to process next sampels */
+    pSrc += 8u;
+
+    /* store imaginary sample to destination */
+    pDst[7] = inI4;
+
+    /* increment destination pointer by 8 to store next samples */
+    pDst += 8u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* realOut + j (imagOut) = realIn + j (-1) imagIn */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    *pDst++ = *pSrc++;
+    *pDst++ = -*pSrc++;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_conj group        
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_conj_q15.c

@@ -0,0 +1,153 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_conj_q15.c    
+*    
+* Description:	Q15 complex conjugate.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_conj    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex conjugate.    
+ * @param  *pSrc points to the input vector    
+ * @param  *pDst points to the output vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.    
+ */
+
+void arm_cmplx_conj_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in1, in2, in3, in4;
+  q31_t zero = 0;
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    in1 = *__SIMD32(pSrc)++;
+    in2 = *__SIMD32(pSrc)++;
+    in3 = *__SIMD32(pSrc)++;
+    in4 = *__SIMD32(pSrc)++;
+
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    in1 = __QASX(zero, in1);
+    in2 = __QASX(zero, in2);
+    in3 = __QASX(zero, in3);
+    in4 = __QASX(zero, in4);
+
+#else
+
+    in1 = __QSAX(zero, in1);
+    in2 = __QSAX(zero, in2);
+    in3 = __QSAX(zero, in3);
+    in4 = __QSAX(zero, in4);
+
+#endif //       #ifndef ARM_MATH_BIG_ENDIAN
+
+    in1 = ((uint32_t) in1 >> 16) | ((uint32_t) in1 << 16);
+    in2 = ((uint32_t) in2 >> 16) | ((uint32_t) in2 << 16);
+    in3 = ((uint32_t) in3 >> 16) | ((uint32_t) in3 << 16);
+    in4 = ((uint32_t) in4 >> 16) | ((uint32_t) in4 << 16);
+
+    *__SIMD32(pDst)++ = in1;
+    *__SIMD32(pDst)++ = in2;
+    *__SIMD32(pDst)++ = in3;
+    *__SIMD32(pDst)++ = in4;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    *pDst++ = *pSrc++;
+    *pDst++ = __SSAT(-*pSrc++, 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  q15_t in;
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* realOut + j (imagOut) = realIn+ j (-1) imagIn */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    *pDst++ = *pSrc++;
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? 0x7fff : -in;
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of cmplx_conj group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_conj_q31.c

@@ -0,0 +1,172 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_conj_q31.c    
+*    
+* Description:	Q31 complex conjugate.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @addtogroup cmplx_conj        
+ * @{        
+ */
+
+/**        
+ * @brief  Q31 complex conjugate.        
+ * @param  *pSrc points to the input vector        
+ * @param  *pDst points to the output vector        
+ * @param  numSamples number of complex samples in each vector        
+ * @return none.        
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.        
+ */
+
+void arm_cmplx_conj_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in;                                      /* Input value */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inR1, inR2, inR3, inR4;                  /* Temporary real variables */
+  q31_t inI1, inI2, inI3, inI4;                  /* Temporary imaginary variables */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    /* Saturated to 0x7fffffff if the input is -1(0x80000000) */
+    /* read real input sample */
+    inR1 = pSrc[0];
+    /* store real input sample */
+    pDst[0] = inR1;
+
+    /* read imaginary input sample */
+    inI1 = pSrc[1];
+
+    /* read real input sample */
+    inR2 = pSrc[2];
+    /* store real input sample */
+    pDst[2] = inR2;
+
+    /* read imaginary input sample */
+    inI2 = pSrc[3];
+
+    /* negate imaginary input sample */
+    inI1 = __QSUB(0, inI1);
+
+    /* read real input sample */
+    inR3 = pSrc[4];
+    /* store real input sample */
+    pDst[4] = inR3;
+
+    /* read imaginary input sample */
+    inI3 = pSrc[5];
+
+    /* negate imaginary input sample */
+    inI2 = __QSUB(0, inI2);
+
+    /* read real input sample */
+    inR4 = pSrc[6];
+    /* store real input sample */
+    pDst[6] = inR4;
+
+    /* negate imaginary input sample */
+    inI3 = __QSUB(0, inI3);
+
+    /* store imaginary input sample */
+    inI4 = pSrc[7];
+
+    /* store imaginary input samples */
+    pDst[1] = inI1;
+
+    /* negate imaginary input sample */
+    inI4 = __QSUB(0, inI4);
+
+    /* store imaginary input samples */
+    pDst[3] = inI2;
+
+    /* increment source pointer by 8 to proecess next samples */
+    pSrc += 8u;
+
+    /* store imaginary input samples */
+    pDst[5] = inI3;
+    pDst[7] = inI4;
+
+    /* increment destination pointer by 8 to process next samples */
+    pDst += 8u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    /* Saturated to 0x7fffffff if the input is -1(0x80000000) */
+    *pDst++ = *pSrc++;
+    in = *pSrc++;
+    *pDst++ = (in == 0x80000000) ? 0x7fffffff : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_conj group        
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_dot_prod_f32.c

@@ -0,0 +1,160 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_dot_prod_f32.c    
+*    
+* Description:	Floating-point complex dot product    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @defgroup cmplx_dot_prod Complex Dot Product    
+ *    
+ * Computes the dot product of two complex vectors.    
+ * The vectors are multiplied element-by-element and then summed.    
+ *   
+ * The <code>pSrcA</code> points to the first complex input vector and    
+ * <code>pSrcB</code> points to the second complex input vector.    
+ * <code>numSamples</code> specifies the number of complex samples    
+ * and the data in each array is stored in an interleaved fashion    
+ * (real, imag, real, imag, ...).    
+ * Each array has a total of <code>2*numSamples</code> values.    
+ *    
+ * The underlying algorithm is used:    
+ * <pre>    
+ * realResult=0;    
+ * imagResult=0;    
+ * for(n=0; n<numSamples; n++) {    
+ *     realResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+0] - pSrcA[(2*n)+1]*pSrcB[(2*n)+1];    
+ *     imagResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+1] + pSrcA[(2*n)+1]*pSrcB[(2*n)+0];    
+ * }    
+ * </pre>    
+ *    
+ * There are separate functions for floating-point, Q15, and Q31 data types.    
+ */
+
+/**    
+ * @addtogroup cmplx_dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief  Floating-point complex dot product    
+ * @param  *pSrcA points to the first input vector    
+ * @param  *pSrcB points to the second input vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @param  *realResult real part of the result returned here    
+ * @param  *imagResult imaginary part of the result returned here    
+ * @return none.    
+ */
+
+void arm_cmplx_dot_prod_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  uint32_t numSamples,
+  float32_t * realResult,
+  float32_t * imagResult)
+{
+  float32_t real_sum = 0.0f, imag_sum = 0.0f;    /* Temporary result storage */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    real_sum += (*pSrcA++) * (*pSrcB++);
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    imag_sum += (*pSrcA++) * (*pSrcB++);
+
+    real_sum += (*pSrcA++) * (*pSrcB++);
+    imag_sum += (*pSrcA++) * (*pSrcB++);
+
+    real_sum += (*pSrcA++) * (*pSrcB++);
+    imag_sum += (*pSrcA++) * (*pSrcB++);
+
+    real_sum += (*pSrcA++) * (*pSrcB++);
+    imag_sum += (*pSrcA++) * (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    real_sum += (*pSrcA++) * (*pSrcB++);
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    imag_sum += (*pSrcA++) * (*pSrcB++);
+
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    real_sum += (*pSrcA++) * (*pSrcB++);
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    imag_sum += (*pSrcA++) * (*pSrcB++);
+
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  /* Store the real and imaginary results in the destination buffers */
+  *realResult = real_sum;
+  *imagResult = imag_sum;
+}
+
+/**    
+ * @} end of cmplx_dot_prod group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_dot_prod_q15.c

@@ -0,0 +1,144 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_dot_prod_q15.c    
+*    
+* Description:	Processing function for the Q15 Complex Dot product    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex dot product    
+ * @param  *pSrcA points to the first input vector    
+ * @param  *pSrcB points to the second input vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @param  *realResult real part of the result returned here    
+ * @param  *imagResult imaginary part of the result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function is implemented using an internal 64-bit accumulator.    
+ * The intermediate 1.15 by 1.15 multiplications are performed with full precision and yield a 2.30 result.    
+ * These are accumulated in a 64-bit accumulator with 34.30 precision.    
+ * As a final step, the accumulators are converted to 8.24 format.    
+ * The return results <code>realResult</code> and <code>imagResult</code> are in 8.24 format.    
+ */
+
+void arm_cmplx_dot_prod_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  uint32_t numSamples,
+  q31_t * realResult,
+  q31_t * imagResult)
+{
+  q63_t real_sum = 0, imag_sum = 0;              /* Temporary result storage */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+
+    real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+    imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+
+    real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+    imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+
+    real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+    imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  /* Store the real and imaginary results in 8.24 format  */
+  /* Convert real data in 34.30 to 8.24 by 6 right shifts */
+  *realResult = (q31_t) (real_sum) >> 6;
+  /* Convert imaginary data in 34.30 to 8.24 by 6 right shifts */
+  *imagResult = (q31_t) (imag_sum) >> 6;
+}
+
+/**    
+ * @} end of cmplx_dot_prod group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_dot_prod_q31.c

@@ -0,0 +1,145 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_dot_prod_q31.c    
+*    
+* Description:	Q31 complex dot product    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief  Q31 complex dot product    
+ * @param  *pSrcA points to the first input vector    
+ * @param  *pSrcB points to the second input vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @param  *realResult real part of the result returned here    
+ * @param  *imagResult imaginary part of the result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function is implemented using an internal 64-bit accumulator.    
+ * The intermediate 1.31 by 1.31 multiplications are performed with 64-bit precision and then shifted to 16.48 format.    
+ * The internal real and imaginary accumulators are in 16.48 format and provide 15 guard bits.    
+ * Additions are nonsaturating and no overflow will occur as long as <code>numSamples</code> is less than 32768.    
+ * The return results <code>realResult</code> and <code>imagResult</code> are in 16.48 format.    
+ * Input down scaling is not required.    
+ */
+
+void arm_cmplx_dot_prod_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  uint32_t numSamples,
+  q63_t * realResult,
+  q63_t * imagResult)
+{
+  q63_t real_sum = 0, imag_sum = 0;              /* Temporary result storage */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    /* Convert real data in 2.62 to 16.48 by 14 right shifts */
+    real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    /* Convert imag data in 2.62 to 16.48 by 14 right shifts */
+    imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+
+    real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+    imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+
+    real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+    imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+
+    real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+    imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples  is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
+    real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+    /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
+    imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* outReal = realA[0]* realB[0] + realA[2]* realB[2] + realA[4]* realB[4] + .....+ realA[numSamples-2]* realB[numSamples-2] */
+    real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+    /* outImag = imagA[1]* imagB[1] + imagA[3]* imagB[3] + imagA[5]* imagB[5] + .....+ imagA[numSamples-1]* imagB[numSamples-1] */
+    imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14;
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  /* Store the real and imaginary results in 16.48 format  */
+  *realResult = real_sum;
+  *imagResult = imag_sum;
+}
+
+/**    
+ * @} end of cmplx_dot_prod group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_f32.c

@@ -0,0 +1,157 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_f32.c    
+*    
+* Description:	Floating-point complex magnitude.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @defgroup cmplx_mag Complex Magnitude    
+ *    
+ * Computes the magnitude of the elements of a complex data vector.    
+ *   
+ * The <code>pSrc</code> points to the source data and    
+ * <code>pDst</code> points to the where the result should be written.    
+ * <code>numSamples</code> specifies the number of complex samples    
+ * in the input array and the data is stored in an interleaved fashion    
+ * (real, imag, real, imag, ...).    
+ * The input array has a total of <code>2*numSamples</code> values;    
+ * the output array has a total of <code>numSamples</code> values.    
+ * The underlying algorithm is used:    
+ *    
+ * <pre>    
+ * for(n=0; n<numSamples; n++) {    
+ *     pDst[n] = sqrt(pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2);    
+ * }    
+ * </pre>    
+ *    
+ * There are separate functions for floating-point, Q15, and Q31 data types.    
+ */
+
+/**    
+ * @addtogroup cmplx_mag    
+ * @{    
+ */
+/**    
+ * @brief Floating-point complex magnitude.    
+ * @param[in]       *pSrc points to complex input buffer    
+ * @param[out]      *pDst points to real output buffer    
+ * @param[in]       numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ */
+
+
+void arm_cmplx_mag_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  float32_t realIn, imagIn;                      /* Temporary variables to hold input values */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    /* store the result in the destination buffer. */
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    /* store the result in the destination buffer. */
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* out = sqrt((real * real) + (imag * imag)) */
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    /* store the result in the destination buffer. */
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of cmplx_mag group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_q15.c

@@ -0,0 +1,145 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_q15.c    
+*    
+* Description:	Q15 complex magnitude.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_mag    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q15 complex magnitude    
+ * @param  *pSrc points to the complex input vector    
+ * @param  *pDst points to the real output vector    
+ * @param  numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.15 by 1.15 multiplications and finally output is converted into 2.14 format.    
+ */
+
+void arm_cmplx_mag_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t acc0, acc1;                              /* Accumulators */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in1, in2, in3, in4;
+  q31_t acc2, acc3;
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    in2 = *__SIMD32(pSrc)++;
+    in3 = *__SIMD32(pSrc)++;
+    in4 = *__SIMD32(pSrc)++;
+
+    acc0 = __SMUAD(in1, in1);
+    acc1 = __SMUAD(in2, in2);
+    acc2 = __SMUAD(in3, in3);
+    acc3 = __SMUAD(in4, in4);
+
+    /* store the result in 2.14 format in the destination buffer. */
+    arm_sqrt_q15((q15_t) ((acc0) >> 17), pDst++);
+    arm_sqrt_q15((q15_t) ((acc1) >> 17), pDst++);
+    arm_sqrt_q15((q15_t) ((acc2) >> 17), pDst++);
+    arm_sqrt_q15((q15_t) ((acc3) >> 17), pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    acc0 = __SMUAD(in1, in1);
+
+    /* store the result in 2.14 format in the destination buffer. */
+    arm_sqrt_q15((q15_t) (acc0 >> 17), pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  q15_t real, imag;                              /* Temporary variables to hold input values */
+
+  while(numSamples > 0u)
+  {
+    /* out = sqrt(real * real + imag * imag) */
+    real = *pSrc++;
+    imag = *pSrc++;
+
+    acc0 = (real * real);
+    acc1 = (imag * imag);
+
+    /* store the result in 2.14 format in the destination buffer. */
+    arm_sqrt_q15((q15_t) (((q63_t) acc0 + acc1) >> 17), pDst++);
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of cmplx_mag group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_q31.c

@@ -0,0 +1,177 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_q31.c    
+*    
+* Description:	Q31 complex magnitude    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @addtogroup cmplx_mag        
+ * @{        
+ */
+
+/**        
+ * @brief  Q31 complex magnitude        
+ * @param  *pSrc points to the complex input vector        
+ * @param  *pDst points to the real output vector        
+ * @param  numSamples number of complex samples in the input vector        
+ * @return none.        
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function implements 1.31 by 1.31 multiplications and finally output is converted into 2.30 format.        
+ * Input down scaling is not required.        
+ */
+
+void arm_cmplx_mag_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t real, imag;                              /* Temporary variables to hold input values */
+  q31_t acc0, acc1;                              /* Accumulators */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t real1, real2, imag1, imag2;              /* Temporary variables to hold input values */
+  q31_t out1, out2, out3, out4;                  /* Accumulators */
+  q63_t mul1, mul2, mul3, mul4;                  /* Temporary variables */
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read complex input from source buffer */
+    real1 = pSrc[0];
+    imag1 = pSrc[1];
+    real2 = pSrc[2];
+    imag2 = pSrc[3];
+
+    /* calculate power of input values */
+    mul1 = (q63_t) real1 *real1;
+    mul2 = (q63_t) imag1 *imag1;
+    mul3 = (q63_t) real2 *real2;
+    mul4 = (q63_t) imag2 *imag2;
+
+    /* get the result to 3.29 format */
+    out1 = (q31_t) (mul1 >> 33);
+    out2 = (q31_t) (mul2 >> 33);
+    out3 = (q31_t) (mul3 >> 33);
+    out4 = (q31_t) (mul4 >> 33);
+
+    /* add real and imaginary accumulators */
+    out1 = out1 + out2;
+    out3 = out3 + out4;
+
+    /* read complex input from source buffer */
+    real1 = pSrc[4];
+    imag1 = pSrc[5];
+    real2 = pSrc[6];
+    imag2 = pSrc[7];
+
+    /* calculate square root */
+    arm_sqrt_q31(out1, &pDst[0]);
+
+    /* calculate power of input values */
+    mul1 = (q63_t) real1 *real1;
+
+    /* calculate square root */
+    arm_sqrt_q31(out3, &pDst[1]);
+
+    /* calculate power of input values */
+    mul2 = (q63_t) imag1 *imag1;
+    mul3 = (q63_t) real2 *real2;
+    mul4 = (q63_t) imag2 *imag2;
+
+    /* get the result to 3.29 format */
+    out1 = (q31_t) (mul1 >> 33);
+    out2 = (q31_t) (mul2 >> 33);
+    out3 = (q31_t) (mul3 >> 33);
+    out4 = (q31_t) (mul4 >> 33);
+
+    /* add real and imaginary accumulators */
+    out1 = out1 + out2;
+    out3 = out3 + out4;
+
+    /* calculate square root */
+    arm_sqrt_q31(out1, &pDst[2]);
+
+    /* increment destination by 8 to process next samples */
+    pSrc += 8u;
+
+    /* calculate square root */
+    arm_sqrt_q31(out3, &pDst[3]);
+
+    /* increment destination by 4 to process next samples */
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 2.30 format in the destination buffer. */
+    arm_sqrt_q31(acc0 + acc1, pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_mag group        
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_f32.c

@@ -0,0 +1,207 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_squared_f32.c    
+*    
+* Description:	Floating-point complex magnitude squared.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup cmplx_mag_squared Complex Magnitude Squared        
+ *        
+ * Computes the magnitude squared of the elements of a complex data vector.        
+ *       
+ * The <code>pSrc</code> points to the source data and        
+ * <code>pDst</code> points to the where the result should be written.        
+ * <code>numSamples</code> specifies the number of complex samples        
+ * in the input array and the data is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * The input array has a total of <code>2*numSamples</code> values;        
+ * the output array has a total of <code>numSamples</code> values.        
+ *        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pDst[n] = pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2;        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup cmplx_mag_squared        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Floating-point complex magnitude squared        
+ * @param[in]  *pSrc points to the complex input vector        
+ * @param[out]  *pDst points to the real output vector        
+ * @param[in]  numSamples number of complex samples in the input vector        
+ * @return none.        
+ */
+
+void arm_cmplx_mag_squared_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  float32_t real, imag;                          /* Temporary variables to store real and imaginary values */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+  float32_t real1, real2, real3, real4;          /* Temporary variables to hold real values */
+  float32_t imag1, imag2, imag3, imag4;          /* Temporary variables to hold imaginary values */
+  float32_t mul1, mul2, mul3, mul4;              /* Temporary variables */
+  float32_t mul5, mul6, mul7, mul8;              /* Temporary variables */
+  float32_t out1, out2, out3, out4;              /* Temporary variables to hold output values */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    /* read real input sample from source buffer */
+    real1 = pSrc[0];
+    /* read imaginary input sample from source buffer */
+    imag1 = pSrc[1];
+
+    /* calculate power of real value */
+    mul1 = real1 * real1;
+
+    /* read real input sample from source buffer */
+    real2 = pSrc[2];
+
+    /* calculate power of imaginary value */
+    mul2 = imag1 * imag1;
+
+    /* read imaginary input sample from source buffer */
+    imag2 = pSrc[3];
+
+    /* calculate power of real value */
+    mul3 = real2 * real2;
+
+    /* read real input sample from source buffer */
+    real3 = pSrc[4];
+
+    /* calculate power of imaginary value */
+    mul4 = imag2 * imag2;
+
+    /* read imaginary input sample from source buffer */
+    imag3 = pSrc[5];
+
+    /* calculate power of real value */
+    mul5 = real3 * real3;
+    /* calculate power of imaginary value */
+    mul6 = imag3 * imag3;
+
+    /* read real input sample from source buffer */
+    real4 = pSrc[6];
+
+    /* accumulate real and imaginary powers */
+    out1 = mul1 + mul2;
+
+    /* read imaginary input sample from source buffer */
+    imag4 = pSrc[7];
+
+    /* accumulate real and imaginary powers */
+    out2 = mul3 + mul4;
+
+    /* calculate power of real value */
+    mul7 = real4 * real4;
+    /* calculate power of imaginary value */
+    mul8 = imag4 * imag4;
+
+    /* store output to destination */
+    pDst[0] = out1;
+
+    /* accumulate real and imaginary powers */
+    out3 = mul5 + mul6;
+
+    /* store output to destination */
+    pDst[1] = out2;
+
+    /* accumulate real and imaginary powers */
+    out4 = mul7 + mul8;
+
+    /* store output to destination */
+    pDst[2] = out3;
+
+    /* increment destination pointer by 8 to process next samples */
+    pSrc += 8u;
+
+    /* store output to destination */
+    pDst[3] = out4;
+
+    /* increment destination pointer by 4 to process next samples */
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+
+    /* out = (real * real) + (imag * imag) */
+    /* store the result in the destination buffer. */
+    *pDst++ = (real * real) + (imag * imag);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_mag_squared group        
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_q15.c

@@ -0,0 +1,140 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_squared_q15.c    
+*    
+* Description:	Q15 complex magnitude squared.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_mag_squared    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex magnitude squared    
+ * @param  *pSrc points to the complex input vector    
+ * @param  *pDst points to the real output vector    
+ * @param  numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.    
+ */
+
+void arm_cmplx_mag_squared_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t acc0, acc1;                              /* Accumulators */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in1, in2, in3, in4;
+  q31_t acc2, acc3;
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    in2 = *__SIMD32(pSrc)++;
+    in3 = *__SIMD32(pSrc)++;
+    in4 = *__SIMD32(pSrc)++;
+
+    acc0 = __SMUAD(in1, in1);
+    acc1 = __SMUAD(in2, in2);
+    acc2 = __SMUAD(in3, in3);
+    acc3 = __SMUAD(in4, in4);
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ = (q15_t) (acc0 >> 17);
+    *pDst++ = (q15_t) (acc1 >> 17);
+    *pDst++ = (q15_t) (acc2 >> 17);
+    *pDst++ = (q15_t) (acc3 >> 17);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    acc0 = __SMUAD(in1, in1);
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ = (q15_t) (acc0 >> 17);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  q15_t real, imag;                              /* Temporary variables to store real and imaginary values */
+
+  while(numSamples > 0u)
+  {
+    /* out = ((real * real) + (imag * imag)) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (real * real);
+    acc1 = (imag * imag);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of cmplx_mag_squared group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_q31.c

@@ -0,0 +1,153 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_squared_q31.c    
+*    
+* Description:	Q31 complex magnitude squared.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_mag_squared    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q31 complex magnitude squared    
+ * @param  *pSrc points to the complex input vector    
+ * @param  *pDst points to the real output vector    
+ * @param  numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.    
+ * Input down scaling is not required.    
+ */
+
+void arm_cmplx_mag_squared_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t real, imag;                              /* Temporary variables to store real and imaginary values */
+  q31_t acc0, acc1;                              /* Accumulators */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* out = ((real * real) + (imag * imag)) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of cmplx_mag_squared group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_cmplx_f32.c

@@ -0,0 +1,199 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_cmplx_f32.c    
+*    
+* Description:	Floating-point complex-by-complex multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup CmplxByCmplxMult Complex-by-Complex Multiplication        
+ *        
+ * Multiplies a complex vector by another complex vector and generates a complex result.        
+ * The data in the complex arrays is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * The parameter <code>numSamples</code> represents the number of complex        
+ * samples processed.  The complex arrays have a total of <code>2*numSamples</code>        
+ * real values.        
+ *        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1];        
+ *     pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0];        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup CmplxByCmplxMult        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Floating-point complex-by-complex multiplication        
+ * @param[in]  *pSrcA points to the first input vector        
+ * @param[in]  *pSrcB points to the second input vector        
+ * @param[out]  *pDst  points to the output vector        
+ * @param[in]  numSamples number of complex samples in each vector        
+ * @return none.        
+ */
+
+void arm_cmplx_mult_cmplx_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  float32_t a1, b1, c1, d1;                      /* Temporary variables to store real and imaginary values */
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t a2, b2, c2, d2;                      /* Temporary variables to store real and imaginary values */
+  float32_t acc1, acc2, acc3, acc4;
+
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a1 = *pSrcA;                /* A[2 * i] */
+    c1 = *pSrcB;                /* B[2 * i] */
+
+    b1 = *(pSrcA + 1);          /* A[2 * i + 1] */
+    acc1 = a1 * c1;             /* acc1 = A[2 * i] * B[2 * i] */
+
+    a2 = *(pSrcA + 2);          /* A[2 * i + 2] */
+    acc2 = (b1 * c1);           /* acc2 = A[2 * i + 1] * B[2 * i] */
+
+    d1 = *(pSrcB + 1);          /* B[2 * i + 1] */
+    c2 = *(pSrcB + 2);          /* B[2 * i + 2] */
+    acc1 -= b1 * d1;            /* acc1 =      A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
+
+    d2 = *(pSrcB + 3);          /* B[2 * i + 3] */
+    acc3 = a2 * c2;             /* acc3 =       A[2 * i + 2] * B[2 * i + 2] */
+
+    b2 = *(pSrcA + 3);          /* A[2 * i + 3] */
+    acc2 += (a1 * d1);          /* acc2 =      A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */
+
+    a1 = *(pSrcA + 4);          /* A[2 * i + 4] */
+    acc4 = (a2 * d2);           /* acc4 =   A[2 * i + 2] * B[2 * i + 3] */
+
+    c1 = *(pSrcB + 4);          /* B[2 * i + 4] */
+    acc3 -= (b2 * d2);          /* acc3 =       A[2 * i + 2] * B[2 * i + 2] - A[2 * i + 3] * B[2 * i + 3] */
+    *pDst = acc1;               /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
+
+    b1 = *(pSrcA + 5);          /* A[2 * i + 5] */
+    acc4 += b2 * c2;            /* acc4 =   A[2 * i + 2] * B[2 * i + 3] + A[2 * i + 3] * B[2 * i + 2] */
+
+    *(pDst + 1) = acc2;         /* C[2 * i + 1] = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1]  */
+    acc1 = (a1 * c1);
+
+    d1 = *(pSrcB + 5);
+    acc2 = (b1 * c1);
+
+    *(pDst + 2) = acc3;
+    *(pDst + 3) = acc4;
+
+    a2 = *(pSrcA + 6);
+    acc1 -= (b1 * d1);
+
+    c2 = *(pSrcB + 6);
+    acc2 += (a1 * d1);
+
+    b2 = *(pSrcA + 7);
+    acc3 = (a2 * c2);
+
+    d2 = *(pSrcB + 7);
+    acc4 = (b2 * c2);
+
+    *(pDst + 4) = acc1;
+    pSrcA += 8u;
+
+    acc3 -= (b2 * d2);
+    acc4 += (a2 * d2);
+
+    *(pDst + 5) = acc2;
+    pSrcB += 8u;
+
+    *(pDst + 6) = acc3;
+    *(pDst + 7) = acc4;
+
+    pDst += 8u;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a1 = *pSrcA++;
+    b1 = *pSrcA++;
+    c1 = *pSrcB++;
+    d1 = *pSrcB++;
+
+    /* store the result in the destination buffer. */
+    *pDst++ = (a1 * c1) - (b1 * d1);
+    *pDst++ = (a1 * d1) + (b1 * c1);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of CmplxByCmplxMult group        
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_cmplx_q15.c

@@ -0,0 +1,185 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_cmplx_q15.c    
+*    
+* Description:	Q15 complex-by-complex multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByCmplxMult    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex-by-complex multiplication    
+ * @param[in]  *pSrcA points to the first input vector    
+ * @param[in]  *pSrcB points to the second input vector    
+ * @param[out]  *pDst  points to the output vector    
+ * @param[in]  numSamples number of complex samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.    
+ */
+
+void arm_cmplx_mult_cmplx_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+  q15_t a, b, c, d;                              /* Temporary variables to store real and imaginary values */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counters */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    /* Decrement the blockSize loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of CmplxByCmplxMult group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_cmplx_q31.c

@@ -0,0 +1,318 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_cmplx_q31.c    
+*    
+* Description:	Q31 complex-by-complex multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByCmplxMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q31 complex-by-complex multiplication    
+ * @param[in]  *pSrcA points to the first input vector    
+ * @param[in]  *pSrcB points to the second input vector    
+ * @param[out]  *pDst  points to the output vector    
+ * @param[in]  numSamples number of complex samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.    
+ * Input down scaling is not required.    
+ */
+
+void arm_cmplx_mult_cmplx_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t a, b, c, d;                              /* Temporary variables to store real and imaginary values */
+  uint32_t blkCnt;                               /* loop counters */
+  q31_t mul1, mul2, mul3, mul4;
+  q31_t out1, out2;
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 1u;
+
+  /* First part of the processing with loop unrolling.  Compute 2 outputs at a time.     
+   ** a second loop below computes the remaining 1 sample. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 2, compute any remaining output samples here.     
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x2u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of CmplxByCmplxMult group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_real_f32.c

@@ -0,0 +1,217 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_real_f32.c    
+*    
+* Description:	Floating-point complex by real multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup CmplxByRealMult Complex-by-Real Multiplication        
+ *        
+ * Multiplies a complex vector by a real vector and generates a complex result.        
+ * The data in the complex arrays is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * The parameter <code>numSamples</code> represents the number of complex        
+ * samples processed.  The complex arrays have a total of <code>2*numSamples</code>        
+ * real values while the real array has a total of <code>numSamples</code>        
+ * real values.        
+ *        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pCmplxDst[(2*n)+0] = pSrcCmplx[(2*n)+0] * pSrcReal[n];        
+ *     pCmplxDst[(2*n)+1] = pSrcCmplx[(2*n)+1] * pSrcReal[n];        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup CmplxByRealMult        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Floating-point complex-by-real multiplication        
+ * @param[in]  *pSrcCmplx points to the complex input vector        
+ * @param[in]  *pSrcReal points to the real input vector        
+ * @param[out]  *pCmplxDst points to the complex output vector        
+ * @param[in]  numSamples number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_cmplx_mult_real_f32(
+  float32_t * pSrcCmplx,
+  float32_t * pSrcReal,
+  float32_t * pCmplxDst,
+  uint32_t numSamples)
+{
+  float32_t in;                                  /* Temporary variable to store input value */
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* Temporary variables to hold input data */
+  float32_t inA5, inA6, inA7, inA8;              /* Temporary variables to hold input data */
+  float32_t inB1, inB2, inB3, inB4;              /* Temporary variables to hold input data */
+  float32_t out1, out2, out3, out4;              /* Temporary variables to hold output data */
+  float32_t out5, out6, out7, out8;              /* Temporary variables to hold output data */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read input from complex input buffer */
+    inA1 = pSrcCmplx[0];
+    inA2 = pSrcCmplx[1];
+    /* read input from real input buffer */
+    inB1 = pSrcReal[0];
+
+    /* read input from complex input buffer */
+    inA3 = pSrcCmplx[2];
+
+    /* multiply complex buffer real input with real buffer input */
+    out1 = inA1 * inB1;
+
+    /* read input from complex input buffer */
+    inA4 = pSrcCmplx[3];
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out2 = inA2 * inB1;
+
+    /* read input from real input buffer */
+    inB2 = pSrcReal[1];
+    /* read input from complex input buffer */
+    inA5 = pSrcCmplx[4];
+
+    /* multiply complex buffer real input with real buffer input */
+    out3 = inA3 * inB2;
+
+    /* read input from complex input buffer */
+    inA6 = pSrcCmplx[5];
+    /* read input from real input buffer */
+    inB3 = pSrcReal[2];
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out4 = inA4 * inB2;
+
+    /* read input from complex input buffer */
+    inA7 = pSrcCmplx[6];
+
+    /* multiply complex buffer real input with real buffer input */
+    out5 = inA5 * inB3;
+
+    /* read input from complex input buffer */
+    inA8 = pSrcCmplx[7];
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out6 = inA6 * inB3;
+
+    /* read input from real input buffer */
+    inB4 = pSrcReal[3];
+
+    /* store result to destination bufer */
+    pCmplxDst[0] = out1;
+
+    /* multiply complex buffer real input with real buffer input */
+    out7 = inA7 * inB4;
+
+    /* store result to destination bufer */
+    pCmplxDst[1] = out2;
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out8 = inA8 * inB4;
+
+    /* store result to destination bufer */
+    pCmplxDst[2] = out3;
+    pCmplxDst[3] = out4;
+    pCmplxDst[4] = out5;
+
+    /* incremnet complex input buffer by 8 to process next samples */
+    pSrcCmplx += 8u;
+
+    /* store result to destination bufer */
+    pCmplxDst[5] = out6;
+
+    /* increment real input buffer by 4 to process next samples */
+    pSrcReal += 4u;
+
+    /* store result to destination bufer */
+    pCmplxDst[6] = out7;
+    pCmplxDst[7] = out8;
+
+    /* increment destination buffer by 8 to process next sampels */
+    pCmplxDst += 8u;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    in = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ = (*pSrcCmplx++) * (in);
+    *pCmplxDst++ = (*pSrcCmplx++) * (in);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of CmplxByRealMult group        
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_real_q15.c

@@ -0,0 +1,195 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_real_q15.c    
+*    
+* Description:	Q15 complex by real multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByRealMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q15 complex-by-real multiplication    
+ * @param[in]  *pSrcCmplx points to the complex input vector    
+ * @param[in]  *pSrcReal points to the real input vector    
+ * @param[out]  *pCmplxDst points to the complex output vector    
+ * @param[in]  numSamples number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_cmplx_mult_real_q15(
+  q15_t * pSrcCmplx,
+  q15_t * pSrcReal,
+  q15_t * pCmplxDst,
+  uint32_t numSamples)
+{
+  q15_t in;                                      /* Temporary variable to store input value */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counters */
+  q31_t inA1, inA2;                              /* Temporary variables to hold input data */
+  q31_t inB1;                                    /* Temporary variables to hold input data */
+  q15_t out1, out2, out3, out4;                  /* Temporary variables to hold output data */
+  q31_t mul1, mul2, mul3, mul4;                  /* Temporary variables to hold intermediate data */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read complex number both real and imaginary from complex input buffer */
+    inA1 = *__SIMD32(pSrcCmplx)++;
+    /* read two real values at a time from real input buffer */
+    inB1 = *__SIMD32(pSrcReal)++;
+    /* read complex number both real and imaginary from complex input buffer */
+    inA2 = *__SIMD32(pSrcCmplx)++;
+
+    /* multiply complex number with real numbers */
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1));
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1));
+    mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16));
+
+#else
+
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
+    mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1);
+    mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1);
+
+#endif //      #ifndef ARM_MATH_BIG_ENDIAN
+
+    /* saturate the result */
+    out1 = (q15_t) __SSAT(mul1 >> 15u, 16);
+    out2 = (q15_t) __SSAT(mul2 >> 15u, 16);
+    out3 = (q15_t) __SSAT(mul3 >> 15u, 16);
+    out4 = (q15_t) __SSAT(mul4 >> 15u, 16);
+
+    /* pack real and imaginary outputs and store them to destination */
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16);
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16);
+
+    inA1 = *__SIMD32(pSrcCmplx)++;
+    inB1 = *__SIMD32(pSrcReal)++;
+    inA2 = *__SIMD32(pSrcCmplx)++;
+
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1));
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1));
+    mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16));
+
+#else
+
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
+    mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1);
+    mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1);
+
+#endif //      #ifndef ARM_MATH_BIG_ENDIAN
+
+    out1 = (q15_t) __SSAT(mul1 >> 15u, 16);
+    out2 = (q15_t) __SSAT(mul2 >> 15u, 16);
+    out3 = (q15_t) __SSAT(mul3 >> 15u, 16);
+    out4 = (q15_t) __SSAT(mul4 >> 15u, 16);
+
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16);
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    in = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* realOut = realA * realB.            */
+    /* imagOut = imagA * realB.                */
+    in = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+
+    /* Decrement the numSamples loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of CmplxByRealMult group    
+ */

libs/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_real_q31.c

@@ -0,0 +1,215 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_real_q31.c    
+*    
+* Description:	Q31 complex by real multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByRealMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q31 complex-by-real multiplication    
+ * @param[in]  *pSrcCmplx points to the complex input vector    
+ * @param[in]  *pSrcReal points to the real input vector    
+ * @param[out]  *pCmplxDst points to the complex output vector    
+ * @param[in]  numSamples number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_cmplx_mult_real_q31(
+  q31_t * pSrcCmplx,
+  q31_t * pSrcReal,
+  q31_t * pCmplxDst,
+  uint32_t numSamples)
+{
+  q31_t inA1;                                    /* Temporary variable to store input value */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counters */
+  q31_t inA2, inA3, inA4;                        /* Temporary variables to hold input data */
+  q31_t inB1, inB2;                              /* Temporary variabels to hold input data */
+  q31_t out1, out2, out3, out4;                  /* Temporary variables to hold output data */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read real input from complex input buffer */
+    inA1 = *pSrcCmplx++;
+    inA2 = *pSrcCmplx++;
+    /* read input from real input bufer */
+    inB1 = *pSrcReal++;
+    inB2 = *pSrcReal++;
+    /* read imaginary input from complex input buffer */
+    inA3 = *pSrcCmplx++;
+    inA4 = *pSrcCmplx++;
+
+    /* multiply complex input with real input */
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB1) >> 32;
+    out3 = ((q63_t) inA3 * inB2) >> 32;
+    out4 = ((q63_t) inA4 * inB2) >> 32;
+
+    /* sature the result */
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+    out3 = __SSAT(out3, 31);
+    out4 = __SSAT(out4, 31);
+
+    /* get result in 1.31 format */
+    out1 = out1 << 1;
+    out2 = out2 << 1;
+    out3 = out3 << 1;
+    out4 = out4 << 1;
+
+    /* store the result to destination buffer */
+    *pCmplxDst++ = out1;
+    *pCmplxDst++ = out2;
+    *pCmplxDst++ = out3;
+    *pCmplxDst++ = out4;
+
+    /* read real input from complex input buffer */
+    inA1 = *pSrcCmplx++;
+    inA2 = *pSrcCmplx++;
+    /* read input from real input bufer */
+    inB1 = *pSrcReal++;
+    inB2 = *pSrcReal++;
+    /* read imaginary input from complex input buffer */
+    inA3 = *pSrcCmplx++;
+    inA4 = *pSrcCmplx++;
+
+    /* multiply complex input with real input */
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB1) >> 32;
+    out3 = ((q63_t) inA3 * inB2) >> 32;
+    out4 = ((q63_t) inA4 * inB2) >> 32;
+
+    /* sature the result */
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+    out3 = __SSAT(out3, 31);
+    out4 = __SSAT(out4, 31);
+
+    /* get result in 1.31 format */
+    out1 = out1 << 1;
+    out2 = out2 << 1;
+    out3 = out3 << 1;
+    out4 = out4 << 1;
+
+    /* store the result to destination buffer */
+    *pCmplxDst++ = out1;
+    *pCmplxDst++ = out2;
+    *pCmplxDst++ = out3;
+    *pCmplxDst++ = out4;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read real input from complex input buffer */
+    inA1 = *pSrcCmplx++;
+    inA2 = *pSrcCmplx++;
+    /* read input from real input bufer */
+    inB1 = *pSrcReal++;
+
+    /* multiply complex input with real input */
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB1) >> 32;
+
+    /* sature the result */
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+
+    /* get result in 1.31 format */
+    out1 = out1 << 1;
+    out2 = out2 << 1;
+
+    /* store the result to destination buffer */
+    *pCmplxDst++ = out1;
+    *pCmplxDst++ = out2;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* realOut = realA * realB.            */
+    /* imagReal = imagA * realB.               */
+    inA1 = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ =
+      (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
+    *pCmplxDst++ =
+      (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
+
+    /* Decrement the numSamples loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of CmplxByRealMult group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_init_f32.c

@@ -0,0 +1,79 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_init_f32.c    
+*    
+* Description:	Floating-point PID Control initialization function    
+*				   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+ * @brief  Initialization function for the floating-point PID Control.   
+ * @param[in,out] *S points to an instance of the PID structure.   
+ * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state & 1 = reset the state.   
+ * @return none.   
+ * \par Description:   
+ * \par    
+ * The <code>resetStateFlag</code> specifies whether to set state to zero or not. \n   
+ * The function computes the structure fields: <code>A0</code>, <code>A1</code> <code>A2</code>    
+ * using the proportional gain( \c Kp), integral gain( \c Ki) and derivative gain( \c Kd)    
+ * also sets the state variables to all zeros.    
+ */
+
+void arm_pid_init_f32(
+  arm_pid_instance_f32 * S,
+  int32_t resetStateFlag)
+{
+
+  /* Derived coefficient A0 */
+  S->A0 = S->Kp + S->Ki + S->Kd;
+
+  /* Derived coefficient A1 */
+  S->A1 = (-S->Kp) - ((float32_t) 2.0 * S->Kd);
+
+  /* Derived coefficient A2 */
+  S->A2 = S->Kd;
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(float32_t));
+  }
+
+}
+
+/**    
+ * @} end of PID group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_init_q15.c

@@ -0,0 +1,114 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_init_q15.c    
+*    
+* Description:	Q15 PID Control initialization function    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+ * @details    
+ * @param[in,out] *S points to an instance of the Q15 PID structure.    
+ * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.    
+ * @return none.    
+ * \par Description:   
+ * \par    
+ * The <code>resetStateFlag</code> specifies whether to set state to zero or not. \n   
+ * The function computes the structure fields: <code>A0</code>, <code>A1</code> <code>A2</code>    
+ * using the proportional gain( \c Kp), integral gain( \c Ki) and derivative gain( \c Kd)    
+ * also sets the state variables to all zeros.    
+ */
+
+void arm_pid_init_q15(
+  arm_pid_instance_q15 * S,
+  int32_t resetStateFlag)
+{
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /* Derived coefficient A0 */
+  S->A0 = __QADD16(__QADD16(S->Kp, S->Ki), S->Kd);
+
+  /* Derived coefficients and pack into A1 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+  S->A1 = __PKHBT(-__QADD16(__QADD16(S->Kd, S->Kd), S->Kp), S->Kd, 16);
+
+#else
+
+  S->A1 = __PKHBT(S->Kd, -__QADD16(__QADD16(S->Kd, S->Kd), S->Kp), 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(q15_t));
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  q31_t temp;                                    /*to store the sum */
+
+  /* Derived coefficient A0 */
+  temp = S->Kp + S->Ki + S->Kd;
+  S->A0 = (q15_t) __SSAT(temp, 16);
+
+  /* Derived coefficients and pack into A1 */
+  temp = -(S->Kd + S->Kd + S->Kp);
+  S->A1 = (q15_t) __SSAT(temp, 16);
+  S->A2 = S->Kd;
+
+
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(q15_t));
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of PID group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_init_q31.c

@@ -0,0 +1,99 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_init_q31.c    
+*    
+* Description:	Q31 PID Control initialization function     
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+ * @brief  Initialization function for the Q31 PID Control.   
+ * @param[in,out] *S points to an instance of the Q31 PID structure.   
+ * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.   
+ * @return none.    
+ * \par Description:   
+ * \par    
+ * The <code>resetStateFlag</code> specifies whether to set state to zero or not. \n   
+ * The function computes the structure fields: <code>A0</code>, <code>A1</code> <code>A2</code>    
+ * using the proportional gain( \c Kp), integral gain( \c Ki) and derivative gain( \c Kd)    
+ * also sets the state variables to all zeros.    
+ */
+
+void arm_pid_init_q31(
+  arm_pid_instance_q31 * S,
+  int32_t resetStateFlag)
+{
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /* Derived coefficient A0 */
+  S->A0 = __QADD(__QADD(S->Kp, S->Ki), S->Kd);
+
+  /* Derived coefficient A1 */
+  S->A1 = -__QADD(__QADD(S->Kd, S->Kd), S->Kp);
+
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  q31_t temp;
+
+  /* Derived coefficient A0 */
+  temp = clip_q63_to_q31((q63_t) S->Kp + S->Ki);
+  S->A0 = clip_q63_to_q31((q63_t) temp + S->Kd);
+
+  /* Derived coefficient A1 */
+  temp = clip_q63_to_q31((q63_t) S->Kd + S->Kd);
+  S->A1 = -clip_q63_to_q31((q63_t) temp + S->Kp);
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  /* Derived coefficient A2 */
+  S->A2 = S->Kd;
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(q31_t));
+  }
+
+}
+
+/**    
+ * @} end of PID group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_reset_f32.c

@@ -0,0 +1,57 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_reset_f32.c    
+*    
+* Description:	Floating-point PID Control reset function   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+* @brief  Reset function for the floating-point PID Control.   
+* @param[in] *S	Instance pointer of PID control data structure.   
+* @return none.    
+* \par Description:   
+* The function resets the state buffer to zeros.    
+*/
+void arm_pid_reset_f32(
+  arm_pid_instance_f32 * S)
+{
+
+  /* Clear the state buffer.  The size will be always 3 samples */
+  memset(S->state, 0, 3u * sizeof(float32_t));
+}
+
+/**    
+ * @} end of PID group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_reset_q15.c

@@ -0,0 +1,56 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_reset_q15.c    
+*    
+* Description:	Q15 PID Control reset function   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+* @brief  Reset function for the Q15 PID Control.   
+* @param[in] *S		Instance pointer of PID control data structure.   
+* @return none.    
+* \par Description:   
+* The function resets the state buffer to zeros.    
+*/
+void arm_pid_reset_q15(
+  arm_pid_instance_q15 * S)
+{
+  /* Reset state to zero, The size will be always 3 samples */
+  memset(S->state, 0, 3u * sizeof(q15_t));
+}
+
+/**    
+ * @} end of PID group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_reset_q31.c

@@ -0,0 +1,57 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_reset_q31.c    
+*    
+* Description:	Q31 PID Control reset function   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+* @brief  Reset function for the Q31 PID Control.   
+* @param[in] *S	Instance pointer of PID control data structure.   
+* @return none.    
+* \par Description:   
+* The function resets the state buffer to zeros.    
+*/
+void arm_pid_reset_q31(
+  arm_pid_instance_q31 * S)
+{
+
+  /* Clear the state buffer.  The size will be always 3 samples */
+  memset(S->state, 0, 3u * sizeof(q31_t));
+}
+
+/**    
+ * @} end of PID group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_sin_cos_f32.c

@@ -0,0 +1,428 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_cos_f32.c    
+*    
+* Description:	Sine and Cosine calculation for floating-point values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupController    
+ */
+
+/**    
+ * @defgroup SinCos Sine Cosine   
+ *    
+ * Computes the trigonometric sine and cosine values using a combination of table lookup   
+ * and linear interpolation.     
+ * There are separate functions for Q31 and floating-point data types.   
+ * The input to the floating-point version is in degrees while the   
+ * fixed-point Q31 have a scaled input with the range   
+ * [-1 0.9999] mapping to [-180 179] degrees.   
+ *   
+ * The implementation is based on table lookup using 360 values together with linear interpolation.   
+ * The steps used are:   
+ *  -# Calculation of the nearest integer table index.   
+ *  -# Compute the fractional portion (fract) of the input.   
+ *  -# Fetch the value corresponding to \c index from sine table to \c y0 and also value from \c index+1 to \c y1.      
+ *  -# Sine value is computed as <code> *psinVal = y0 + (fract * (y1 - y0))</code>.    
+ *  -# Fetch the value corresponding to \c index from cosine table to \c y0 and also value from \c index+1 to \c y1.      
+ *  -# Cosine value is computed as <code> *pcosVal = y0 + (fract * (y1 - y0))</code>.    
+ */
+
+ /**    
+ * @addtogroup SinCos    
+ * @{    
+ */
+
+
+/**    
+* \par    
+* Cosine Table is generated from following loop    
+* <pre>for(i = 0; i < 360; i++)    
+* {    
+*    cosTable[i]= cos((i-180) * PI/180.0);    
+* } </pre>   
+*/
+
+static const float32_t cosTable[360] = {
+  -0.999847695156391270f, -0.999390827019095760f, -0.998629534754573830f,
+  -0.997564050259824200f, -0.996194698091745550f, -0.994521895368273290f,
+  -0.992546151641321980f, -0.990268068741570250f,
+  -0.987688340595137660f, -0.984807753012208020f, -0.981627183447663980f,
+  -0.978147600733805690f, -0.974370064785235250f, -0.970295726275996470f,
+  -0.965925826289068200f, -0.961261695938318670f,
+  -0.956304755963035440f, -0.951056516295153530f, -0.945518575599316740f,
+  -0.939692620785908320f, -0.933580426497201740f, -0.927183854566787310f,
+  -0.920504853452440150f, -0.913545457642600760f,
+  -0.906307787036649940f, -0.898794046299167040f, -0.891006524188367790f,
+  -0.882947592858926770f, -0.874619707139395740f, -0.866025403784438710f,
+  -0.857167300702112220f, -0.848048096156425960f,
+  -0.838670567945424160f, -0.829037572555041620f, -0.819152044288991580f,
+  -0.809016994374947340f, -0.798635510047292940f, -0.788010753606721900f,
+  -0.777145961456970680f, -0.766044443118977900f,
+  -0.754709580222772010f, -0.743144825477394130f, -0.731353701619170460f,
+  -0.719339800338651300f, -0.707106781186547460f, -0.694658370458997030f,
+  -0.681998360062498370f, -0.669130606358858240f,
+  -0.656059028990507500f, -0.642787609686539360f, -0.629320391049837280f,
+  -0.615661475325658290f, -0.601815023152048380f, -0.587785252292473030f,
+  -0.573576436351045830f, -0.559192903470746680f,
+  -0.544639035015027080f, -0.529919264233204790f, -0.515038074910054270f,
+  -0.499999999999999780f, -0.484809620246337000f, -0.469471562785890530f,
+  -0.453990499739546750f, -0.438371146789077510f,
+  -0.422618261740699330f, -0.406736643075800100f, -0.390731128489273600f,
+  -0.374606593415912070f, -0.358367949545300270f, -0.342020143325668710f,
+  -0.325568154457156420f, -0.309016994374947340f,
+  -0.292371704722736660f, -0.275637355816999050f, -0.258819045102520850f,
+  -0.241921895599667790f, -0.224951054343864810f, -0.207911690817759120f,
+  -0.190808995376544800f, -0.173648177666930300f,
+  -0.156434465040231040f, -0.139173100960065350f, -0.121869343405147370f,
+  -0.104528463267653330f, -0.087155742747658235f, -0.069756473744125330f,
+  -0.052335956242943620f, -0.034899496702500733f,
+  -0.017452406437283477f, 0.000000000000000061f, 0.017452406437283376f,
+  0.034899496702501080f, 0.052335956242943966f, 0.069756473744125455f,
+  0.087155742747658138f, 0.104528463267653460f,
+  0.121869343405147490f, 0.139173100960065690f, 0.156434465040230920f,
+  0.173648177666930410f, 0.190808995376544920f, 0.207911690817759450f,
+  0.224951054343864920f, 0.241921895599667900f,
+  0.258819045102520740f, 0.275637355816999160f, 0.292371704722736770f,
+  0.309016994374947450f, 0.325568154457156760f, 0.342020143325668820f,
+  0.358367949545300380f, 0.374606593415911960f,
+  0.390731128489273940f, 0.406736643075800210f, 0.422618261740699440f,
+  0.438371146789077460f, 0.453990499739546860f, 0.469471562785890860f,
+  0.484809620246337110f, 0.500000000000000110f,
+  0.515038074910054380f, 0.529919264233204900f, 0.544639035015027200f,
+  0.559192903470746790f, 0.573576436351046050f, 0.587785252292473140f,
+  0.601815023152048270f, 0.615661475325658290f,
+  0.629320391049837500f, 0.642787609686539360f, 0.656059028990507280f,
+  0.669130606358858240f, 0.681998360062498480f, 0.694658370458997370f,
+  0.707106781186547570f, 0.719339800338651190f,
+  0.731353701619170570f, 0.743144825477394240f, 0.754709580222772010f,
+  0.766044443118978010f, 0.777145961456970900f, 0.788010753606722010f,
+  0.798635510047292830f, 0.809016994374947450f,
+  0.819152044288991800f, 0.829037572555041620f, 0.838670567945424050f,
+  0.848048096156425960f, 0.857167300702112330f, 0.866025403784438710f,
+  0.874619707139395740f, 0.882947592858926990f,
+  0.891006524188367900f, 0.898794046299167040f, 0.906307787036649940f,
+  0.913545457642600870f, 0.920504853452440370f, 0.927183854566787420f,
+  0.933580426497201740f, 0.939692620785908430f,
+  0.945518575599316850f, 0.951056516295153530f, 0.956304755963035440f,
+  0.961261695938318890f, 0.965925826289068310f, 0.970295726275996470f,
+  0.974370064785235250f, 0.978147600733805690f,
+  0.981627183447663980f, 0.984807753012208020f, 0.987688340595137770f,
+  0.990268068741570360f, 0.992546151641321980f, 0.994521895368273290f,
+  0.996194698091745550f, 0.997564050259824200f,
+  0.998629534754573830f, 0.999390827019095760f, 0.999847695156391270f,
+  1.000000000000000000f, 0.999847695156391270f, 0.999390827019095760f,
+  0.998629534754573830f, 0.997564050259824200f,
+  0.996194698091745550f, 0.994521895368273290f, 0.992546151641321980f,
+  0.990268068741570360f, 0.987688340595137770f, 0.984807753012208020f,
+  0.981627183447663980f, 0.978147600733805690f,
+  0.974370064785235250f, 0.970295726275996470f, 0.965925826289068310f,
+  0.961261695938318890f, 0.956304755963035440f, 0.951056516295153530f,
+  0.945518575599316850f, 0.939692620785908430f,
+  0.933580426497201740f, 0.927183854566787420f, 0.920504853452440370f,
+  0.913545457642600870f, 0.906307787036649940f, 0.898794046299167040f,
+  0.891006524188367900f, 0.882947592858926990f,
+  0.874619707139395740f, 0.866025403784438710f, 0.857167300702112330f,
+  0.848048096156425960f, 0.838670567945424050f, 0.829037572555041620f,
+  0.819152044288991800f, 0.809016994374947450f,
+  0.798635510047292830f, 0.788010753606722010f, 0.777145961456970900f,
+  0.766044443118978010f, 0.754709580222772010f, 0.743144825477394240f,
+  0.731353701619170570f, 0.719339800338651190f,
+  0.707106781186547570f, 0.694658370458997370f, 0.681998360062498480f,
+  0.669130606358858240f, 0.656059028990507280f, 0.642787609686539360f,
+  0.629320391049837500f, 0.615661475325658290f,
+  0.601815023152048270f, 0.587785252292473140f, 0.573576436351046050f,
+  0.559192903470746790f, 0.544639035015027200f, 0.529919264233204900f,
+  0.515038074910054380f, 0.500000000000000110f,
+  0.484809620246337110f, 0.469471562785890860f, 0.453990499739546860f,
+  0.438371146789077460f, 0.422618261740699440f, 0.406736643075800210f,
+  0.390731128489273940f, 0.374606593415911960f,
+  0.358367949545300380f, 0.342020143325668820f, 0.325568154457156760f,
+  0.309016994374947450f, 0.292371704722736770f, 0.275637355816999160f,
+  0.258819045102520740f, 0.241921895599667900f,
+  0.224951054343864920f, 0.207911690817759450f, 0.190808995376544920f,
+  0.173648177666930410f, 0.156434465040230920f, 0.139173100960065690f,
+  0.121869343405147490f, 0.104528463267653460f,
+  0.087155742747658138f, 0.069756473744125455f, 0.052335956242943966f,
+  0.034899496702501080f, 0.017452406437283376f, 0.000000000000000061f,
+  -0.017452406437283477f, -0.034899496702500733f,
+  -0.052335956242943620f, -0.069756473744125330f, -0.087155742747658235f,
+  -0.104528463267653330f, -0.121869343405147370f, -0.139173100960065350f,
+  -0.156434465040231040f, -0.173648177666930300f,
+  -0.190808995376544800f, -0.207911690817759120f, -0.224951054343864810f,
+  -0.241921895599667790f, -0.258819045102520850f, -0.275637355816999050f,
+  -0.292371704722736660f, -0.309016994374947340f,
+  -0.325568154457156420f, -0.342020143325668710f, -0.358367949545300270f,
+  -0.374606593415912070f, -0.390731128489273600f, -0.406736643075800100f,
+  -0.422618261740699330f, -0.438371146789077510f,
+  -0.453990499739546750f, -0.469471562785890530f, -0.484809620246337000f,
+  -0.499999999999999780f, -0.515038074910054270f, -0.529919264233204790f,
+  -0.544639035015027080f, -0.559192903470746680f,
+  -0.573576436351045830f, -0.587785252292473030f, -0.601815023152048380f,
+  -0.615661475325658290f, -0.629320391049837280f, -0.642787609686539360f,
+  -0.656059028990507500f, -0.669130606358858240f,
+  -0.681998360062498370f, -0.694658370458997030f, -0.707106781186547460f,
+  -0.719339800338651300f, -0.731353701619170460f, -0.743144825477394130f,
+  -0.754709580222772010f, -0.766044443118977900f,
+  -0.777145961456970680f, -0.788010753606721900f, -0.798635510047292940f,
+  -0.809016994374947340f, -0.819152044288991580f, -0.829037572555041620f,
+  -0.838670567945424160f, -0.848048096156425960f,
+  -0.857167300702112220f, -0.866025403784438710f, -0.874619707139395740f,
+  -0.882947592858926770f, -0.891006524188367790f, -0.898794046299167040f,
+  -0.906307787036649940f, -0.913545457642600760f,
+  -0.920504853452440150f, -0.927183854566787310f, -0.933580426497201740f,
+  -0.939692620785908320f, -0.945518575599316740f, -0.951056516295153530f,
+  -0.956304755963035440f, -0.961261695938318670f,
+  -0.965925826289068200f, -0.970295726275996470f, -0.974370064785235250f,
+  -0.978147600733805690f, -0.981627183447663980f, -0.984807753012208020f,
+  -0.987688340595137660f, -0.990268068741570250f,
+  -0.992546151641321980f, -0.994521895368273290f, -0.996194698091745550f,
+  -0.997564050259824200f, -0.998629534754573830f, -0.999390827019095760f,
+  -0.999847695156391270f, -1.000000000000000000f
+};
+
+/**    
+* \par    
+* Sine Table is generated from following loop    
+* <pre>for(i = 0; i < 360; i++)    
+* {    
+*    sinTable[i]= sin((i-180) * PI/180.0);    
+* } </pre>    
+*/
+
+
+static const float32_t sinTable[360] = {
+  -0.017452406437283439f, -0.034899496702500699f, -0.052335956242943807f,
+  -0.069756473744125524f, -0.087155742747658638f, -0.104528463267653730f,
+  -0.121869343405147550f, -0.139173100960065740f,
+  -0.156434465040230980f, -0.173648177666930280f, -0.190808995376544970f,
+  -0.207911690817759310f, -0.224951054343864780f, -0.241921895599667730f,
+  -0.258819045102521020f, -0.275637355816999660f,
+  -0.292371704722737050f, -0.309016994374947510f, -0.325568154457156980f,
+  -0.342020143325668880f, -0.358367949545300210f, -0.374606593415912240f,
+  -0.390731128489274160f, -0.406736643075800430f,
+  -0.422618261740699500f, -0.438371146789077290f, -0.453990499739546860f,
+  -0.469471562785891080f, -0.484809620246337170f, -0.499999999999999940f,
+  -0.515038074910054380f, -0.529919264233204900f,
+  -0.544639035015026860f, -0.559192903470746900f, -0.573576436351046380f,
+  -0.587785252292473250f, -0.601815023152048160f, -0.615661475325658400f,
+  -0.629320391049837720f, -0.642787609686539470f,
+  -0.656059028990507280f, -0.669130606358858350f, -0.681998360062498590f,
+  -0.694658370458997140f, -0.707106781186547570f, -0.719339800338651410f,
+  -0.731353701619170570f, -0.743144825477394240f,
+  -0.754709580222771790f, -0.766044443118978010f, -0.777145961456971010f,
+  -0.788010753606722010f, -0.798635510047292720f, -0.809016994374947450f,
+  -0.819152044288992020f, -0.829037572555041740f,
+  -0.838670567945424050f, -0.848048096156426070f, -0.857167300702112330f,
+  -0.866025403784438710f, -0.874619707139395850f, -0.882947592858927100f,
+  -0.891006524188367900f, -0.898794046299166930f,
+  -0.906307787036650050f, -0.913545457642600980f, -0.920504853452440370f,
+  -0.927183854566787420f, -0.933580426497201740f, -0.939692620785908430f,
+  -0.945518575599316850f, -0.951056516295153640f,
+  -0.956304755963035550f, -0.961261695938318890f, -0.965925826289068310f,
+  -0.970295726275996470f, -0.974370064785235250f, -0.978147600733805690f,
+  -0.981627183447663980f, -0.984807753012208020f,
+  -0.987688340595137660f, -0.990268068741570360f, -0.992546151641322090f,
+  -0.994521895368273400f, -0.996194698091745550f, -0.997564050259824200f,
+  -0.998629534754573830f, -0.999390827019095760f,
+  -0.999847695156391270f, -1.000000000000000000f, -0.999847695156391270f,
+  -0.999390827019095760f, -0.998629534754573830f, -0.997564050259824200f,
+  -0.996194698091745550f, -0.994521895368273290f,
+  -0.992546151641321980f, -0.990268068741570250f, -0.987688340595137770f,
+  -0.984807753012208020f, -0.981627183447663980f, -0.978147600733805580f,
+  -0.974370064785235250f, -0.970295726275996470f,
+  -0.965925826289068310f, -0.961261695938318890f, -0.956304755963035440f,
+  -0.951056516295153530f, -0.945518575599316740f, -0.939692620785908320f,
+  -0.933580426497201740f, -0.927183854566787420f,
+  -0.920504853452440260f, -0.913545457642600870f, -0.906307787036649940f,
+  -0.898794046299167040f, -0.891006524188367790f, -0.882947592858926880f,
+  -0.874619707139395740f, -0.866025403784438600f,
+  -0.857167300702112220f, -0.848048096156426070f, -0.838670567945423940f,
+  -0.829037572555041740f, -0.819152044288991800f, -0.809016994374947450f,
+  -0.798635510047292830f, -0.788010753606722010f,
+  -0.777145961456970790f, -0.766044443118978010f, -0.754709580222772010f,
+  -0.743144825477394240f, -0.731353701619170460f, -0.719339800338651080f,
+  -0.707106781186547460f, -0.694658370458997250f,
+  -0.681998360062498480f, -0.669130606358858240f, -0.656059028990507160f,
+  -0.642787609686539250f, -0.629320391049837390f, -0.615661475325658180f,
+  -0.601815023152048270f, -0.587785252292473140f,
+  -0.573576436351046050f, -0.559192903470746900f, -0.544639035015027080f,
+  -0.529919264233204900f, -0.515038074910054160f, -0.499999999999999940f,
+  -0.484809620246337060f, -0.469471562785890810f,
+  -0.453990499739546750f, -0.438371146789077400f, -0.422618261740699440f,
+  -0.406736643075800150f, -0.390731128489273720f, -0.374606593415912010f,
+  -0.358367949545300270f, -0.342020143325668710f,
+  -0.325568154457156640f, -0.309016994374947400f, -0.292371704722736770f,
+  -0.275637355816999160f, -0.258819045102520740f, -0.241921895599667730f,
+  -0.224951054343865000f, -0.207911690817759310f,
+  -0.190808995376544800f, -0.173648177666930330f, -0.156434465040230870f,
+  -0.139173100960065440f, -0.121869343405147480f, -0.104528463267653460f,
+  -0.087155742747658166f, -0.069756473744125302f,
+  -0.052335956242943828f, -0.034899496702500969f, -0.017452406437283512f,
+  0.000000000000000000f, 0.017452406437283512f, 0.034899496702500969f,
+  0.052335956242943828f, 0.069756473744125302f,
+  0.087155742747658166f, 0.104528463267653460f, 0.121869343405147480f,
+  0.139173100960065440f, 0.156434465040230870f, 0.173648177666930330f,
+  0.190808995376544800f, 0.207911690817759310f,
+  0.224951054343865000f, 0.241921895599667730f, 0.258819045102520740f,
+  0.275637355816999160f, 0.292371704722736770f, 0.309016994374947400f,
+  0.325568154457156640f, 0.342020143325668710f,
+  0.358367949545300270f, 0.374606593415912010f, 0.390731128489273720f,
+  0.406736643075800150f, 0.422618261740699440f, 0.438371146789077400f,
+  0.453990499739546750f, 0.469471562785890810f,
+  0.484809620246337060f, 0.499999999999999940f, 0.515038074910054160f,
+  0.529919264233204900f, 0.544639035015027080f, 0.559192903470746900f,
+  0.573576436351046050f, 0.587785252292473140f,
+  0.601815023152048270f, 0.615661475325658180f, 0.629320391049837390f,
+  0.642787609686539250f, 0.656059028990507160f, 0.669130606358858240f,
+  0.681998360062498480f, 0.694658370458997250f,
+  0.707106781186547460f, 0.719339800338651080f, 0.731353701619170460f,
+  0.743144825477394240f, 0.754709580222772010f, 0.766044443118978010f,
+  0.777145961456970790f, 0.788010753606722010f,
+  0.798635510047292830f, 0.809016994374947450f, 0.819152044288991800f,
+  0.829037572555041740f, 0.838670567945423940f, 0.848048096156426070f,
+  0.857167300702112220f, 0.866025403784438600f,
+  0.874619707139395740f, 0.882947592858926880f, 0.891006524188367790f,
+  0.898794046299167040f, 0.906307787036649940f, 0.913545457642600870f,
+  0.920504853452440260f, 0.927183854566787420f,
+  0.933580426497201740f, 0.939692620785908320f, 0.945518575599316740f,
+  0.951056516295153530f, 0.956304755963035440f, 0.961261695938318890f,
+  0.965925826289068310f, 0.970295726275996470f,
+  0.974370064785235250f, 0.978147600733805580f, 0.981627183447663980f,
+  0.984807753012208020f, 0.987688340595137770f, 0.990268068741570250f,
+  0.992546151641321980f, 0.994521895368273290f,
+  0.996194698091745550f, 0.997564050259824200f, 0.998629534754573830f,
+  0.999390827019095760f, 0.999847695156391270f, 1.000000000000000000f,
+  0.999847695156391270f, 0.999390827019095760f,
+  0.998629534754573830f, 0.997564050259824200f, 0.996194698091745550f,
+  0.994521895368273400f, 0.992546151641322090f, 0.990268068741570360f,
+  0.987688340595137660f, 0.984807753012208020f,
+  0.981627183447663980f, 0.978147600733805690f, 0.974370064785235250f,
+  0.970295726275996470f, 0.965925826289068310f, 0.961261695938318890f,
+  0.956304755963035550f, 0.951056516295153640f,
+  0.945518575599316850f, 0.939692620785908430f, 0.933580426497201740f,
+  0.927183854566787420f, 0.920504853452440370f, 0.913545457642600980f,
+  0.906307787036650050f, 0.898794046299166930f,
+  0.891006524188367900f, 0.882947592858927100f, 0.874619707139395850f,
+  0.866025403784438710f, 0.857167300702112330f, 0.848048096156426070f,
+  0.838670567945424050f, 0.829037572555041740f,
+  0.819152044288992020f, 0.809016994374947450f, 0.798635510047292720f,
+  0.788010753606722010f, 0.777145961456971010f, 0.766044443118978010f,
+  0.754709580222771790f, 0.743144825477394240f,
+  0.731353701619170570f, 0.719339800338651410f, 0.707106781186547570f,
+  0.694658370458997140f, 0.681998360062498590f, 0.669130606358858350f,
+  0.656059028990507280f, 0.642787609686539470f,
+  0.629320391049837720f, 0.615661475325658400f, 0.601815023152048160f,
+  0.587785252292473250f, 0.573576436351046380f, 0.559192903470746900f,
+  0.544639035015026860f, 0.529919264233204900f,
+  0.515038074910054380f, 0.499999999999999940f, 0.484809620246337170f,
+  0.469471562785891080f, 0.453990499739546860f, 0.438371146789077290f,
+  0.422618261740699500f, 0.406736643075800430f,
+  0.390731128489274160f, 0.374606593415912240f, 0.358367949545300210f,
+  0.342020143325668880f, 0.325568154457156980f, 0.309016994374947510f,
+  0.292371704722737050f, 0.275637355816999660f,
+  0.258819045102521020f, 0.241921895599667730f, 0.224951054343864780f,
+  0.207911690817759310f, 0.190808995376544970f, 0.173648177666930280f,
+  0.156434465040230980f, 0.139173100960065740f,
+  0.121869343405147550f, 0.104528463267653730f, 0.087155742747658638f,
+  0.069756473744125524f, 0.052335956242943807f, 0.034899496702500699f,
+  0.017452406437283439f, 0.000000000000000122f
+};
+
+
+/**    
+ * @brief  Floating-point sin_cos function.   
+ * @param[in]  theta    input value in degrees    
+ * @param[out] *pSinVal points to the processed sine output.    
+ * @param[out] *pCosVal points to the processed cos output.    
+ * @return none.   
+ */
+
+
+void arm_sin_cos_f32(
+  float32_t theta,
+  float32_t * pSinVal,
+  float32_t * pCosVal)
+{
+  int32_t i;                                     /* Index for reading nearwst output values */
+  float32_t x1 = -179.0f;                        /* Initial input value */
+  float32_t y0, y1;                              /* nearest output values */
+  float32_t y2, y3;
+  float32_t fract;                               /* fractional part of input */
+
+  /* Calculation of fractional part */
+  if(theta > 0.0f)
+  {
+    fract = theta - (float32_t) ((int32_t) theta);
+  }
+  else
+  {
+    fract = (theta - (float32_t) ((int32_t) theta)) + 1.0f;
+  }
+
+  /* index calculation for reading nearest output values */
+  i = (uint32_t) (theta - x1);
+
+  /* Checking min and max index of table */
+  if(i < 0)
+  {
+    i = 0;
+  }
+  else if(i >= 359)
+  {
+    i = 358;
+  }
+
+  /* reading nearest sine output values */
+  y0 = sinTable[i];
+  y1 = sinTable[i + 1u];
+
+  /* reading nearest cosine output values */
+  y2 = cosTable[i];
+  y3 = cosTable[i + 1u];
+
+  y1 = y1 - y0;
+  y3 = y3 - y2;
+
+  y1 = fract * y1;
+  y3 = fract * y3;
+
+  /* Calculation of sine value */
+  *pSinVal = y0 + y1;
+
+  /* Calculation of cosine value */
+  *pCosVal = y2 + y3;
+
+}
+
+/**    
+ * @} end of SinCos group    
+ */

libs/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_sin_cos_q31.c

@@ -0,0 +1,324 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_cos_q31.c    
+*    
+* Description:	Cosine & Sine calculation for Q31 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupController    
+ */
+
+ /**    
+ * @addtogroup SinCos    
+ * @{    
+ */
+
+/**    
+* \par    
+* Sine Table is generated from following loop    
+* <pre>for(i = 0; i < 360; i++)    
+* {    
+*    sinTable[i]= sin((i-180) * PI/180.0);    
+* } </pre>   
+* Convert above coefficients to fixed point 1.31 format.    
+*/
+
+static const int32_t sinTableQ31[360] = {
+
+  0x0, 0xfdc41e9b, 0xfb8869ce, 0xf94d0e2e, 0xf7123849, 0xf4d814a4, 0xf29ecfb2,
+  0xf06695da,
+  0xee2f9369, 0xebf9f498, 0xe9c5e582, 0xe7939223, 0xe5632654, 0xe334cdc9,
+  0xe108b40d, 0xdedf047d,
+  0xdcb7ea46, 0xda939061, 0xd8722192, 0xd653c860, 0xd438af17, 0xd220ffc0,
+  0xd00ce422, 0xcdfc85bb,
+  0xcbf00dbe, 0xc9e7a512, 0xc7e3744b, 0xc5e3a3a9, 0xc3e85b18, 0xc1f1c224,
+  0xc0000000, 0xbe133b7c,
+  0xbc2b9b05, 0xba4944a2, 0xb86c5df0, 0xb6950c1e, 0xb4c373ee, 0xb2f7b9af,
+  0xb1320139, 0xaf726def,
+  0xadb922b7, 0xac0641fb, 0xaa59eda4, 0xa8b4471a, 0xa7156f3c, 0xa57d8666,
+  0xa3ecac65, 0xa263007d,
+  0xa0e0a15f, 0x9f65ad2d, 0x9df24175, 0x9c867b2c, 0x9b2276b0, 0x99c64fc5,
+  0x98722192, 0x9726069c,
+  0x95e218c9, 0x94a6715d, 0x937328f5, 0x92485786, 0x9126145f, 0x900c7621,
+  0x8efb92c2, 0x8df37f8b,
+  0x8cf45113, 0x8bfe1b3f, 0x8b10f144, 0x8a2ce59f, 0x89520a1a, 0x88806fc4,
+  0x87b826f7, 0x86f93f50,
+  0x8643c7b3, 0x8597ce46, 0x84f56073, 0x845c8ae3, 0x83cd5982, 0x8347d77b,
+  0x82cc0f36, 0x825a0a5b,
+  0x81f1d1ce, 0x81936daf, 0x813ee55b, 0x80f43f69, 0x80b381ac, 0x807cb130,
+  0x804fd23a, 0x802ce84c,
+  0x8013f61d, 0x8004fda0, 0x80000000, 0x8004fda0, 0x8013f61d, 0x802ce84c,
+  0x804fd23a, 0x807cb130,
+  0x80b381ac, 0x80f43f69, 0x813ee55b, 0x81936daf, 0x81f1d1ce, 0x825a0a5b,
+  0x82cc0f36, 0x8347d77b,
+  0x83cd5982, 0x845c8ae3, 0x84f56073, 0x8597ce46, 0x8643c7b3, 0x86f93f50,
+  0x87b826f7, 0x88806fc4,
+  0x89520a1a, 0x8a2ce59f, 0x8b10f144, 0x8bfe1b3f, 0x8cf45113, 0x8df37f8b,
+  0x8efb92c2, 0x900c7621,
+  0x9126145f, 0x92485786, 0x937328f5, 0x94a6715d, 0x95e218c9, 0x9726069c,
+  0x98722192, 0x99c64fc5,
+  0x9b2276b0, 0x9c867b2c, 0x9df24175, 0x9f65ad2d, 0xa0e0a15f, 0xa263007d,
+  0xa3ecac65, 0xa57d8666,
+  0xa7156f3c, 0xa8b4471a, 0xaa59eda4, 0xac0641fb, 0xadb922b7, 0xaf726def,
+  0xb1320139, 0xb2f7b9af,
+  0xb4c373ee, 0xb6950c1e, 0xb86c5df0, 0xba4944a2, 0xbc2b9b05, 0xbe133b7c,
+  0xc0000000, 0xc1f1c224,
+  0xc3e85b18, 0xc5e3a3a9, 0xc7e3744b, 0xc9e7a512, 0xcbf00dbe, 0xcdfc85bb,
+  0xd00ce422, 0xd220ffc0,
+  0xd438af17, 0xd653c860, 0xd8722192, 0xda939061, 0xdcb7ea46, 0xdedf047d,
+  0xe108b40d, 0xe334cdc9,
+  0xe5632654, 0xe7939223, 0xe9c5e582, 0xebf9f498, 0xee2f9369, 0xf06695da,
+  0xf29ecfb2, 0xf4d814a4,
+  0xf7123849, 0xf94d0e2e, 0xfb8869ce, 0xfdc41e9b, 0x0, 0x23be165, 0x4779632,
+  0x6b2f1d2,
+  0x8edc7b7, 0xb27eb5c, 0xd61304e, 0xf996a26, 0x11d06c97, 0x14060b68,
+  0x163a1a7e, 0x186c6ddd,
+  0x1a9cd9ac, 0x1ccb3237, 0x1ef74bf3, 0x2120fb83, 0x234815ba, 0x256c6f9f,
+  0x278dde6e, 0x29ac37a0,
+  0x2bc750e9, 0x2ddf0040, 0x2ff31bde, 0x32037a45, 0x340ff242, 0x36185aee,
+  0x381c8bb5, 0x3a1c5c57,
+  0x3c17a4e8, 0x3e0e3ddc, 0x40000000, 0x41ecc484, 0x43d464fb, 0x45b6bb5e,
+  0x4793a210, 0x496af3e2,
+  0x4b3c8c12, 0x4d084651, 0x4ecdfec7, 0x508d9211, 0x5246dd49, 0x53f9be05,
+  0x55a6125c, 0x574bb8e6,
+  0x58ea90c4, 0x5a82799a, 0x5c13539b, 0x5d9cff83, 0x5f1f5ea1, 0x609a52d3,
+  0x620dbe8b, 0x637984d4,
+  0x64dd8950, 0x6639b03b, 0x678dde6e, 0x68d9f964, 0x6a1de737, 0x6b598ea3,
+  0x6c8cd70b, 0x6db7a87a,
+  0x6ed9eba1, 0x6ff389df, 0x71046d3e, 0x720c8075, 0x730baeed, 0x7401e4c1,
+  0x74ef0ebc, 0x75d31a61,
+  0x76adf5e6, 0x777f903c, 0x7847d909, 0x7906c0b0, 0x79bc384d, 0x7a6831ba,
+  0x7b0a9f8d, 0x7ba3751d,
+  0x7c32a67e, 0x7cb82885, 0x7d33f0ca, 0x7da5f5a5, 0x7e0e2e32, 0x7e6c9251,
+  0x7ec11aa5, 0x7f0bc097,
+  0x7f4c7e54, 0x7f834ed0, 0x7fb02dc6, 0x7fd317b4, 0x7fec09e3, 0x7ffb0260,
+  0x7fffffff, 0x7ffb0260,
+  0x7fec09e3, 0x7fd317b4, 0x7fb02dc6, 0x7f834ed0, 0x7f4c7e54, 0x7f0bc097,
+  0x7ec11aa5, 0x7e6c9251,
+  0x7e0e2e32, 0x7da5f5a5, 0x7d33f0ca, 0x7cb82885, 0x7c32a67e, 0x7ba3751d,
+  0x7b0a9f8d, 0x7a6831ba,
+  0x79bc384d, 0x7906c0b0, 0x7847d909, 0x777f903c, 0x76adf5e6, 0x75d31a61,
+  0x74ef0ebc, 0x7401e4c1,
+  0x730baeed, 0x720c8075, 0x71046d3e, 0x6ff389df, 0x6ed9eba1, 0x6db7a87a,
+  0x6c8cd70b, 0x6b598ea3,
+  0x6a1de737, 0x68d9f964, 0x678dde6e, 0x6639b03b, 0x64dd8950, 0x637984d4,
+  0x620dbe8b, 0x609a52d3,
+  0x5f1f5ea1, 0x5d9cff83, 0x5c13539b, 0x5a82799a, 0x58ea90c4, 0x574bb8e6,
+  0x55a6125c, 0x53f9be05,
+  0x5246dd49, 0x508d9211, 0x4ecdfec7, 0x4d084651, 0x4b3c8c12, 0x496af3e2,
+  0x4793a210, 0x45b6bb5e,
+  0x43d464fb, 0x41ecc484, 0x40000000, 0x3e0e3ddc, 0x3c17a4e8, 0x3a1c5c57,
+  0x381c8bb5, 0x36185aee,
+  0x340ff242, 0x32037a45, 0x2ff31bde, 0x2ddf0040, 0x2bc750e9, 0x29ac37a0,
+  0x278dde6e, 0x256c6f9f,
+  0x234815ba, 0x2120fb83, 0x1ef74bf3, 0x1ccb3237, 0x1a9cd9ac, 0x186c6ddd,
+  0x163a1a7e, 0x14060b68,
+  0x11d06c97, 0xf996a26, 0xd61304e, 0xb27eb5c, 0x8edc7b7, 0x6b2f1d2,
+  0x4779632, 0x23be165,
+
+
+};
+
+/**    
+* \par    
+* Cosine Table is generated from following loop    
+* <pre>for(i = 0; i < 360; i++)    
+* {    
+*    cosTable[i]= cos((i-180) * PI/180.0);    
+* } </pre>   
+* \par    
+* Convert above coefficients to fixed point 1.31 format.    
+*/
+static const int32_t cosTableQ31[360] = {
+  0x80000000, 0x8004fda0, 0x8013f61d, 0x802ce84c, 0x804fd23a, 0x807cb130,
+  0x80b381ac, 0x80f43f69,
+  0x813ee55b, 0x81936daf, 0x81f1d1ce, 0x825a0a5b, 0x82cc0f36, 0x8347d77b,
+  0x83cd5982, 0x845c8ae3,
+  0x84f56073, 0x8597ce46, 0x8643c7b3, 0x86f93f50, 0x87b826f7, 0x88806fc4,
+  0x89520a1a, 0x8a2ce59f,
+  0x8b10f144, 0x8bfe1b3f, 0x8cf45113, 0x8df37f8b, 0x8efb92c2, 0x900c7621,
+  0x9126145f, 0x92485786,
+  0x937328f5, 0x94a6715d, 0x95e218c9, 0x9726069c, 0x98722192, 0x99c64fc5,
+  0x9b2276b0, 0x9c867b2c,
+  0x9df24175, 0x9f65ad2d, 0xa0e0a15f, 0xa263007d, 0xa3ecac65, 0xa57d8666,
+  0xa7156f3c, 0xa8b4471a,
+  0xaa59eda4, 0xac0641fb, 0xadb922b7, 0xaf726def, 0xb1320139, 0xb2f7b9af,
+  0xb4c373ee, 0xb6950c1e,
+  0xb86c5df0, 0xba4944a2, 0xbc2b9b05, 0xbe133b7c, 0xc0000000, 0xc1f1c224,
+  0xc3e85b18, 0xc5e3a3a9,
+  0xc7e3744b, 0xc9e7a512, 0xcbf00dbe, 0xcdfc85bb, 0xd00ce422, 0xd220ffc0,
+  0xd438af17, 0xd653c860,
+  0xd8722192, 0xda939061, 0xdcb7ea46, 0xdedf047d, 0xe108b40d, 0xe334cdc9,
+  0xe5632654, 0xe7939223,
+  0xe9c5e582, 0xebf9f498, 0xee2f9369, 0xf06695da, 0xf29ecfb2, 0xf4d814a4,
+  0xf7123849, 0xf94d0e2e,
+  0xfb8869ce, 0xfdc41e9b, 0x0, 0x23be165, 0x4779632, 0x6b2f1d2, 0x8edc7b7,
+  0xb27eb5c,
+  0xd61304e, 0xf996a26, 0x11d06c97, 0x14060b68, 0x163a1a7e, 0x186c6ddd,
+  0x1a9cd9ac, 0x1ccb3237,
+  0x1ef74bf3, 0x2120fb83, 0x234815ba, 0x256c6f9f, 0x278dde6e, 0x29ac37a0,
+  0x2bc750e9, 0x2ddf0040,
+  0x2ff31bde, 0x32037a45, 0x340ff242, 0x36185aee, 0x381c8bb5, 0x3a1c5c57,
+  0x3c17a4e8, 0x3e0e3ddc,
+  0x40000000, 0x41ecc484, 0x43d464fb, 0x45b6bb5e, 0x4793a210, 0x496af3e2,
+  0x4b3c8c12, 0x4d084651,
+  0x4ecdfec7, 0x508d9211, 0x5246dd49, 0x53f9be05, 0x55a6125c, 0x574bb8e6,
+  0x58ea90c4, 0x5a82799a,
+  0x5c13539b, 0x5d9cff83, 0x5f1f5ea1, 0x609a52d3, 0x620dbe8b, 0x637984d4,
+  0x64dd8950, 0x6639b03b,
+  0x678dde6e, 0x68d9f964, 0x6a1de737, 0x6b598ea3, 0x6c8cd70b, 0x6db7a87a,
+  0x6ed9eba1, 0x6ff389df,
+  0x71046d3e, 0x720c8075, 0x730baeed, 0x7401e4c1, 0x74ef0ebc, 0x75d31a61,
+  0x76adf5e6, 0x777f903c,
+  0x7847d909, 0x7906c0b0, 0x79bc384d, 0x7a6831ba, 0x7b0a9f8d, 0x7ba3751d,
+  0x7c32a67e, 0x7cb82885,
+  0x7d33f0ca, 0x7da5f5a5, 0x7e0e2e32, 0x7e6c9251, 0x7ec11aa5, 0x7f0bc097,
+  0x7f4c7e54, 0x7f834ed0,
+  0x7fb02dc6, 0x7fd317b4, 0x7fec09e3, 0x7ffb0260, 0x7fffffff, 0x7ffb0260,
+  0x7fec09e3, 0x7fd317b4,
+  0x7fb02dc6, 0x7f834ed0, 0x7f4c7e54, 0x7f0bc097, 0x7ec11aa5, 0x7e6c9251,
+  0x7e0e2e32, 0x7da5f5a5,
+  0x7d33f0ca, 0x7cb82885, 0x7c32a67e, 0x7ba3751d, 0x7b0a9f8d, 0x7a6831ba,
+  0x79bc384d, 0x7906c0b0,
+  0x7847d909, 0x777f903c, 0x76adf5e6, 0x75d31a61, 0x74ef0ebc, 0x7401e4c1,
+  0x730baeed, 0x720c8075,
+  0x71046d3e, 0x6ff389df, 0x6ed9eba1, 0x6db7a87a, 0x6c8cd70b, 0x6b598ea3,
+  0x6a1de737, 0x68d9f964,
+  0x678dde6e, 0x6639b03b, 0x64dd8950, 0x637984d4, 0x620dbe8b, 0x609a52d3,
+  0x5f1f5ea1, 0x5d9cff83,
+  0x5c13539b, 0x5a82799a, 0x58ea90c4, 0x574bb8e6, 0x55a6125c, 0x53f9be05,
+  0x5246dd49, 0x508d9211,
+  0x4ecdfec7, 0x4d084651, 0x4b3c8c12, 0x496af3e2, 0x4793a210, 0x45b6bb5e,
+  0x43d464fb, 0x41ecc484,
+  0x40000000, 0x3e0e3ddc, 0x3c17a4e8, 0x3a1c5c57, 0x381c8bb5, 0x36185aee,
+  0x340ff242, 0x32037a45,
+  0x2ff31bde, 0x2ddf0040, 0x2bc750e9, 0x29ac37a0, 0x278dde6e, 0x256c6f9f,
+  0x234815ba, 0x2120fb83,
+  0x1ef74bf3, 0x1ccb3237, 0x1a9cd9ac, 0x186c6ddd, 0x163a1a7e, 0x14060b68,
+  0x11d06c97, 0xf996a26,
+  0xd61304e, 0xb27eb5c, 0x8edc7b7, 0x6b2f1d2, 0x4779632, 0x23be165, 0x0,
+  0xfdc41e9b,
+  0xfb8869ce, 0xf94d0e2e, 0xf7123849, 0xf4d814a4, 0xf29ecfb2, 0xf06695da,
+  0xee2f9369, 0xebf9f498,
+  0xe9c5e582, 0xe7939223, 0xe5632654, 0xe334cdc9, 0xe108b40d, 0xdedf047d,
+  0xdcb7ea46, 0xda939061,
+  0xd8722192, 0xd653c860, 0xd438af17, 0xd220ffc0, 0xd00ce422, 0xcdfc85bb,
+  0xcbf00dbe, 0xc9e7a512,
+  0xc7e3744b, 0xc5e3a3a9, 0xc3e85b18, 0xc1f1c224, 0xc0000000, 0xbe133b7c,
+  0xbc2b9b05, 0xba4944a2,
+  0xb86c5df0, 0xb6950c1e, 0xb4c373ee, 0xb2f7b9af, 0xb1320139, 0xaf726def,
+  0xadb922b7, 0xac0641fb,
+  0xaa59eda4, 0xa8b4471a, 0xa7156f3c, 0xa57d8666, 0xa3ecac65, 0xa263007d,
+  0xa0e0a15f, 0x9f65ad2d,
+  0x9df24175, 0x9c867b2c, 0x9b2276b0, 0x99c64fc5, 0x98722192, 0x9726069c,
+  0x95e218c9, 0x94a6715d,
+  0x937328f5, 0x92485786, 0x9126145f, 0x900c7621, 0x8efb92c2, 0x8df37f8b,
+  0x8cf45113, 0x8bfe1b3f,
+  0x8b10f144, 0x8a2ce59f, 0x89520a1a, 0x88806fc4, 0x87b826f7, 0x86f93f50,
+  0x8643c7b3, 0x8597ce46,
+  0x84f56073, 0x845c8ae3, 0x83cd5982, 0x8347d77b, 0x82cc0f36, 0x825a0a5b,
+  0x81f1d1ce, 0x81936daf,
+  0x813ee55b, 0x80f43f69, 0x80b381ac, 0x807cb130, 0x804fd23a, 0x802ce84c,
+  0x8013f61d, 0x8004fda0,
+
+};
+
+
+/**    
+ * @brief  Q31 sin_cos function.   
+ * @param[in]  theta    scaled input value in degrees    
+ * @param[out] *pSinVal points to the processed sine output.    
+ * @param[out] *pCosVal points to the processed cosine output.    
+ * @return none.   
+ *    
+ * The Q31 input value is in the range [-1 0.999999] and is mapped to a degree value in the range [-180 179].   
+ *    
+ */
+
+
+void arm_sin_cos_q31(
+  q31_t theta,
+  q31_t * pSinVal,
+  q31_t * pCosVal)
+{
+  q31_t x0;                                      /* Nearest input value */
+  q31_t y0, y1;                                  /* Nearest output values */
+  q31_t xSpacing = INPUT_SPACING;                /* Spaing between inputs */
+  int32_t i;                                     /* Index */
+  q31_t oneByXSpacing;                           /* 1/ xSpacing value */
+  q31_t out;                                     /* temporary variable */
+  uint32_t sign_bits;                            /* No.of sign bits */
+  uint32_t firstX = 0x80000000;                  /* First X value */
+
+  /* Calculation of index */
+  i = ((uint32_t) theta - firstX) / (uint32_t) xSpacing;
+
+  /* Checking min and max index of table */
+  if(i < 0)
+  {
+    i = 0;
+  }
+  else if(i >= 359)
+  {
+    i = 358;
+  }
+
+  /* Calculation of first nearest input value */
+  x0 = (q31_t) firstX + ((q31_t) i * xSpacing);
+
+  /* Reading nearest sine output values from table */
+  y0 = sinTableQ31[i];
+  y1 = sinTableQ31[i + 1u];
+
+  /* Calculation of 1/(x1-x0) */
+  /* (x1-x0) is xSpacing which is fixed value */
+  sign_bits = 8u;
+  oneByXSpacing = 0x5A000000;
+
+  /* Calculation of (theta - x0)/(x1-x0) */
+  out =
+    (((q31_t) (((q63_t) (theta - x0) * oneByXSpacing) >> 32)) << sign_bits);
+
+  /* Calculation of y0 + (y1 - y0) * ((theta - x0)/(x1-x0)) */
+  *pSinVal = __QADD(y0, ((q31_t) (((q63_t) (y1 - y0) * out) >> 30)));
+
+  /* Reading nearest cosine output values from table */
+  y0 = cosTableQ31[i];
+  y1 = cosTableQ31[i + 1u];
+
+  /* Calculation of y0 + (y1 - y0) * ((theta - x0)/(x1-x0)) */
+  *pCosVal = __QADD(y0, ((q31_t) (((q63_t) (y1 - y0) * out) >> 30)));
+
+}
+
+/**    
+ * @} end of SinCos group    
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_cos_f32.c

@@ -0,0 +1,280 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cos_f32.c    
+*    
+* Description:	Fast cosine calculation for floating-point values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+/**    
+ * @ingroup groupFastMath    
+ */
+
+/**    
+ * @defgroup cos Cosine    
+ *    
+ * Computes the trigonometric cosine function using a combination of table lookup   
+ * and cubic interpolation.  There are separate functions for   
+ * Q15, Q31, and floating-point data types.   
+ * The input to the floating-point version is in radians while the   
+ * fixed-point Q15 and Q31 have a scaled input with the range   
+ * [0 +0.9999] mapping to [0 2*pi), Where range excludes 2*pi.   
+ *   
+ * The implementation is based on table lookup using 256 values together with cubic interpolation.   
+ * The steps used are:   
+ *  -# Calculation of the nearest integer table index   
+ *  -# Fetch the four table values a, b, c, and d     
+ *  -# Compute the fractional portion (fract) of the table index.   
+ *  -# Calculation of wa, wb, wc, wd    
+ *  -# The final result equals <code>a*wa + b*wb + c*wc + d*wd</code>   
+ *   
+ * where   
+ * <pre>    
+ *    a=Table[index-1];    
+ *    b=Table[index+0];    
+ *    c=Table[index+1];    
+ *    d=Table[index+2];    
+ * </pre>   
+ * and   
+ * <pre>    
+ *    wa=-(1/6)*fract.^3 + (1/2)*fract.^2 - (1/3)*fract;    
+ *    wb=(1/2)*fract.^3 - fract.^2 - (1/2)*fract + 1;    
+ *    wc=-(1/2)*fract.^3+(1/2)*fract.^2+fract;    
+ *    wd=(1/6)*fract.^3 - (1/6)*fract;    
+ * </pre>    
+ */
+
+ /**    
+ * @addtogroup cos    
+ * @{    
+ */
+
+
+/**    
+* \par    
+* <b>Example code for Generation of Cos Table:</b>   
+* tableSize = 256;    
+* <pre>for(n = -1; n < (tableSize + 2); n++)    
+* {    
+*	cosTable[n+1]= cos(2*pi*n/tableSize);    
+* } </pre>    
+* where pi value is  3.14159265358979    
+*/
+
+static const float32_t cosTable[260] = {
+  0.999698817729949950f, 1.000000000000000000f, 0.999698817729949950f,
+  0.998795449733734130f, 0.997290432453155520f, 0.995184719562530520f,
+  0.992479562759399410f, 0.989176511764526370f,
+  0.985277652740478520f, 0.980785250663757320f, 0.975702106952667240f,
+  0.970031261444091800f, 0.963776051998138430f, 0.956940352916717530f,
+  0.949528157711029050f, 0.941544055938720700f,
+  0.932992815971374510f, 0.923879504203796390f, 0.914209783077239990f,
+  0.903989315032958980f, 0.893224298954010010f, 0.881921291351318360f,
+  0.870086967945098880f, 0.857728600502014160f,
+  0.844853579998016360f, 0.831469595432281490f, 0.817584812641143800f,
+  0.803207516670227050f, 0.788346409797668460f, 0.773010432720184330f,
+  0.757208824157714840f, 0.740951120853424070f,
+  0.724247097969055180f, 0.707106769084930420f, 0.689540565013885500f,
+  0.671558976173400880f, 0.653172850608825680f, 0.634393274784088130f,
+  0.615231573581695560f, 0.595699310302734380f,
+  0.575808167457580570f, 0.555570244789123540f, 0.534997642040252690f,
+  0.514102756977081300f, 0.492898195981979370f, 0.471396744251251220f,
+  0.449611335992813110f, 0.427555084228515630f,
+  0.405241310596466060f, 0.382683426141738890f, 0.359895050525665280f,
+  0.336889863014221190f, 0.313681751489639280f, 0.290284663438797000f,
+  0.266712754964828490f, 0.242980182170867920f,
+  0.219101235270500180f, 0.195090323686599730f, 0.170961886644363400f,
+  0.146730467677116390f, 0.122410677373409270f, 0.098017141222953796f,
+  0.073564566671848297f, 0.049067676067352295f,
+  0.024541229009628296f, 0.000000000000000061f, -0.024541229009628296f,
+  -0.049067676067352295f, -0.073564566671848297f, -0.098017141222953796f,
+  -0.122410677373409270f, -0.146730467677116390f,
+  -0.170961886644363400f, -0.195090323686599730f, -0.219101235270500180f,
+  -0.242980182170867920f, -0.266712754964828490f, -0.290284663438797000f,
+  -0.313681751489639280f, -0.336889863014221190f,
+  -0.359895050525665280f, -0.382683426141738890f, -0.405241310596466060f,
+  -0.427555084228515630f, -0.449611335992813110f, -0.471396744251251220f,
+  -0.492898195981979370f, -0.514102756977081300f,
+  -0.534997642040252690f, -0.555570244789123540f, -0.575808167457580570f,
+  -0.595699310302734380f, -0.615231573581695560f, -0.634393274784088130f,
+  -0.653172850608825680f, -0.671558976173400880f,
+  -0.689540565013885500f, -0.707106769084930420f, -0.724247097969055180f,
+  -0.740951120853424070f, -0.757208824157714840f, -0.773010432720184330f,
+  -0.788346409797668460f, -0.803207516670227050f,
+  -0.817584812641143800f, -0.831469595432281490f, -0.844853579998016360f,
+  -0.857728600502014160f, -0.870086967945098880f, -0.881921291351318360f,
+  -0.893224298954010010f, -0.903989315032958980f,
+  -0.914209783077239990f, -0.923879504203796390f, -0.932992815971374510f,
+  -0.941544055938720700f, -0.949528157711029050f, -0.956940352916717530f,
+  -0.963776051998138430f, -0.970031261444091800f,
+  -0.975702106952667240f, -0.980785250663757320f, -0.985277652740478520f,
+  -0.989176511764526370f, -0.992479562759399410f, -0.995184719562530520f,
+  -0.997290432453155520f, -0.998795449733734130f,
+  -0.999698817729949950f, -1.000000000000000000f, -0.999698817729949950f,
+  -0.998795449733734130f, -0.997290432453155520f, -0.995184719562530520f,
+  -0.992479562759399410f, -0.989176511764526370f,
+  -0.985277652740478520f, -0.980785250663757320f, -0.975702106952667240f,
+  -0.970031261444091800f, -0.963776051998138430f, -0.956940352916717530f,
+  -0.949528157711029050f, -0.941544055938720700f,
+  -0.932992815971374510f, -0.923879504203796390f, -0.914209783077239990f,
+  -0.903989315032958980f, -0.893224298954010010f, -0.881921291351318360f,
+  -0.870086967945098880f, -0.857728600502014160f,
+  -0.844853579998016360f, -0.831469595432281490f, -0.817584812641143800f,
+  -0.803207516670227050f, -0.788346409797668460f, -0.773010432720184330f,
+  -0.757208824157714840f, -0.740951120853424070f,
+  -0.724247097969055180f, -0.707106769084930420f, -0.689540565013885500f,
+  -0.671558976173400880f, -0.653172850608825680f, -0.634393274784088130f,
+  -0.615231573581695560f, -0.595699310302734380f,
+  -0.575808167457580570f, -0.555570244789123540f, -0.534997642040252690f,
+  -0.514102756977081300f, -0.492898195981979370f, -0.471396744251251220f,
+  -0.449611335992813110f, -0.427555084228515630f,
+  -0.405241310596466060f, -0.382683426141738890f, -0.359895050525665280f,
+  -0.336889863014221190f, -0.313681751489639280f, -0.290284663438797000f,
+  -0.266712754964828490f, -0.242980182170867920f,
+  -0.219101235270500180f, -0.195090323686599730f, -0.170961886644363400f,
+  -0.146730467677116390f, -0.122410677373409270f, -0.098017141222953796f,
+  -0.073564566671848297f, -0.049067676067352295f,
+  -0.024541229009628296f, -0.000000000000000184f, 0.024541229009628296f,
+  0.049067676067352295f, 0.073564566671848297f, 0.098017141222953796f,
+  0.122410677373409270f, 0.146730467677116390f,
+  0.170961886644363400f, 0.195090323686599730f, 0.219101235270500180f,
+  0.242980182170867920f, 0.266712754964828490f, 0.290284663438797000f,
+  0.313681751489639280f, 0.336889863014221190f,
+  0.359895050525665280f, 0.382683426141738890f, 0.405241310596466060f,
+  0.427555084228515630f, 0.449611335992813110f, 0.471396744251251220f,
+  0.492898195981979370f, 0.514102756977081300f,
+  0.534997642040252690f, 0.555570244789123540f, 0.575808167457580570f,
+  0.595699310302734380f, 0.615231573581695560f, 0.634393274784088130f,
+  0.653172850608825680f, 0.671558976173400880f,
+  0.689540565013885500f, 0.707106769084930420f, 0.724247097969055180f,
+  0.740951120853424070f, 0.757208824157714840f, 0.773010432720184330f,
+  0.788346409797668460f, 0.803207516670227050f,
+  0.817584812641143800f, 0.831469595432281490f, 0.844853579998016360f,
+  0.857728600502014160f, 0.870086967945098880f, 0.881921291351318360f,
+  0.893224298954010010f, 0.903989315032958980f,
+  0.914209783077239990f, 0.923879504203796390f, 0.932992815971374510f,
+  0.941544055938720700f, 0.949528157711029050f, 0.956940352916717530f,
+  0.963776051998138430f, 0.970031261444091800f,
+  0.975702106952667240f, 0.980785250663757320f, 0.985277652740478520f,
+  0.989176511764526370f, 0.992479562759399410f, 0.995184719562530520f,
+  0.997290432453155520f, 0.998795449733734130f,
+  0.999698817729949950f, 1.000000000000000000f, 0.999698817729949950f,
+  0.998795449733734130f
+};
+
+/**   
+ * @brief  Fast approximation to the trigonometric cosine function for floating-point data.   
+ * @param[in] x input value in radians.   
+ * @return cos(x).   
+ */
+
+
+float32_t arm_cos_f32(
+  float32_t x)
+{
+  float32_t cosVal, fract, in;
+  int32_t index;
+  uint32_t tableSize = (uint32_t) TABLE_SIZE;
+  float32_t wa, wb, wc, wd;
+  float32_t a, b, c, d;
+  float32_t *tablePtr;
+  int32_t n;
+  float32_t fractsq, fractby2, fractby6, fractby3, fractsqby2;
+  float32_t oneminusfractby2;
+  float32_t frby2xfrsq, frby6xfrsq;
+
+  /* input x is in radians */
+  /* Scale the input to [0 1] range from [0 2*PI] , divide input by 2*pi */
+  in = x * 0.159154943092f;
+
+  /* Calculation of floor value of input */
+  n = (int32_t) in;
+
+  /* Make negative values towards -infinity */
+  if(x < 0.0f)
+  {
+    n = n - 1;
+  }
+
+  /* Map input value to [0 1] */
+  in = in - (float32_t) n;
+
+  /* Calculation of index of the table */
+  index = (uint32_t) (tableSize * in);
+
+  /* fractional value calculation */
+  fract = ((float32_t) tableSize * in) - (float32_t) index;
+
+  /* Checking min and max index of table */
+  if(index < 0)
+  {
+    index = 0;
+  }
+  else if(index > 256)
+  {
+    index = 256;
+  }
+
+  /* Initialise table pointer */
+  tablePtr = (float32_t *) & cosTable[index];
+
+  /* Read four nearest values of input value from the cos table */
+  a = tablePtr[0];
+  b = tablePtr[1];
+  c = tablePtr[2];
+  d = tablePtr[3];
+
+  /* Cubic interpolation process */
+  fractsq = fract * fract;
+  fractby2 = fract * 0.5f;
+  fractby6 = fract * 0.166666667f;
+  fractby3 = fract * 0.3333333333333f;
+  fractsqby2 = fractsq * 0.5f;
+  frby2xfrsq = (fractby2) * fractsq;
+  frby6xfrsq = (fractby6) * fractsq;
+  oneminusfractby2 = 1.0f - fractby2;
+  wb = fractsqby2 - fractby3;
+  wc = (fractsqby2 + fract);
+  wa = wb - frby6xfrsq;
+  wb = frby2xfrsq - fractsq;
+  cosVal = wa * a;
+  wc = wc - frby2xfrsq;
+  wd = (frby6xfrsq) - fractby6;
+  wb = wb + oneminusfractby2;
+
+  /* Calculate cos value */
+  cosVal = (cosVal + (b * wb)) + ((c * wc) + (d * wd));
+
+  /* Return the output value */
+  return (cosVal);
+
+}
+
+/**    
+ * @} end of cos group    
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_cos_q15.c

@@ -0,0 +1,205 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cos_q15.c    
+*    
+* Description:	Fast cosine calculation for Q15 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFastMath    
+ */
+
+ /**    
+ * @addtogroup cos    
+ * @{    
+ */
+
+/**   
+* \par    
+* Table Values are in Q15(1.15 Fixed point format) and generation is done in three steps    
+* \par    
+* First Generate cos values in floating point:    
+* tableSize = 256;     
+* <pre>for(n = -1; n < (tableSize + 1); n++)    
+* {    
+*	cosTable[n+1]= cos(2*pi*n/tableSize);    
+* }</pre>   
+* where pi value is  3.14159265358979    
+* \par    
+* Secondly Convert Floating point to Q15(Fixed point):    
+*	(cosTable[i] * pow(2, 15))    
+* \par    
+* Finally Rounding to nearest integer is done    
+* 	cosTable[i] += (cosTable[i] > 0 ? 0.5 :-0.5);    
+*/
+
+static const q15_t cosTableQ15[259] = {
+  0x7ff6, 0x7fff, 0x7ff6, 0x7fd9, 0x7fa7, 0x7f62, 0x7f0a, 0x7e9d,
+  0x7e1e, 0x7d8a, 0x7ce4, 0x7c2a, 0x7b5d, 0x7a7d, 0x798a, 0x7885,
+  0x776c, 0x7642, 0x7505, 0x73b6, 0x7255, 0x70e3, 0x6f5f, 0x6dca,
+  0x6c24, 0x6a6e, 0x68a7, 0x66d0, 0x64e9, 0x62f2, 0x60ec, 0x5ed7,
+  0x5cb4, 0x5a82, 0x5843, 0x55f6, 0x539b, 0x5134, 0x4ec0, 0x4c40,
+  0x49b4, 0x471d, 0x447b, 0x41ce, 0x3f17, 0x3c57, 0x398d, 0x36ba,
+  0x33df, 0x30fc, 0x2e11, 0x2b1f, 0x2827, 0x2528, 0x2224, 0x1f1a,
+  0x1c0c, 0x18f9, 0x15e2, 0x12c8, 0xfab, 0xc8c, 0x96b, 0x648,
+  0x324, 0x0, 0xfcdc, 0xf9b8, 0xf695, 0xf374, 0xf055, 0xed38,
+  0xea1e, 0xe707, 0xe3f4, 0xe0e6, 0xdddc, 0xdad8, 0xd7d9, 0xd4e1,
+  0xd1ef, 0xcf04, 0xcc21, 0xc946, 0xc673, 0xc3a9, 0xc0e9, 0xbe32,
+  0xbb85, 0xb8e3, 0xb64c, 0xb3c0, 0xb140, 0xaecc, 0xac65, 0xaa0a,
+  0xa7bd, 0xa57e, 0xa34c, 0xa129, 0x9f14, 0x9d0e, 0x9b17, 0x9930,
+  0x9759, 0x9592, 0x93dc, 0x9236, 0x90a1, 0x8f1d, 0x8dab, 0x8c4a,
+  0x8afb, 0x89be, 0x8894, 0x877b, 0x8676, 0x8583, 0x84a3, 0x83d6,
+  0x831c, 0x8276, 0x81e2, 0x8163, 0x80f6, 0x809e, 0x8059, 0x8027,
+  0x800a, 0x8000, 0x800a, 0x8027, 0x8059, 0x809e, 0x80f6, 0x8163,
+  0x81e2, 0x8276, 0x831c, 0x83d6, 0x84a3, 0x8583, 0x8676, 0x877b,
+  0x8894, 0x89be, 0x8afb, 0x8c4a, 0x8dab, 0x8f1d, 0x90a1, 0x9236,
+  0x93dc, 0x9592, 0x9759, 0x9930, 0x9b17, 0x9d0e, 0x9f14, 0xa129,
+  0xa34c, 0xa57e, 0xa7bd, 0xaa0a, 0xac65, 0xaecc, 0xb140, 0xb3c0,
+  0xb64c, 0xb8e3, 0xbb85, 0xbe32, 0xc0e9, 0xc3a9, 0xc673, 0xc946,
+  0xcc21, 0xcf04, 0xd1ef, 0xd4e1, 0xd7d9, 0xdad8, 0xdddc, 0xe0e6,
+  0xe3f4, 0xe707, 0xea1e, 0xed38, 0xf055, 0xf374, 0xf695, 0xf9b8,
+  0xfcdc, 0x0, 0x324, 0x648, 0x96b, 0xc8c, 0xfab, 0x12c8,
+  0x15e2, 0x18f9, 0x1c0c, 0x1f1a, 0x2224, 0x2528, 0x2827, 0x2b1f,
+  0x2e11, 0x30fc, 0x33df, 0x36ba, 0x398d, 0x3c57, 0x3f17, 0x41ce,
+  0x447b, 0x471d, 0x49b4, 0x4c40, 0x4ec0, 0x5134, 0x539b, 0x55f6,
+  0x5843, 0x5a82, 0x5cb4, 0x5ed7, 0x60ec, 0x62f2, 0x64e9, 0x66d0,
+  0x68a7, 0x6a6e, 0x6c24, 0x6dca, 0x6f5f, 0x70e3, 0x7255, 0x73b6,
+  0x7505, 0x7642, 0x776c, 0x7885, 0x798a, 0x7a7d, 0x7b5d, 0x7c2a,
+  0x7ce4, 0x7d8a, 0x7e1e, 0x7e9d, 0x7f0a, 0x7f62, 0x7fa7, 0x7fd9,
+  0x7ff6, 0x7fff, 0x7ff6
+};
+
+
+/**   
+ * @brief Fast approximation to the trigonometric cosine function for Q15 data.   
+ * @param[in] x Scaled input value in radians.   
+ * @return  cos(x).   
+ *   
+ * The Q15 input value is in the range [0 +0.9999] and is mapped to a radian value in the range [0 2*pi), Here range excludes 2*pi.   
+ */
+
+q15_t arm_cos_q15(
+  q15_t x)
+{
+  q31_t cosVal;                                  /* Temporary variable for output */
+  q15_t *tablePtr;                               /* Pointer to table */
+  q15_t in, in2;                                 /* Temporary variables for input */
+  q31_t wa, wb, wc, wd;                          /* Cubic interpolation coefficients */
+  q15_t a, b, c, d;                              /* Four nearest output values */
+  q15_t fract, fractCube, fractSquare;           /* Variables for fractional value */
+  q15_t oneBy6 = 0x1555;                         /* Fixed point value of 1/6 */
+  q15_t tableSpacing = TABLE_SPACING_Q15;        /* Table spacing */
+  int32_t index;                                 /* Index variable */
+
+  in = x;
+
+  /* Calculate the nearest index */
+  index = (int32_t) in / tableSpacing;
+
+  /* Calculate the nearest value of input */
+  in2 = (q15_t) index *tableSpacing;
+
+  /* Calculation of fractional value */
+  fract = (in - in2) << 8;
+
+  /* fractSquare = fract * fract */
+  fractSquare = (q15_t) ((fract * fract) >> 15);
+
+  /* fractCube = fract * fract * fract */
+  fractCube = (q15_t) ((fractSquare * fract) >> 15);
+
+  /* Checking min and max index of table */
+  if(index < 0)
+  {
+    index = 0;
+  }
+  else if(index > 256)
+  {
+    index = 256;
+  }
+
+  /* Initialise table pointer */
+  tablePtr = (q15_t *) & cosTableQ15[index];
+
+  /* Cubic interpolation process */
+  /* Calculation of wa */
+  /* wa = -(oneBy6)*fractCube + (fractSquare >> 1u) - (0x2AAA)*fract; */
+  wa = (q31_t) oneBy6 *fractCube;
+  wa += (q31_t) 0x2AAA *fract;
+  wa = -(wa >> 15);
+  wa += (fractSquare >> 1u);
+
+  /* Read first nearest value of output from the cos table */
+  a = *tablePtr++;
+
+  /* cosVal = a * wa */
+  cosVal = a * wa;
+
+  /* Calculation of wb */
+  wb = (((fractCube >> 1u) - fractSquare) - (fract >> 1u)) + 0x7FFF;
+
+  /* Read second nearest value of output from the cos table */
+  b = *tablePtr++;
+
+  /*      cosVal += b*wb */
+  cosVal += b * wb;
+
+  /* Calculation of wc */
+  wc = -(q31_t) fractCube + fractSquare;
+  wc = (wc >> 1u) + fract;
+
+  /* Read third nearest value of output from the cos table */
+  c = *tablePtr++;
+
+  /* cosVal += c*wc */
+  cosVal += c * wc;
+
+  /* Calculation of wd */
+  /* wd = (oneBy6)*fractCube - (oneBy6)*fract; */
+  fractCube = fractCube - fract;
+  wd = ((q15_t) (((q31_t) oneBy6 * fractCube) >> 15));
+
+  /* Read fourth nearest value of output from the cos table */
+  d = *tablePtr++;
+
+  /* cosVal += d*wd; */
+  cosVal += d * wd;
+
+  /* Convert output value in 1.15(q15) format and saturate */
+  cosVal = __SSAT((cosVal >> 15), 16);
+
+  /* Return the output value in 1.15(q15) format */
+  return ((q15_t) cosVal);
+
+}
+
+/**    
+ * @} end of cos group    
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_cos_q31.c

@@ -0,0 +1,239 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cos_q31.c    
+*    
+* Description:	Fast cosine calculation for Q31 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFastMath    
+ */
+
+ /**    
+ * @addtogroup cos    
+ * @{    
+ */
+
+/**    
+ * \par    
+ * Table Values are in Q31(1.31 Fixed point format) and generation is done in three steps    
+ * First Generate cos values in floating point:    
+ * tableSize = 256;      
+ * <pre>for(n = -1; n < (tableSize + 1); n++)    
+ * {    
+ *	cosTable[n+1]= cos(2*pi*n/tableSize);    
+ * } </pre>     
+ * where pi value is  3.14159265358979    
+ * \par    
+ * Secondly Convert Floating point to Q31(Fixed point):    
+ *	(cosTable[i] * pow(2, 31))    
+ * \par    
+ * Finally Rounding to nearest integer is done    
+ * 	cosTable[i] += (cosTable[i] > 0 ? 0.5 :-0.5);    
+ */
+
+
+static const q31_t cosTableQ31[259] = {
+  0x7ff62182, 0x7fffffff, 0x7ff62182, 0x7fd8878e, 0x7fa736b4, 0x7f62368f,
+  0x7f0991c4, 0x7e9d55fc,
+  0x7e1d93ea, 0x7d8a5f40, 0x7ce3ceb2, 0x7c29fbee, 0x7b5d039e, 0x7a7d055b,
+  0x798a23b1, 0x78848414,
+  0x776c4edb, 0x7641af3d, 0x7504d345, 0x73b5ebd1, 0x72552c85, 0x70e2cbc6,
+  0x6f5f02b2, 0x6dca0d14,
+  0x6c242960, 0x6a6d98a4, 0x68a69e81, 0x66cf8120, 0x64e88926, 0x62f201ac,
+  0x60ec3830, 0x5ed77c8a,
+  0x5cb420e0, 0x5a82799a, 0x5842dd54, 0x55f5a4d2, 0x539b2af0, 0x5133cc94,
+  0x4ebfe8a5, 0x4c3fdff4,
+  0x49b41533, 0x471cece7, 0x447acd50, 0x41ce1e65, 0x3f1749b8, 0x3c56ba70,
+  0x398cdd32, 0x36ba2014,
+  0x33def287, 0x30fbc54d, 0x2e110a62, 0x2b1f34eb, 0x2826b928, 0x25280c5e,
+  0x2223a4c5, 0x1f19f97b,
+  0x1c0b826a, 0x18f8b83c, 0x15e21445, 0x12c8106f, 0xfab272b, 0xc8bd35e,
+  0x96a9049, 0x647d97c,
+  0x3242abf, 0x0, 0xfcdbd541, 0xf9b82684, 0xf6956fb7, 0xf3742ca2, 0xf054d8d5,
+  0xed37ef91,
+  0xea1debbb, 0xe70747c4, 0xe3f47d96, 0xe0e60685, 0xdddc5b3b, 0xdad7f3a2,
+  0xd7d946d8, 0xd4e0cb15,
+  0xd1eef59e, 0xcf043ab3, 0xcc210d79, 0xc945dfec, 0xc67322ce, 0xc3a94590,
+  0xc0e8b648, 0xbe31e19b,
+  0xbb8532b0, 0xb8e31319, 0xb64beacd, 0xb3c0200c, 0xb140175b, 0xaecc336c,
+  0xac64d510, 0xaa0a5b2e,
+  0xa7bd22ac, 0xa57d8666, 0xa34bdf20, 0xa1288376, 0x9f13c7d0, 0x9d0dfe54,
+  0x9b1776da, 0x99307ee0,
+  0x9759617f, 0x9592675c, 0x93dbd6a0, 0x9235f2ec, 0x90a0fd4e, 0x8f1d343a,
+  0x8daad37b, 0x8c4a142f,
+  0x8afb2cbb, 0x89be50c3, 0x8893b125, 0x877b7bec, 0x8675dc4f, 0x8582faa5,
+  0x84a2fc62, 0x83d60412,
+  0x831c314e, 0x8275a0c0, 0x81e26c16, 0x8162aa04, 0x80f66e3c, 0x809dc971,
+  0x8058c94c, 0x80277872,
+  0x8009de7e, 0x80000000, 0x8009de7e, 0x80277872, 0x8058c94c, 0x809dc971,
+  0x80f66e3c, 0x8162aa04,
+  0x81e26c16, 0x8275a0c0, 0x831c314e, 0x83d60412, 0x84a2fc62, 0x8582faa5,
+  0x8675dc4f, 0x877b7bec,
+  0x8893b125, 0x89be50c3, 0x8afb2cbb, 0x8c4a142f, 0x8daad37b, 0x8f1d343a,
+  0x90a0fd4e, 0x9235f2ec,
+  0x93dbd6a0, 0x9592675c, 0x9759617f, 0x99307ee0, 0x9b1776da, 0x9d0dfe54,
+  0x9f13c7d0, 0xa1288376,
+  0xa34bdf20, 0xa57d8666, 0xa7bd22ac, 0xaa0a5b2e, 0xac64d510, 0xaecc336c,
+  0xb140175b, 0xb3c0200c,
+  0xb64beacd, 0xb8e31319, 0xbb8532b0, 0xbe31e19b, 0xc0e8b648, 0xc3a94590,
+  0xc67322ce, 0xc945dfec,
+  0xcc210d79, 0xcf043ab3, 0xd1eef59e, 0xd4e0cb15, 0xd7d946d8, 0xdad7f3a2,
+  0xdddc5b3b, 0xe0e60685,
+  0xe3f47d96, 0xe70747c4, 0xea1debbb, 0xed37ef91, 0xf054d8d5, 0xf3742ca2,
+  0xf6956fb7, 0xf9b82684,
+  0xfcdbd541, 0x0, 0x3242abf, 0x647d97c, 0x96a9049, 0xc8bd35e, 0xfab272b,
+  0x12c8106f,
+  0x15e21445, 0x18f8b83c, 0x1c0b826a, 0x1f19f97b, 0x2223a4c5, 0x25280c5e,
+  0x2826b928, 0x2b1f34eb,
+  0x2e110a62, 0x30fbc54d, 0x33def287, 0x36ba2014, 0x398cdd32, 0x3c56ba70,
+  0x3f1749b8, 0x41ce1e65,
+  0x447acd50, 0x471cece7, 0x49b41533, 0x4c3fdff4, 0x4ebfe8a5, 0x5133cc94,
+  0x539b2af0, 0x55f5a4d2,
+  0x5842dd54, 0x5a82799a, 0x5cb420e0, 0x5ed77c8a, 0x60ec3830, 0x62f201ac,
+  0x64e88926, 0x66cf8120,
+  0x68a69e81, 0x6a6d98a4, 0x6c242960, 0x6dca0d14, 0x6f5f02b2, 0x70e2cbc6,
+  0x72552c85, 0x73b5ebd1,
+  0x7504d345, 0x7641af3d, 0x776c4edb, 0x78848414, 0x798a23b1, 0x7a7d055b,
+  0x7b5d039e, 0x7c29fbee,
+  0x7ce3ceb2, 0x7d8a5f40, 0x7e1d93ea, 0x7e9d55fc, 0x7f0991c4, 0x7f62368f,
+  0x7fa736b4, 0x7fd8878e,
+  0x7ff62182, 0x7fffffff, 0x7ff62182
+};
+
+/**   
+ * @brief Fast approximation to the trigonometric cosine function for Q31 data.   
+ * @param[in] x Scaled input value in radians.   
+ * @return  cos(x).   
+ *   
+ * The Q31 input value is in the range [0 +0.9999] and is mapped to a radian value in the range [0 2*pi), Here range excludes 2*pi.   
+ */
+
+q31_t arm_cos_q31(
+  q31_t x)
+{
+  q31_t cosVal, in, in2;                         /* Temporary variables for input, output */
+  q31_t wa, wb, wc, wd;                          /* Cubic interpolation coefficients */
+  q31_t a, b, c, d;                              /* Four nearest output values */
+  q31_t *tablePtr;                               /* Pointer to table */
+  q31_t fract, fractCube, fractSquare;           /* Temporary values for fractional values */
+  q31_t oneBy6 = 0x15555555;                     /* Fixed point value of 1/6 */
+  q31_t tableSpacing = TABLE_SPACING_Q31;        /* Table spacing */
+  q31_t temp;                                    /* Temporary variable for intermediate process */
+  int32_t index;                                 /* Index variable */
+
+  in = x;
+
+  /* Calculate the nearest index */
+  index = in / tableSpacing;
+
+  /* Calculate the nearest value of input */
+  in2 = ((q31_t) index) * tableSpacing;
+
+  /* Calculation of fractional value */
+  fract = (in - in2) << 8;
+
+  /* fractSquare = fract * fract */
+  fractSquare = ((q31_t) (((q63_t) fract * fract) >> 32));
+  fractSquare = fractSquare << 1;
+
+  /* fractCube = fract * fract * fract */
+  fractCube = ((q31_t) (((q63_t) fractSquare * fract) >> 32));
+  fractCube = fractCube << 1;
+
+  /* Checking min and max index of table */
+  if(index < 0)
+  {
+    index = 0;
+  }
+  else if(index > 256)
+  {
+    index = 256;
+  }
+
+  /* Initialise table pointer */
+  tablePtr = (q31_t *) & cosTableQ31[index];
+
+  /* Cubic interpolation process */
+  /* Calculation of wa */
+  /* wa = -(oneBy6)*fractCube + (fractSquare >> 1u) - (0x2AAAAAAA)*fract; */
+  wa = ((q31_t) (((q63_t) oneBy6 * fractCube) >> 32));
+  temp = 0x2AAAAAAA;
+  wa = (q31_t) ((((q63_t) wa << 32) + ((q63_t) temp * fract)) >> 32);
+  wa = -(wa << 1u);
+  wa += (fractSquare >> 1u);
+
+  /* Read first nearest value of output from the cos table */
+  a = *tablePtr++;
+
+  /* cosVal = a*wa */
+  cosVal = ((q31_t) (((q63_t) a * wa) >> 32));
+
+  /* q31(1.31) Fixed point value of 1 */
+  temp = 0x7FFFFFFF;
+
+  /* Calculation of wb */
+  wb = ((fractCube >> 1u) - (fractSquare + (fract >> 1u))) + temp;
+  /* Read second nearest value of output from the cos table */
+  b = *tablePtr++;
+
+  /*      cosVal += b*wb */
+  cosVal = (q31_t) ((((q63_t) cosVal << 32) + ((q63_t) b * (wb))) >> 32);
+
+  /* Calculation of wc */
+  wc = -fractCube + fractSquare;
+  wc = (wc >> 1u) + fract;
+  /* Read third nearest values of output value from the cos table */
+  c = *tablePtr++;
+
+  /*      cosVal += c*wc */
+  cosVal = (q31_t) ((((q63_t) cosVal << 32) + ((q63_t) c * (wc))) >> 32);
+
+  /* Calculation of wd */
+  /* wd = (oneBy6)*fractCube - (oneBy6)*fract; */
+  fractCube = fractCube - fract;
+  wd = ((q31_t) (((q63_t) oneBy6 * fractCube) >> 32));
+  wd = (wd << 1u);
+
+  /* Read fourth nearest value of output from the cos table */
+  d = *tablePtr++;
+
+  /* cosVal += d*wd; */
+  cosVal = (q31_t) ((((q63_t) cosVal << 32) + ((q63_t) d * (wd))) >> 32);
+
+
+  /* convert cosVal in 2.30 format to 1.31 format */
+  return (__QADD(cosVal, cosVal));
+
+}
+
+/**    
+ * @} end of cos group    
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sin_f32.c

@@ -0,0 +1,281 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_f32.c    
+*    
+* Description:	Fast sine calculation for floating-point values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFastMath    
+ */
+
+/**    
+ * @defgroup sin Sine    
+ *    
+ * Computes the trigonometric sine function using a combination of table lookup   
+ * and cubic interpolation.  There are separate functions for   
+ * Q15, Q31, and floating-point data types.   
+ * The input to the floating-point version is in radians while the   
+ * fixed-point Q15 and Q31 have a scaled input with the range   
+ * [0 +0.9999] mapping to [0 2*pi), Where range excludes 2*pi.   
+ *   
+ * The implementation is based on table lookup using 256 values together with cubic interpolation.   
+ * The steps used are:   
+ *  -# Calculation of the nearest integer table index   
+ *  -# Fetch the four table values a, b, c, and d     
+ *  -# Compute the fractional portion (fract) of the table index.   
+ *  -# Calculation of wa, wb, wc, wd    
+ *  -# The final result equals <code>a*wa + b*wb + c*wc + d*wd</code>   
+ *   
+ * where   
+ * <pre>    
+ *    a=Table[index-1];    
+ *    b=Table[index+0];    
+ *    c=Table[index+1];    
+ *    d=Table[index+2];    
+ * </pre>   
+ * and   
+ * <pre>    
+ *    wa=-(1/6)*fract.^3 + (1/2)*fract.^2 - (1/3)*fract;    
+ *    wb=(1/2)*fract.^3 - fract.^2 - (1/2)*fract + 1;    
+ *    wc=-(1/2)*fract.^3+(1/2)*fract.^2+fract;    
+ *    wd=(1/6)*fract.^3 - (1/6)*fract;    
+ * </pre>    
+ */
+
+/**    
+ * @addtogroup sin    
+ * @{    
+ */
+
+
+/**   
+ * \par    
+ * Example code for Generation of Floating-point Sin Table:   
+ * tableSize = 256;    
+ * <pre>for(n = -1; n < (tableSize + 1); n++)    
+ * {    
+ *	sinTable[n+1]=sin(2*pi*n/tableSize);    
+ * }</pre>    
+ * \par    
+ * where pi value is  3.14159265358979    
+ */
+
+static const float32_t sinTable[259] = {
+  -0.024541229009628296f, 0.000000000000000000f, 0.024541229009628296f,
+  0.049067676067352295f, 0.073564566671848297f, 0.098017141222953796f,
+  0.122410677373409270f, 0.146730467677116390f,
+  0.170961886644363400f, 0.195090323686599730f, 0.219101235270500180f,
+  0.242980182170867920f, 0.266712754964828490f, 0.290284663438797000f,
+  0.313681751489639280f, 0.336889863014221190f,
+  0.359895050525665280f, 0.382683426141738890f, 0.405241310596466060f,
+  0.427555084228515630f, 0.449611335992813110f, 0.471396744251251220f,
+  0.492898195981979370f, 0.514102756977081300f,
+  0.534997642040252690f, 0.555570244789123540f, 0.575808167457580570f,
+  0.595699310302734380f, 0.615231573581695560f, 0.634393274784088130f,
+  0.653172850608825680f, 0.671558976173400880f,
+  0.689540565013885500f, 0.707106769084930420f, 0.724247097969055180f,
+  0.740951120853424070f, 0.757208824157714840f, 0.773010432720184330f,
+  0.788346409797668460f, 0.803207516670227050f,
+  0.817584812641143800f, 0.831469595432281490f, 0.844853579998016360f,
+  0.857728600502014160f, 0.870086967945098880f, 0.881921291351318360f,
+  0.893224298954010010f, 0.903989315032958980f,
+  0.914209783077239990f, 0.923879504203796390f, 0.932992815971374510f,
+  0.941544055938720700f, 0.949528157711029050f, 0.956940352916717530f,
+  0.963776051998138430f, 0.970031261444091800f,
+  0.975702106952667240f, 0.980785250663757320f, 0.985277652740478520f,
+  0.989176511764526370f, 0.992479562759399410f, 0.995184719562530520f,
+  0.997290432453155520f, 0.998795449733734130f,
+  0.999698817729949950f, 1.000000000000000000f, 0.999698817729949950f,
+  0.998795449733734130f, 0.997290432453155520f, 0.995184719562530520f,
+  0.992479562759399410f, 0.989176511764526370f,
+  0.985277652740478520f, 0.980785250663757320f, 0.975702106952667240f,
+  0.970031261444091800f, 0.963776051998138430f, 0.956940352916717530f,
+  0.949528157711029050f, 0.941544055938720700f,
+  0.932992815971374510f, 0.923879504203796390f, 0.914209783077239990f,
+  0.903989315032958980f, 0.893224298954010010f, 0.881921291351318360f,
+  0.870086967945098880f, 0.857728600502014160f,
+  0.844853579998016360f, 0.831469595432281490f, 0.817584812641143800f,
+  0.803207516670227050f, 0.788346409797668460f, 0.773010432720184330f,
+  0.757208824157714840f, 0.740951120853424070f,
+  0.724247097969055180f, 0.707106769084930420f, 0.689540565013885500f,
+  0.671558976173400880f, 0.653172850608825680f, 0.634393274784088130f,
+  0.615231573581695560f, 0.595699310302734380f,
+  0.575808167457580570f, 0.555570244789123540f, 0.534997642040252690f,
+  0.514102756977081300f, 0.492898195981979370f, 0.471396744251251220f,
+  0.449611335992813110f, 0.427555084228515630f,
+  0.405241310596466060f, 0.382683426141738890f, 0.359895050525665280f,
+  0.336889863014221190f, 0.313681751489639280f, 0.290284663438797000f,
+  0.266712754964828490f, 0.242980182170867920f,
+  0.219101235270500180f, 0.195090323686599730f, 0.170961886644363400f,
+  0.146730467677116390f, 0.122410677373409270f, 0.098017141222953796f,
+  0.073564566671848297f, 0.049067676067352295f,
+  0.024541229009628296f, 0.000000000000000122f, -0.024541229009628296f,
+  -0.049067676067352295f, -0.073564566671848297f, -0.098017141222953796f,
+  -0.122410677373409270f, -0.146730467677116390f,
+  -0.170961886644363400f, -0.195090323686599730f, -0.219101235270500180f,
+  -0.242980182170867920f, -0.266712754964828490f, -0.290284663438797000f,
+  -0.313681751489639280f, -0.336889863014221190f,
+  -0.359895050525665280f, -0.382683426141738890f, -0.405241310596466060f,
+  -0.427555084228515630f, -0.449611335992813110f, -0.471396744251251220f,
+  -0.492898195981979370f, -0.514102756977081300f,
+  -0.534997642040252690f, -0.555570244789123540f, -0.575808167457580570f,
+  -0.595699310302734380f, -0.615231573581695560f, -0.634393274784088130f,
+  -0.653172850608825680f, -0.671558976173400880f,
+  -0.689540565013885500f, -0.707106769084930420f, -0.724247097969055180f,
+  -0.740951120853424070f, -0.757208824157714840f, -0.773010432720184330f,
+  -0.788346409797668460f, -0.803207516670227050f,
+  -0.817584812641143800f, -0.831469595432281490f, -0.844853579998016360f,
+  -0.857728600502014160f, -0.870086967945098880f, -0.881921291351318360f,
+  -0.893224298954010010f, -0.903989315032958980f,
+  -0.914209783077239990f, -0.923879504203796390f, -0.932992815971374510f,
+  -0.941544055938720700f, -0.949528157711029050f, -0.956940352916717530f,
+  -0.963776051998138430f, -0.970031261444091800f,
+  -0.975702106952667240f, -0.980785250663757320f, -0.985277652740478520f,
+  -0.989176511764526370f, -0.992479562759399410f, -0.995184719562530520f,
+  -0.997290432453155520f, -0.998795449733734130f,
+  -0.999698817729949950f, -1.000000000000000000f, -0.999698817729949950f,
+  -0.998795449733734130f, -0.997290432453155520f, -0.995184719562530520f,
+  -0.992479562759399410f, -0.989176511764526370f,
+  -0.985277652740478520f, -0.980785250663757320f, -0.975702106952667240f,
+  -0.970031261444091800f, -0.963776051998138430f, -0.956940352916717530f,
+  -0.949528157711029050f, -0.941544055938720700f,
+  -0.932992815971374510f, -0.923879504203796390f, -0.914209783077239990f,
+  -0.903989315032958980f, -0.893224298954010010f, -0.881921291351318360f,
+  -0.870086967945098880f, -0.857728600502014160f,
+  -0.844853579998016360f, -0.831469595432281490f, -0.817584812641143800f,
+  -0.803207516670227050f, -0.788346409797668460f, -0.773010432720184330f,
+  -0.757208824157714840f, -0.740951120853424070f,
+  -0.724247097969055180f, -0.707106769084930420f, -0.689540565013885500f,
+  -0.671558976173400880f, -0.653172850608825680f, -0.634393274784088130f,
+  -0.615231573581695560f, -0.595699310302734380f,
+  -0.575808167457580570f, -0.555570244789123540f, -0.534997642040252690f,
+  -0.514102756977081300f, -0.492898195981979370f, -0.471396744251251220f,
+  -0.449611335992813110f, -0.427555084228515630f,
+  -0.405241310596466060f, -0.382683426141738890f, -0.359895050525665280f,
+  -0.336889863014221190f, -0.313681751489639280f, -0.290284663438797000f,
+  -0.266712754964828490f, -0.242980182170867920f,
+  -0.219101235270500180f, -0.195090323686599730f, -0.170961886644363400f,
+  -0.146730467677116390f, -0.122410677373409270f, -0.098017141222953796f,
+  -0.073564566671848297f, -0.049067676067352295f,
+  -0.024541229009628296f, -0.000000000000000245f, 0.024541229009628296f
+};
+
+
+/**   
+ * @brief  Fast approximation to the trigonometric sine function for floating-point data.   
+ * @param[in] x input value in radians.   
+ * @return  sin(x).   
+ */
+
+float32_t arm_sin_f32(
+  float32_t x)
+{
+  float32_t sinVal, fract, in;                   /* Temporary variables for input, output */
+  int32_t index;                                 /* Index variable */
+  uint32_t tableSize = (uint32_t) TABLE_SIZE;    /* Initialise tablesize */
+  float32_t wa, wb, wc, wd;                      /* Cubic interpolation coefficients */
+  float32_t a, b, c, d;                          /* Four nearest output values */
+  float32_t *tablePtr;                           /* Pointer to table */
+  int32_t n;
+  float32_t fractsq, fractby2, fractby6, fractby3, fractsqby2;
+  float32_t oneminusfractby2;
+  float32_t frby2xfrsq, frby6xfrsq;
+
+  /* input x is in radians */
+  /* Scale the input to [0 1] range from [0 2*PI] , divide input by 2*pi */
+  in = x * 0.159154943092f;
+
+  /* Calculation of floor value of input */
+  n = (int32_t) in;
+
+  /* Make negative values towards -infinity */
+  if(x < 0.0f)
+  {
+    n = n - 1;
+  }
+
+  /* Map input value to [0 1] */
+  in = in - (float32_t) n;
+
+  /* Calculation of index of the table */
+  index = (uint32_t) (tableSize * in);
+
+  /* fractional value calculation */
+  fract = ((float32_t) tableSize * in) - (float32_t) index;
+
+  /* Checking min and max index of table */
+  if(index < 0)
+  {
+    index = 0;
+  }
+  else if(index > 256)
+  {
+    index = 256;
+  }
+
+  /* Initialise table pointer */
+  tablePtr = (float32_t *) & sinTable[index];
+
+  /* Read four nearest values of input value from the sin table */
+  a = tablePtr[0];
+  b = tablePtr[1];
+  c = tablePtr[2];
+  d = tablePtr[3];
+
+  /* Cubic interpolation process */
+  fractsq = fract * fract;
+  fractby2 = fract * 0.5f;
+  fractby6 = fract * 0.166666667f;
+  fractby3 = fract * 0.3333333333333f;
+  fractsqby2 = fractsq * 0.5f;
+  frby2xfrsq = (fractby2) * fractsq;
+  frby6xfrsq = (fractby6) * fractsq;
+  oneminusfractby2 = 1.0f - fractby2;
+  wb = fractsqby2 - fractby3;
+  wc = (fractsqby2 + fract);
+  wa = wb - frby6xfrsq;
+  wb = frby2xfrsq - fractsq;
+  sinVal = wa * a;
+  wc = wc - frby2xfrsq;
+  wd = (frby6xfrsq) - fractby6;
+  wb = wb + oneminusfractby2;
+
+  /* Calculate sin value */
+  sinVal = (sinVal + (b * wb)) + ((c * wc) + (d * wd));
+
+  /* Return the output value */
+  return (sinVal);
+
+}
+
+/**    
+ * @} end of sin group    
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sin_q15.c

@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_q15.c    
+*    
+* Description:	Fast sine calculation for Q15 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFastMath    
+ */
+
+ /**    
+ * @addtogroup sin    
+ * @{    
+ */
+
+
+/**    
+ * \par    
+ * Example code for Generation of Q15 Sin Table:   
+ * \par    
+ * <pre>tableSize = 256;    
+ * for(n = -1; n < (tableSize + 1); n++)    
+ * {    
+ *	sinTable[n+1]=sin(2*pi*n/tableSize);    
+ * } </pre>    
+ * where pi value is  3.14159265358979    
+ * \par    
+ * Convert Floating point to Q15(Fixed point):    
+ *	(sinTable[i] * pow(2, 15))    
+ * \par    
+ * rounding to nearest integer is done    
+ * 	sinTable[i] += (sinTable[i] > 0 ? 0.5 :-0.5);    
+ */
+
+
+static const q15_t sinTableQ15[259] = {
+  0xfcdc, 0x0, 0x324, 0x648, 0x96b, 0xc8c, 0xfab, 0x12c8,
+  0x15e2, 0x18f9, 0x1c0c, 0x1f1a, 0x2224, 0x2528, 0x2827, 0x2b1f,
+  0x2e11, 0x30fc, 0x33df, 0x36ba, 0x398d, 0x3c57, 0x3f17, 0x41ce,
+  0x447b, 0x471d, 0x49b4, 0x4c40, 0x4ec0, 0x5134, 0x539b, 0x55f6,
+  0x5843, 0x5a82, 0x5cb4, 0x5ed7, 0x60ec, 0x62f2, 0x64e9, 0x66d0,
+  0x68a7, 0x6a6e, 0x6c24, 0x6dca, 0x6f5f, 0x70e3, 0x7255, 0x73b6,
+  0x7505, 0x7642, 0x776c, 0x7885, 0x798a, 0x7a7d, 0x7b5d, 0x7c2a,
+  0x7ce4, 0x7d8a, 0x7e1e, 0x7e9d, 0x7f0a, 0x7f62, 0x7fa7, 0x7fd9,
+  0x7ff6, 0x7fff, 0x7ff6, 0x7fd9, 0x7fa7, 0x7f62, 0x7f0a, 0x7e9d,
+  0x7e1e, 0x7d8a, 0x7ce4, 0x7c2a, 0x7b5d, 0x7a7d, 0x798a, 0x7885,
+  0x776c, 0x7642, 0x7505, 0x73b6, 0x7255, 0x70e3, 0x6f5f, 0x6dca,
+  0x6c24, 0x6a6e, 0x68a7, 0x66d0, 0x64e9, 0x62f2, 0x60ec, 0x5ed7,
+  0x5cb4, 0x5a82, 0x5843, 0x55f6, 0x539b, 0x5134, 0x4ec0, 0x4c40,
+  0x49b4, 0x471d, 0x447b, 0x41ce, 0x3f17, 0x3c57, 0x398d, 0x36ba,
+  0x33df, 0x30fc, 0x2e11, 0x2b1f, 0x2827, 0x2528, 0x2224, 0x1f1a,
+  0x1c0c, 0x18f9, 0x15e2, 0x12c8, 0xfab, 0xc8c, 0x96b, 0x648,
+  0x324, 0x0, 0xfcdc, 0xf9b8, 0xf695, 0xf374, 0xf055, 0xed38,
+  0xea1e, 0xe707, 0xe3f4, 0xe0e6, 0xdddc, 0xdad8, 0xd7d9, 0xd4e1,
+  0xd1ef, 0xcf04, 0xcc21, 0xc946, 0xc673, 0xc3a9, 0xc0e9, 0xbe32,
+  0xbb85, 0xb8e3, 0xb64c, 0xb3c0, 0xb140, 0xaecc, 0xac65, 0xaa0a,
+  0xa7bd, 0xa57e, 0xa34c, 0xa129, 0x9f14, 0x9d0e, 0x9b17, 0x9930,
+  0x9759, 0x9592, 0x93dc, 0x9236, 0x90a1, 0x8f1d, 0x8dab, 0x8c4a,
+  0x8afb, 0x89be, 0x8894, 0x877b, 0x8676, 0x8583, 0x84a3, 0x83d6,
+  0x831c, 0x8276, 0x81e2, 0x8163, 0x80f6, 0x809e, 0x8059, 0x8027,
+  0x800a, 0x8000, 0x800a, 0x8027, 0x8059, 0x809e, 0x80f6, 0x8163,
+  0x81e2, 0x8276, 0x831c, 0x83d6, 0x84a3, 0x8583, 0x8676, 0x877b,
+  0x8894, 0x89be, 0x8afb, 0x8c4a, 0x8dab, 0x8f1d, 0x90a1, 0x9236,
+  0x93dc, 0x9592, 0x9759, 0x9930, 0x9b17, 0x9d0e, 0x9f14, 0xa129,
+  0xa34c, 0xa57e, 0xa7bd, 0xaa0a, 0xac65, 0xaecc, 0xb140, 0xb3c0,
+  0xb64c, 0xb8e3, 0xbb85, 0xbe32, 0xc0e9, 0xc3a9, 0xc673, 0xc946,
+  0xcc21, 0xcf04, 0xd1ef, 0xd4e1, 0xd7d9, 0xdad8, 0xdddc, 0xe0e6,
+  0xe3f4, 0xe707, 0xea1e, 0xed38, 0xf055, 0xf374, 0xf695, 0xf9b8,
+  0xfcdc, 0x0, 0x324
+};
+
+
+/**   
+ * @brief Fast approximation to the trigonometric sine function for Q15 data.   
+ * @param[in] x Scaled input value in radians.   
+ * @return  sin(x).   
+ *   
+ * The Q15 input value is in the range [0 +0.9999] and is mapped to a radian value in the range [0 2*pi), Here range excludes 2*pi.   
+ */
+
+q15_t arm_sin_q15(
+  q15_t x)
+{
+  q31_t sinVal;                                  /* Temporary variables output */
+  q15_t *tablePtr;                               /* Pointer to table */
+  q15_t fract, in, in2;                          /* Temporary variables for input, output */
+  q31_t wa, wb, wc, wd;                          /* Cubic interpolation coefficients */
+  q15_t a, b, c, d;                              /* Four nearest output values */
+  q15_t fractCube, fractSquare;                  /* Temporary values for fractional value */
+  q15_t oneBy6 = 0x1555;                         /* Fixed point value of 1/6 */
+  q15_t tableSpacing = TABLE_SPACING_Q15;        /* Table spacing */
+  int32_t index;                                 /* Index variable */
+
+  in = x;
+
+  /* Calculate the nearest index */
+  index = (int32_t) in / tableSpacing;
+
+  /* Calculate the nearest value of input */
+  in2 = (q15_t) ((index) * tableSpacing);
+
+  /* Calculation of fractional value */
+  fract = (in - in2) << 8;
+
+  /* fractSquare = fract * fract */
+  fractSquare = (q15_t) ((fract * fract) >> 15);
+
+  /* fractCube = fract * fract * fract */
+  fractCube = (q15_t) ((fractSquare * fract) >> 15);
+
+  /* Checking min and max index of table */
+  if(index < 0)
+  {
+    index = 0;
+  }
+  else if(index > 256)
+  {
+    index = 256;
+  }
+
+  /* Initialise table pointer */
+  tablePtr = (q15_t *) & sinTableQ15[index];
+
+  /* Cubic interpolation process */
+  /* Calculation of wa */
+  /* wa = -(oneBy6)*fractCube + (fractSquare >> 1u) - (0x2AAA)*fract; */
+  wa = (q31_t) oneBy6 *fractCube;
+  wa += (q31_t) 0x2AAA *fract;
+  wa = -(wa >> 15);
+  wa += ((q31_t) fractSquare >> 1u);
+
+  /* Read first nearest value of output from the sin table */
+  a = *tablePtr++;
+
+  /* sinVal = a * wa */
+  sinVal = a * wa;
+
+  /* Calculation of wb */
+  wb = (((q31_t) fractCube >> 1u) - (q31_t) fractSquare) -
+    (((q31_t) fract >> 1u) - 0x7FFF);
+
+  /* Read second nearest value of output from the sin table */
+  b = *tablePtr++;
+
+  /*      sinVal += b*wb */
+  sinVal += b * wb;
+
+
+  /* Calculation of wc */
+  wc = -(q31_t) fractCube + fractSquare;
+  wc = (wc >> 1u) + fract;
+
+  /* Read third nearest value of output from the sin table */
+  c = *tablePtr++;
+
+  /* sinVal += c*wc */
+  sinVal += c * wc;
+
+  /* Calculation of wd */
+  /* wd = (oneBy6)*fractCube - (oneBy6)*fract; */
+  fractCube = fractCube - fract;
+  wd = ((q15_t) (((q31_t) oneBy6 * fractCube) >> 15));
+
+  /* Read fourth nearest value of output from the sin table */
+  d = *tablePtr++;
+
+  /* sinVal += d*wd; */
+  sinVal += d * wd;
+
+  /* Convert output value in 1.15(q15) format and saturate */
+  sinVal = __SSAT((sinVal >> 15), 16);
+
+  /* Return the output value in 1.15(q15) format */
+  return ((q15_t) sinVal);
+
+}
+
+/**    
+ * @} end of sin group    
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sin_q31.c

@@ -0,0 +1,240 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_q31.c    
+*    
+* Description:	Fast sine calculation for Q31 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFastMath    
+ */
+
+ /**    
+ * @addtogroup sin    
+ * @{    
+ */
+
+/**   
+ * \par    
+ * Tables generated are in Q31(1.31 Fixed point format)    
+ * Generation of sin values in floating point:    
+ * <pre>tableSize = 256;      
+ * for(n = -1; n < (tableSize + 1); n++)    
+ * {    
+ *	sinTable[n+1]= sin(2*pi*n/tableSize);    
+ * } </pre>    
+ * where pi value is  3.14159265358979    
+ * \par    
+ * Convert Floating point to Q31(Fixed point):    
+ *	(sinTable[i] * pow(2, 31))    
+ * \par    
+ * rounding to nearest integer is done    
+ * 	sinTable[i] += (sinTable[i] > 0 ? 0.5 :-0.5);    
+ */
+
+static const q31_t sinTableQ31[259] = {
+  0xfcdbd541, 0x0, 0x3242abf, 0x647d97c, 0x96a9049, 0xc8bd35e, 0xfab272b,
+  0x12c8106f,
+  0x15e21445, 0x18f8b83c, 0x1c0b826a, 0x1f19f97b, 0x2223a4c5, 0x25280c5e,
+  0x2826b928, 0x2b1f34eb,
+  0x2e110a62, 0x30fbc54d, 0x33def287, 0x36ba2014, 0x398cdd32, 0x3c56ba70,
+  0x3f1749b8, 0x41ce1e65,
+  0x447acd50, 0x471cece7, 0x49b41533, 0x4c3fdff4, 0x4ebfe8a5, 0x5133cc94,
+  0x539b2af0, 0x55f5a4d2,
+  0x5842dd54, 0x5a82799a, 0x5cb420e0, 0x5ed77c8a, 0x60ec3830, 0x62f201ac,
+  0x64e88926, 0x66cf8120,
+  0x68a69e81, 0x6a6d98a4, 0x6c242960, 0x6dca0d14, 0x6f5f02b2, 0x70e2cbc6,
+  0x72552c85, 0x73b5ebd1,
+  0x7504d345, 0x7641af3d, 0x776c4edb, 0x78848414, 0x798a23b1, 0x7a7d055b,
+  0x7b5d039e, 0x7c29fbee,
+  0x7ce3ceb2, 0x7d8a5f40, 0x7e1d93ea, 0x7e9d55fc, 0x7f0991c4, 0x7f62368f,
+  0x7fa736b4, 0x7fd8878e,
+  0x7ff62182, 0x7fffffff, 0x7ff62182, 0x7fd8878e, 0x7fa736b4, 0x7f62368f,
+  0x7f0991c4, 0x7e9d55fc,
+  0x7e1d93ea, 0x7d8a5f40, 0x7ce3ceb2, 0x7c29fbee, 0x7b5d039e, 0x7a7d055b,
+  0x798a23b1, 0x78848414,
+  0x776c4edb, 0x7641af3d, 0x7504d345, 0x73b5ebd1, 0x72552c85, 0x70e2cbc6,
+  0x6f5f02b2, 0x6dca0d14,
+  0x6c242960, 0x6a6d98a4, 0x68a69e81, 0x66cf8120, 0x64e88926, 0x62f201ac,
+  0x60ec3830, 0x5ed77c8a,
+  0x5cb420e0, 0x5a82799a, 0x5842dd54, 0x55f5a4d2, 0x539b2af0, 0x5133cc94,
+  0x4ebfe8a5, 0x4c3fdff4,
+  0x49b41533, 0x471cece7, 0x447acd50, 0x41ce1e65, 0x3f1749b8, 0x3c56ba70,
+  0x398cdd32, 0x36ba2014,
+  0x33def287, 0x30fbc54d, 0x2e110a62, 0x2b1f34eb, 0x2826b928, 0x25280c5e,
+  0x2223a4c5, 0x1f19f97b,
+  0x1c0b826a, 0x18f8b83c, 0x15e21445, 0x12c8106f, 0xfab272b, 0xc8bd35e,
+  0x96a9049, 0x647d97c,
+  0x3242abf, 0x0, 0xfcdbd541, 0xf9b82684, 0xf6956fb7, 0xf3742ca2, 0xf054d8d5,
+  0xed37ef91,
+  0xea1debbb, 0xe70747c4, 0xe3f47d96, 0xe0e60685, 0xdddc5b3b, 0xdad7f3a2,
+  0xd7d946d8, 0xd4e0cb15,
+  0xd1eef59e, 0xcf043ab3, 0xcc210d79, 0xc945dfec, 0xc67322ce, 0xc3a94590,
+  0xc0e8b648, 0xbe31e19b,
+  0xbb8532b0, 0xb8e31319, 0xb64beacd, 0xb3c0200c, 0xb140175b, 0xaecc336c,
+  0xac64d510, 0xaa0a5b2e,
+  0xa7bd22ac, 0xa57d8666, 0xa34bdf20, 0xa1288376, 0x9f13c7d0, 0x9d0dfe54,
+  0x9b1776da, 0x99307ee0,
+  0x9759617f, 0x9592675c, 0x93dbd6a0, 0x9235f2ec, 0x90a0fd4e, 0x8f1d343a,
+  0x8daad37b, 0x8c4a142f,
+  0x8afb2cbb, 0x89be50c3, 0x8893b125, 0x877b7bec, 0x8675dc4f, 0x8582faa5,
+  0x84a2fc62, 0x83d60412,
+  0x831c314e, 0x8275a0c0, 0x81e26c16, 0x8162aa04, 0x80f66e3c, 0x809dc971,
+  0x8058c94c, 0x80277872,
+  0x8009de7e, 0x80000000, 0x8009de7e, 0x80277872, 0x8058c94c, 0x809dc971,
+  0x80f66e3c, 0x8162aa04,
+  0x81e26c16, 0x8275a0c0, 0x831c314e, 0x83d60412, 0x84a2fc62, 0x8582faa5,
+  0x8675dc4f, 0x877b7bec,
+  0x8893b125, 0x89be50c3, 0x8afb2cbb, 0x8c4a142f, 0x8daad37b, 0x8f1d343a,
+  0x90a0fd4e, 0x9235f2ec,
+  0x93dbd6a0, 0x9592675c, 0x9759617f, 0x99307ee0, 0x9b1776da, 0x9d0dfe54,
+  0x9f13c7d0, 0xa1288376,
+  0xa34bdf20, 0xa57d8666, 0xa7bd22ac, 0xaa0a5b2e, 0xac64d510, 0xaecc336c,
+  0xb140175b, 0xb3c0200c,
+  0xb64beacd, 0xb8e31319, 0xbb8532b0, 0xbe31e19b, 0xc0e8b648, 0xc3a94590,
+  0xc67322ce, 0xc945dfec,
+  0xcc210d79, 0xcf043ab3, 0xd1eef59e, 0xd4e0cb15, 0xd7d946d8, 0xdad7f3a2,
+  0xdddc5b3b, 0xe0e60685,
+  0xe3f47d96, 0xe70747c4, 0xea1debbb, 0xed37ef91, 0xf054d8d5, 0xf3742ca2,
+  0xf6956fb7, 0xf9b82684,
+  0xfcdbd541, 0x0, 0x3242abf
+};
+
+
+/**   
+ * @brief Fast approximation to the trigonometric sine function for Q31 data.   
+ * @param[in] x Scaled input value in radians.   
+ * @return  sin(x).   
+ *   
+ * The Q31 input value is in the range [0 +0.9999] and is mapped to a radian value in the range [0 2*pi), Here range excludes 2*pi.   
+ */
+
+q31_t arm_sin_q31(
+  q31_t x)
+{
+  q31_t sinVal, in, in2;                         /* Temporary variables for input, output */
+  int32_t index;                                 /* Index variables */
+  q31_t wa, wb, wc, wd;                          /* Cubic interpolation coefficients */
+  q31_t a, b, c, d;                              /* Four nearest output values */
+  q31_t *tablePtr;                               /* Pointer to table */
+  q31_t fract, fractCube, fractSquare;           /* Temporary values for fractional values */
+  q31_t oneBy6 = 0x15555555;                     /* Fixed point value of 1/6 */
+  q31_t tableSpacing = TABLE_SPACING_Q31;        /* Table spacing */
+  q31_t temp;                                    /* Temporary variable for intermediate process */
+
+  in = x;
+
+  /* Calculate the nearest index */
+  index = (uint32_t) in / (uint32_t) tableSpacing;
+
+  /* Calculate the nearest value of input */
+  in2 = (q31_t) index *tableSpacing;
+
+  /* Calculation of fractional value */
+  fract = (in - in2) << 8;
+
+  /* fractSquare = fract * fract */
+  fractSquare = ((q31_t) (((q63_t) fract * fract) >> 32));
+  fractSquare = fractSquare << 1;
+
+  /* fractCube = fract * fract * fract */
+  fractCube = ((q31_t) (((q63_t) fractSquare * fract) >> 32));
+  fractCube = fractCube << 1;
+
+  /* Checking min and max index of table */
+  if(index < 0)
+  {
+    index = 0;
+  }
+  else if(index > 256)
+  {
+    index = 256;
+  }
+
+  /* Initialise table pointer */
+  tablePtr = (q31_t *) & sinTableQ31[index];
+
+  /* Cubic interpolation process */
+  /* Calculation of wa */
+  /* wa = -(oneBy6)*fractCube + (fractSquare >> 1u) - (0x2AAAAAAA)*fract; */
+  wa = ((q31_t) (((q63_t) oneBy6 * fractCube) >> 32));
+  temp = 0x2AAAAAAA;
+  wa = (q31_t) ((((q63_t) wa << 32) + ((q63_t) temp * fract)) >> 32);
+  wa = -(wa << 1u);
+  wa += (fractSquare >> 1u);
+
+  /* Read first nearest value of output from the sin table */
+  a = *tablePtr++;
+
+  /* sinVal = a*wa */
+  sinVal = ((q31_t) (((q63_t) a * wa) >> 32));
+
+  /* q31(1.31) Fixed point value of 1 */
+  temp = 0x7FFFFFFF;
+
+  /* Calculation of wb */
+  wb = ((fractCube >> 1u) - (fractSquare + (fract >> 1u))) + temp;
+
+  /* Read second nearest value of output from the sin table */
+  b = *tablePtr++;
+
+  /*  sinVal += b*wb */
+  sinVal = (q31_t) ((((q63_t) sinVal << 32) + (q63_t) b * (wb)) >> 32);
+
+  /* Calculation of wc */
+  wc = -fractCube + fractSquare;
+  wc = (wc >> 1u) + fract;
+
+  /* Read third nearest value of output from the sin table */
+  c = *tablePtr++;
+
+  /*      sinVal += c*wc */
+  sinVal = (q31_t) ((((q63_t) sinVal << 32) + ((q63_t) c * wc)) >> 32);
+
+  /* Calculation of wd */
+  /* wd = (oneBy6) * fractCube - (oneBy6) * fract; */
+  fractCube = fractCube - fract;
+  wd = ((q31_t) (((q63_t) oneBy6 * fractCube) >> 32));
+  wd = (wd << 1u);
+
+  /* Read fourth nearest value of output from the sin table */
+  d = *tablePtr++;
+
+  /* sinVal += d*wd; */
+  sinVal = (q31_t) ((((q63_t) sinVal << 32) + ((q63_t) d * wd)) >> 32);
+
+  /* convert sinVal in 2.30 format to 1.31 format */
+  return (__QADD(sinVal, sinVal));
+
+}
+
+/**    
+ * @} end of sin group    
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sqrt_q15.c

@@ -0,0 +1,131 @@
+/* ----------------------------------------------------------------------     
+* Copyright (C) 2011 ARM Limited. All rights reserved.  
+*     
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*     
+* Project:      CMSIS DSP Library  
+* Title:		arm_sqrt_q15.c     
+*     
+* Description:	Q15 square root function.    
+*     
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+* 
+* Version 1.0.0 2011/03/08 
+*     Alpha release. 
+* 
+* Version 1.0.1 2011/09/30 
+*     Beta release.  
+*     
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+
+/**     
+ * @ingroup groupFastMath     
+ */
+
+/**     
+ * @addtogroup SQRT     
+ * @{     
+ */
+
+  /**    
+   * @brief  Q15 square root function.    
+   * @param[in]   in     input value.  The range of the input value is [0 +1) or 0x0000 to 0x7FFF.    
+   * @param[out]  *pOut  square root of input value.    
+   * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if    
+   * <code>in</code> is negative value and returns zero output for negative values.    
+   */
+
+arm_status arm_sqrt_q15(
+  q15_t in,
+  q15_t * pOut)
+{
+  q15_t number, temp1, var1, signBits1, half;
+  q31_t bits_val1;
+  float32_t temp_float1;
+
+  number = in;
+
+  /* If the input is a positive number then compute the signBits. */
+  if(number > 0)
+  {
+    signBits1 = __CLZ(number) - 17;
+
+    /* Shift by the number of signBits1 */
+    if((signBits1 % 2) == 0)
+    {
+      number = number << signBits1;
+    }
+    else
+    {
+      number = number << (signBits1 - 1);
+    }
+
+    /* Calculate half value of the number */
+    half = number >> 1;
+    /* Store the number for later use */
+    temp1 = number;
+
+    /*Convert to float */
+    temp_float1 = number * 3.051757812500000e-005f;
+    /*Store as integer */
+    bits_val1 = *(int *) &temp_float1;
+    /* Subtract the shifted value from the magic number to give intial guess */
+    bits_val1 = 0x5f3759df - (bits_val1 >> 1);  // gives initial guess  
+    /* Store as float */
+    temp_float1 = *(float *) &bits_val1;
+    /* Convert to integer format */
+    var1 = (q31_t) (temp_float1 * 16384);
+
+    /* 1st iteration */
+    var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
+                                     ((q15_t)
+                                      ((((q15_t)
+                                         (((q31_t) var1 * var1) >> 15)) *
+                                        (q31_t) half) >> 15))) >> 15)) << 2;
+    /* 2nd iteration */
+    var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
+                                     ((q15_t)
+                                      ((((q15_t)
+                                         (((q31_t) var1 * var1) >> 15)) *
+                                        (q31_t) half) >> 15))) >> 15)) << 2;
+    /* 3rd iteration */
+    var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
+                                     ((q15_t)
+                                      ((((q15_t)
+                                         (((q31_t) var1 * var1) >> 15)) *
+                                        (q31_t) half) >> 15))) >> 15)) << 2;
+
+    /* Multiply the inverse square root with the original value */
+    var1 = ((q15_t) (((q31_t) temp1 * var1) >> 15)) << 1;
+
+    /* Shift the output down accordingly */
+    if((signBits1 % 2) == 0)
+    {
+      var1 = var1 >> (signBits1 / 2);
+    }
+    else
+    {
+      var1 = var1 >> ((signBits1 - 1) / 2);
+    }
+    *pOut = var1;
+
+    return (ARM_MATH_SUCCESS);
+  }
+  /* If the number is a negative number then store zero as its square root value */
+  else
+  {
+    *pOut = 0;
+    return (ARM_MATH_ARGUMENT_ERROR);
+  }
+}
+
+/**     
+ * @} end of SQRT group     
+ */

libs/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sqrt_q31.c

@@ -0,0 +1,129 @@
+/* ----------------------------------------------------------------------     
+* Copyright (C) 2011 ARM Limited. All rights reserved.  
+*     
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*     
+* Project:      CMSIS DSP Library  
+* Title:		arm_sqrt_q31.c     
+*     
+* Description:	Q31 square root function.    
+*     
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+* 
+* Version 1.0.0 2011/03/08 
+*     Alpha release. 
+* 
+* Version 1.0.1 2011/09/30 
+*     Beta release.  
+*     
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**     
+ * @ingroup groupFastMath     
+ */
+
+/**     
+ * @addtogroup SQRT     
+ * @{     
+ */
+
+/**    
+ * @brief Q31 square root function.    
+ * @param[in]   in    input value.  The range of the input value is [0 +1) or 0x00000000 to 0x7FFFFFFF.    
+ * @param[out]  *pOut square root of input value.    
+ * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if    
+ * <code>in</code> is negative value and returns zero output for negative values.    
+ */
+
+arm_status arm_sqrt_q31(
+  q31_t in,
+  q31_t * pOut)
+{
+  q31_t number, temp1, bits_val1, var1, signBits1, half;
+  float32_t temp_float1;
+
+  number = in;
+
+  /* If the input is a positive number then compute the signBits. */
+  if(number > 0)
+  {
+    signBits1 = __CLZ(number) - 1;
+
+    /* Shift by the number of signBits1 */
+    if((signBits1 % 2) == 0)
+    {
+      number = number << signBits1;
+    }
+    else
+    {
+      number = number << (signBits1 - 1);
+    }
+
+    /* Calculate half value of the number */
+    half = number >> 1;
+    /* Store the number for later use */
+    temp1 = number;
+
+    /*Convert to float */
+    temp_float1 = number * 4.6566128731e-010f;
+    /*Store as integer */
+    bits_val1 = *(int *) &temp_float1;
+    /* Subtract the shifted value from the magic number to give intial guess */
+    bits_val1 = 0x5f3759df - (bits_val1 >> 1);  // gives initial guess  
+    /* Store as float */
+    temp_float1 = *(float *) &bits_val1;
+    /* Convert to integer format */
+    var1 = (q31_t) (temp_float1 * 1073741824);
+
+    /* 1st iteration */
+    var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
+                                     ((q31_t)
+                                      ((((q31_t)
+                                         (((q63_t) var1 * var1) >> 31)) *
+                                        (q63_t) half) >> 31))) >> 31)) << 2;
+    /* 2nd iteration */
+    var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
+                                     ((q31_t)
+                                      ((((q31_t)
+                                         (((q63_t) var1 * var1) >> 31)) *
+                                        (q63_t) half) >> 31))) >> 31)) << 2;
+    /* 3rd iteration */
+    var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
+                                     ((q31_t)
+                                      ((((q31_t)
+                                         (((q63_t) var1 * var1) >> 31)) *
+                                        (q63_t) half) >> 31))) >> 31)) << 2;
+
+    /* Multiply the inverse square root with the original value */
+    var1 = ((q31_t) (((q63_t) temp1 * var1) >> 31)) << 1;
+
+    /* Shift the output down accordingly */
+    if((signBits1 % 2) == 0)
+    {
+      var1 = var1 >> (signBits1 / 2);
+    }
+    else
+    {
+      var1 = var1 >> ((signBits1 - 1) / 2);
+    }
+    *pOut = var1;
+
+    return (ARM_MATH_SUCCESS);
+  }
+  /* If the number is a negative number then store zero as its square root value */
+  else
+  {
+    *pOut = 0;
+    return (ARM_MATH_ARGUMENT_ERROR);
+  }
+}
+
+/**     
+ * @} end of SQRT group     
+ */

libs/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_32x64_init_q31.c

@@ -0,0 +1,105 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_32x64_init_q31.c    
+*    
+* Description:	High precision Q31 Biquad cascade filter initialization function.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1_32x64    
+ * @{    
+ */
+
+/**    
+ * @details    
+ *    
+ * @param[in,out] *S           	points to an instance of the high precision Q31 Biquad cascade filter structure.    
+ * @param[in]     numStages     number of 2nd order stages in the filter.    
+ * @param[in]     *pCoeffs      points to the filter coefficients.    
+ * @param[in]     *pState       points to the state buffer.    
+ * @param[in]     postShift     Shift to be applied after the accumulator.  Varies according to the coefficients format.    
+ * @return        none    
+ *    
+ * <b>Coefficient and State Ordering:</b>    
+ *    
+ * \par    
+ * The coefficients are stored in the array <code>pCoeffs</code> in the following order:    
+ * <pre>    
+ *     {b10, b11, b12, a11, a12, b20, b21, b22, a21, a22, ...}    
+ * </pre>    
+ * where <code>b1x</code> and <code>a1x</code> are the coefficients for the first stage,    
+ * <code>b2x</code> and <code>a2x</code> are the coefficients for the second stage,    
+ * and so on.  The <code>pCoeffs</code> array contains a total of <code>5*numStages</code> values.    
+ *    
+ * \par    
+ * The <code>pState</code> points to state variables array and size of each state variable is 1.63 format.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the state array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ */
+
+void arm_biquad_cas_df1_32x64_init_q31(
+  arm_biquad_cas_df1_32x64_ins_q31 * S,
+  uint8_t numStages,
+  q31_t * pCoeffs,
+  q63_t * pState,
+  uint8_t postShift)
+{
+  /* Assign filter stages */
+  S->numStages = numStages;
+
+  /* Assign postShift to be applied to the output */
+  S->postShift = postShift;
+
+  /* Assign coefficient pointer */
+  S->pCoeffs = pCoeffs;
+
+  /* Clear state buffer and size is always 4 * numStages */
+  memset(pState, 0, (4u * (uint32_t) numStages) * sizeof(q63_t));
+
+  /* Assign state pointer */
+  S->pState = pState;
+}
+
+/**    
+ * @} end of BiquadCascadeDF1_32x64 group    
+ */

libs/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_32x64_q31.c

@@ -0,0 +1,553 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_32x64_q31.c    
+*    
+* Description:	High precision Q31 Biquad cascade filter processing function    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @defgroup BiquadCascadeDF1_32x64 High Precision Q31 Biquad Cascade Filter    
+ *    
+ * This function implements a high precision Biquad cascade filter which operates on    
+ * Q31 data values.  The filter coefficients are in 1.31 format and the state variables    
+ * are in 1.63 format.  The double precision state variables reduce quantization noise    
+ * in the filter and provide a cleaner output.    
+ * These filters are particularly useful when implementing filters in which the    
+ * singularities are close to the unit circle.  This is common for low pass or high    
+ * pass filters with very low cutoff frequencies.    
+ *    
+ * The function operates on blocks of input and output data    
+ * and each call to the function processes <code>blockSize</code> samples through    
+ * the filter. <code>pSrc</code> and <code>pDst</code> points to input and output arrays    
+ * containing <code>blockSize</code> Q31 values.    
+ *    
+ * \par Algorithm    
+ * Each Biquad stage implements a second order filter using the difference equation:    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]    
+ * </pre>    
+ * A Direct Form I algorithm is used with 5 coefficients and 4 state variables per stage.    
+ * \image html Biquad.gif "Single Biquad filter stage"    
+ * Coefficients <code>b0, b1, and b2 </code> multiply the input signal <code>x[n]</code> and are referred to as the feedforward coefficients.    
+ * Coefficients <code>a1</code> and <code>a2</code> multiply the output signal <code>y[n]</code> and are referred to as the feedback coefficients.    
+ * Pay careful attention to the sign of the feedback coefficients.    
+ * Some design tools use the difference equation    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] - a1 * y[n-1] - a2 * y[n-2]    
+ * </pre>    
+ * In this case the feedback coefficients <code>a1</code> and <code>a2</code> must be negated when used with the CMSIS DSP Library.    
+ *    
+ * \par    
+ * Higher order filters are realized as a cascade of second order sections.    
+ * <code>numStages</code> refers to the number of second order stages used.    
+ * For example, an 8th order filter would be realized with <code>numStages=4</code> second order stages.    
+ * \image html BiquadCascade.gif "8th order filter using a cascade of Biquad stages"    
+ * A 9th order filter would be realized with <code>numStages=5</code> second order stages with the coefficients for one of the stages configured as a first order filter (<code>b2=0</code> and <code>a2=0</code>).    
+ *    
+ * \par    
+ * The <code>pState</code> points to state variables array .    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code> and each state variable in 1.63 format to improve precision.    
+ * The state variables are arranged in the array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ *    
+ * \par    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values of data in 1.63 format.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ *    
+ * \par Instance Structure    
+ * The coefficients and state variables for a filter are stored together in an instance data structure.    
+ * A separate instance structure must be defined for each filter.    
+ * Coefficient arrays may be shared among several instances while state variable arrays cannot be shared.    
+ *    
+ * \par Init Function    
+ * There is also an associated initialization function which performs the following operations:    
+ * - Sets the values of the internal structure fields.    
+ * - Zeros out the values in the state buffer.    
+ * \par    
+ * Use of the initialization function is optional.    
+ * However, if the initialization function is used, then the instance structure cannot be placed into a const data section.    
+ * To place an instance structure into a const data section, the instance structure must be manually initialized.    
+ * Set the values in the state buffer to zeros before static initialization.    
+ * For example, to statically initialize the filter instance structure use    
+ * <pre>    
+ *     arm_biquad_cas_df1_32x64_ins_q31 S1 = {numStages, pState, pCoeffs, postShift};    
+ * </pre>    
+ * where <code>numStages</code> is the number of Biquad stages in the filter; <code>pState</code> is the address of the state buffer;    
+ * <code>pCoeffs</code> is the address of the coefficient buffer; <code>postShift</code> shift to be applied which is described in detail below.    
+ * \par Fixed-Point Behavior    
+ * Care must be taken while using Biquad Cascade 32x64 filter function.    
+ * Following issues must be considered:    
+ * - Scaling of coefficients    
+ * - Filter gain    
+ * - Overflow and saturation    
+ *    
+ * \par    
+ * Filter coefficients are represented as fractional values and    
+ * restricted to lie in the range <code>[-1 +1)</code>.    
+ * The processing function has an additional scaling parameter <code>postShift</code>    
+ * which allows the filter coefficients to exceed the range <code>[+1 -1)</code>.    
+ * At the output of the filter's accumulator is a shift register which shifts the result by <code>postShift</code> bits.    
+ * \image html BiquadPostshift.gif "Fixed-point Biquad with shift by postShift bits after accumulator"    
+ * This essentially scales the filter coefficients by <code>2^postShift</code>.    
+ * For example, to realize the coefficients    
+ * <pre>    
+ *    {1.5, -0.8, 1.2, 1.6, -0.9}    
+ * </pre>    
+ * set the Coefficient array to:    
+ * <pre>    
+ *    {0.75, -0.4, 0.6, 0.8, -0.45}    
+ * </pre>    
+ * and set <code>postShift=1</code>    
+ *    
+ * \par    
+ * The second thing to keep in mind is the gain through the filter.    
+ * The frequency response of a Biquad filter is a function of its coefficients.    
+ * It is possible for the gain through the filter to exceed 1.0 meaning that the filter increases the amplitude of certain frequencies.    
+ * This means that an input signal with amplitude < 1.0 may result in an output > 1.0 and these are saturated or overflowed based on the implementation of the filter.    
+ * To avoid this behavior the filter needs to be scaled down such that its peak gain < 1.0 or the input signal must be scaled down so that the combination of input and filter are never overflowed.    
+ *    
+ * \par    
+ * The third item to consider is the overflow and saturation behavior of the fixed-point Q31 version.    
+ * This is described in the function specific documentation below.    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1_32x64    
+ * @{    
+ */
+
+/**    
+ * @details    
+    
+ * @param[in]  *S points to an instance of the high precision Q31 Biquad cascade filter.    
+ * @param[in]  *pSrc points to the block of input data.    
+ * @param[out] *pDst points to the block of output data.    
+ * @param[in]  blockSize number of samples to process.    
+ * @return none.    
+ *    
+ * \par    
+ * The function is implemented using an internal 64-bit accumulator.    
+ * The accumulator has a 2.62 format and maintains full precision of the intermediate multiplication results but provides only a single guard bit.    
+ * Thus, if the accumulator result overflows it wraps around rather than clip.    
+ * In order to avoid overflows completely the input signal must be scaled down by 2 bits and lie in the range [-0.25 +0.25).    
+ * After all 5 multiply-accumulates are performed, the 2.62 accumulator is shifted by <code>postShift</code> bits and the result truncated to    
+ * 1.31 format by discarding the low 32 bits.    
+ *    
+ * \par    
+ * Two related functions are provided in the CMSIS DSP library.    
+ * <code>arm_biquad_cascade_df1_q31()</code> implements a Biquad cascade with 32-bit coefficients and state variables with a Q63 accumulator.    
+ * <code>arm_biquad_cascade_df1_fast_q31()</code> implements a Biquad cascade with 32-bit coefficients and state variables with a Q31 accumulator.    
+ */
+
+void arm_biquad_cas_df1_32x64_q31(
+  const arm_biquad_cas_df1_32x64_ins_q31 * S,
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  q31_t *pIn = pSrc;                             /*  input pointer initialization  */
+  q31_t *pOut = pDst;                            /*  output pointer initialization */
+  q63_t *pState = S->pState;                     /*  state pointer initialization  */
+  q31_t *pCoeffs = S->pCoeffs;                   /*  coeff pointer initialization  */
+  q63_t acc;                                     /*  accumulator                   */
+  q31_t Xn1, Xn2;                                /*  Input Filter state variables        */
+  q63_t Yn1, Yn2;                                /*  Output Filter state variables        */
+  q31_t b0, b1, b2, a1, a2;                      /*  Filter coefficients           */
+  q31_t Xn;                                      /*  temporary input               */
+  int32_t shift = (int32_t) S->postShift + 1;    /*  Shift to be applied to the output */
+  uint32_t sample, stage = S->numStages;         /*  loop counters                     */
+  q31_t acc_l, acc_h;                            /*  temporary output               */
+  uint32_t uShift = ((uint32_t) S->postShift + 1u);
+  uint32_t lShift = 32u - uShift;                /*  Shift to be applied to the output */
+
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the state values */
+    Xn1 = (q31_t) (pState[0]);
+    Xn2 = (q31_t) (pState[1]);
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* Apply loop unrolling and compute 4 output values simultaneously. */
+    /* The variable acc hold output value that is being computed and    
+     * stored in the destination buffer    
+     * acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]    
+     */
+
+    sample = blockSize >> 2u;
+
+    /* First part of the processing with loop unrolling. Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* The result is converted to 1.63 , Yn2 variable is reused */
+      Yn2 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *pOut = acc_h;
+
+      /* Read the second input into Xn2, to reuse the value */
+      Xn2 = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc +=  b1 * x[n-1] */
+      acc = (q63_t) Xn *b1;
+
+      /* acc =  b0 * x[n] */
+      acc += (q63_t) Xn2 *b0;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn1 *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn2, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn1, a2);
+
+      /* The result is converted to 1.63, Yn1 variable is reused */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Read the third input into Xn1, to reuse the value */
+      Xn1 = *pIn++;
+
+      /* The result is converted to 1.31 */
+      /* Store the output in the destination buffer. */
+      *(pOut + 1u) = acc_h;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn1 *b0;
+
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn2 *b1;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* The result is converted to 1.63, Yn2 variable is reused  */
+      Yn2 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *(pOut + 2u) = acc_h;
+
+      /* Read the fourth input into Xn, to reuse the value */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn2, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn1, a2);
+
+      /* The result is converted to 1.63, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *(pOut + 3u) = acc_h;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+
+      /* update output pointer */
+      pOut += 4u;
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    sample = (blockSize & 0x3u);
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      /* The result is converted to 1.63, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *pOut++ = acc_h;
+      //Yn1 = acc << shift; 
+
+      /* Store the output in the destination buffer in 1.31 format. */
+//      *pOut++ = (q31_t) (acc >> (32 - shift)); 
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /*  The first stage output is given as input to the second stage. */
+    pIn = pDst;
+
+    /* Reset to destination buffer working pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the pState array */
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = (q63_t) Xn1;
+    *pState++ = (q63_t) Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+  } while(--stage);
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the state values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* The variable acc hold output value that is being computed and        
+     * stored in the destination buffer            
+     * acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]            
+     */
+
+    sample = blockSize;
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+
+      /* The result is converted to 1.63, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *pOut++ = acc_h;
+
+      //Yn1 = acc << shift; 
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      //*pOut++ = (q31_t) (acc >> (32 - shift)); 
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /*  The first stage output is given as input to the second stage. */
+    pIn = pDst;
+
+    /* Reset to destination buffer working pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = (q63_t) Xn1;
+    *pState++ = (q63_t) Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+  } while(--stage);
+
+#endif /*    #ifndef ARM_MATH_CM0     */
+}
+
+  /**    
+   * @} end of BiquadCascadeDF1_32x64 group    
+   */

libs/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_f32.c

@@ -0,0 +1,421 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_f32.c    
+*    
+* Description:	Processing function for the    
+*               floating-point Biquad cascade DirectFormI(DF1) filter.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.5  2010/04/26     
+* 	 incorporated review comments and updated with latest CMSIS layer    
+*    
+* Version 0.0.3  2010/03/10     
+*    Initial version    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @defgroup BiquadCascadeDF1 Biquad Cascade IIR Filters Using Direct Form I Structure    
+ *    
+ * This set of functions implements arbitrary order recursive (IIR) filters.    
+ * The filters are implemented as a cascade of second order Biquad sections.    
+ * The functions support Q15, Q31 and floating-point data types.  
+ * Fast version of Q15 and Q31 also supported on CortexM4 and Cortex-M3.    
+ *    
+ * The functions operate on blocks of input and output data and each call to the function    
+ * processes <code>blockSize</code> samples through the filter.    
+ * <code>pSrc</code> points to the array of input data and    
+ * <code>pDst</code> points to the array of output data.    
+ * Both arrays contain <code>blockSize</code> values.    
+ *    
+ * \par Algorithm    
+ * Each Biquad stage implements a second order filter using the difference equation:    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]    
+ * </pre>    
+ * A Direct Form I algorithm is used with 5 coefficients and 4 state variables per stage.    
+ * \image html Biquad.gif "Single Biquad filter stage"    
+ * Coefficients <code>b0, b1 and b2 </code> multiply the input signal <code>x[n]</code> and are referred to as the feedforward coefficients.    
+ * Coefficients <code>a1</code> and <code>a2</code> multiply the output signal <code>y[n]</code> and are referred to as the feedback coefficients.    
+ * Pay careful attention to the sign of the feedback coefficients.    
+ * Some design tools use the difference equation    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] - a1 * y[n-1] - a2 * y[n-2]    
+ * </pre>    
+ * In this case the feedback coefficients <code>a1</code> and <code>a2</code> must be negated when used with the CMSIS DSP Library.    
+ *    
+ * \par    
+ * Higher order filters are realized as a cascade of second order sections.    
+ * <code>numStages</code> refers to the number of second order stages used.    
+ * For example, an 8th order filter would be realized with <code>numStages=4</code> second order stages.    
+ * \image html BiquadCascade.gif "8th order filter using a cascade of Biquad stages"    
+ * A 9th order filter would be realized with <code>numStages=5</code> second order stages with the coefficients for one of the stages configured as a first order filter (<code>b2=0</code> and <code>a2=0</code>).    
+ *    
+ * \par    
+ * The <code>pState</code> points to state variables array.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the <code>pState</code> array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ *    
+ * \par    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed, the coefficients are untouched.    
+ *    
+ * \par Instance Structure    
+ * The coefficients and state variables for a filter are stored together in an instance data structure.    
+ * A separate instance structure must be defined for each filter.    
+ * Coefficient arrays may be shared among several instances while state variable arrays cannot be shared.    
+ * There are separate instance structure declarations for each of the 3 supported data types.    
+ *    
+ * \par Init Functions    
+ * There is also an associated initialization function for each data type.    
+ * The initialization function performs following operations:    
+ * - Sets the values of the internal structure fields.    
+ * - Zeros out the values in the state buffer.    
+ *    
+ * \par    
+ * Use of the initialization function is optional.    
+ * However, if the initialization function is used, then the instance structure cannot be placed into a const data section.    
+ * To place an instance structure into a const data section, the instance structure must be manually initialized.    
+ * Set the values in the state buffer to zeros before static initialization.    
+ * The code below statically initializes each of the 3 different data type filter instance structures    
+ * <pre>    
+ *     arm_biquad_casd_df1_inst_f32 S1 = {numStages, pState, pCoeffs};    
+ *     arm_biquad_casd_df1_inst_q15 S2 = {numStages, pState, pCoeffs, postShift};    
+ *     arm_biquad_casd_df1_inst_q31 S3 = {numStages, pState, pCoeffs, postShift};    
+ * </pre>    
+ * where <code>numStages</code> is the number of Biquad stages in the filter; <code>pState</code> is the address of the state buffer;    
+ * <code>pCoeffs</code> is the address of the coefficient buffer; <code>postShift</code> shift to be applied.    
+ *    
+ * \par Fixed-Point Behavior    
+ * Care must be taken when using the Q15 and Q31 versions of the Biquad Cascade filter functions.    
+ * Following issues must be considered:    
+ * - Scaling of coefficients    
+ * - Filter gain    
+ * - Overflow and saturation    
+ *    
+ * \par    
+ * <b>Scaling of coefficients: </b>    
+ * Filter coefficients are represented as fractional values and    
+ * coefficients are restricted to lie in the range <code>[-1 +1)</code>.    
+ * The fixed-point functions have an additional scaling parameter <code>postShift</code>    
+ * which allow the filter coefficients to exceed the range <code>[+1 -1)</code>.    
+ * At the output of the filter's accumulator is a shift register which shifts the result by <code>postShift</code> bits.    
+ * \image html BiquadPostshift.gif "Fixed-point Biquad with shift by postShift bits after accumulator"    
+ * This essentially scales the filter coefficients by <code>2^postShift</code>.    
+ * For example, to realize the coefficients    
+ * <pre>    
+ *    {1.5, -0.8, 1.2, 1.6, -0.9}    
+ * </pre>    
+ * set the pCoeffs array to:    
+ * <pre>    
+ *    {0.75, -0.4, 0.6, 0.8, -0.45}    
+ * </pre>    
+ * and set <code>postShift=1</code>    
+ *    
+ * \par    
+ * <b>Filter gain: </b>    
+ * The frequency response of a Biquad filter is a function of its coefficients.    
+ * It is possible for the gain through the filter to exceed 1.0 meaning that the filter increases the amplitude of certain frequencies.    
+ * This means that an input signal with amplitude < 1.0 may result in an output > 1.0 and these are saturated or overflowed based on the implementation of the filter.    
+ * To avoid this behavior the filter needs to be scaled down such that its peak gain < 1.0 or the input signal must be scaled down so that the combination of input and filter are never overflowed.    
+ *    
+ * \par    
+ * <b>Overflow and saturation: </b>    
+ * For Q15 and Q31 versions, it is described separately as part of the function specific documentation below.    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @param[in]  *S         points to an instance of the floating-point Biquad cascade structure.    
+ * @param[in]  *pSrc      points to the block of input data.    
+ * @param[out] *pDst      points to the block of output data.    
+ * @param[in]  blockSize  number of samples to process per call.    
+ * @return     none.    
+ *    
+ */
+
+void arm_biquad_cascade_df1_f32(
+  const arm_biquad_casd_df1_inst_f32 * S,
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  float32_t *pIn = pSrc;                         /*  source pointer            */
+  float32_t *pOut = pDst;                        /*  destination pointer       */
+  float32_t *pState = S->pState;                 /*  pState pointer            */
+  float32_t *pCoeffs = S->pCoeffs;               /*  coefficient pointer       */
+  float32_t acc;                                 /*  Simulates the accumulator */
+  float32_t b0, b1, b2, a1, a2;                  /*  Filter coefficients       */
+  float32_t Xn1, Xn2, Yn1, Yn2;                  /*  Filter pState variables   */
+  float32_t Xn;                                  /*  temporary input           */
+  uint32_t sample, stage = S->numStages;         /*  loop counters             */
+
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the pState values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* Apply loop unrolling and compute 4 output values simultaneously. */
+    /*      The variable acc hold output values that are being computed:    
+     *    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     */
+
+    sample = blockSize >> 2u;
+
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(sample > 0u)
+    {
+      /* Read the first input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn2 = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn2;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+
+      /* Read the second input */
+      Xn2 = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn1 = (b0 * Xn2) + (b1 * Xn) + (b2 * Xn1) + (a1 * Yn2) + (a2 * Yn1);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn1;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+
+      /* Read the third input */
+      Xn1 = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn2 = (b0 * Xn1) + (b1 * Xn2) + (b2 * Xn) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn2;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as: */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+
+      /* Read the forth input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn1 = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn2) + (a2 * Yn1);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn1;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+
+      /* decrement the loop counter */
+      sample--;
+
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    sample = blockSize & 0x3u;
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      acc = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = acc;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:    */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      Yn1 = acc;
+
+      /* decrement the loop counter */
+      sample--;
+
+    }
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = Xn1;
+    *pState++ = Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+    /*  The first stage goes from the input buffer to the output buffer. */
+    /*  Subsequent numStages  occur in-place in the output buffer */
+    pIn = pDst;
+
+    /* Reset the output pointer */
+    pOut = pDst;
+
+    /* decrement the loop counter */
+    stage--;
+
+  } while(stage > 0u);
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the pState values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /*      The variables acc holds the output value that is computed:        
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]        
+     */
+
+    sample = blockSize;
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      acc = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = acc;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:    */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      Yn1 = acc;
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = Xn1;
+    *pState++ = Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+    /*  The first stage goes from the input buffer to the output buffer. */
+    /*  Subsequent numStages  occur in-place in the output buffer */
+    pIn = pDst;
+
+    /* Reset the output pointer */
+    pOut = pDst;
+
+    /* decrement the loop counter */
+    stage--;
+
+  } while(stage > 0u);
+
+#endif /*   #ifndef ARM_MATH_CM0         */
+
+}
+
+
+  /**    
+   * @} end of BiquadCascadeDF1 group    
+   */

libs/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_fast_q15.c

@@ -0,0 +1,283 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_fast_q15.c    
+*    
+* Description:	Fast processing function for the    
+*				Q15 Biquad cascade filter.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.9  2010/08/16     
+*    Initial version    
+*    
+*    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ * @param[in]  *S points to an instance of the Q15 Biquad cascade structure.    
+ * @param[in]  *pSrc points to the block of input data.    
+ * @param[out] *pDst points to the block of output data.    
+ * @param[in]  blockSize number of samples to process per call.    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * This fast version uses a 32-bit accumulator with 2.30 format.    
+ * The accumulator maintains full precision of the intermediate multiplication results but provides only a single guard bit.    
+ * Thus, if the accumulator result overflows it wraps around and distorts the result.    
+ * In order to avoid overflows completely the input signal must be scaled down by two bits and lie in the range [-0.25 +0.25).    
+ * The 2.30 accumulator is then shifted by <code>postShift</code> bits and the result truncated to 1.15 format by discarding the low 16 bits.    
+ *    
+ * \par    
+ * Refer to the function <code>arm_biquad_cascade_df1_q15()</code> for a slower implementation of this function which uses 64-bit accumulation to avoid wrap around distortion.  Both the slow and the fast versions use the same instance structure.    
+ * Use the function <code>arm_biquad_cascade_df1_init_q15()</code> to initialize the filter structure.    
+ *    
+ */
+
+void arm_biquad_cascade_df1_fast_q15(
+  const arm_biquad_casd_df1_inst_q15 * S,
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  q15_t *pIn = pSrc;                             /*  Source pointer                               */
+  q15_t *pOut = pDst;                            /*  Destination pointer                          */
+  q31_t in;                                      /*  Temporary variable to hold input value       */
+  q31_t out;                                     /*  Temporary variable to hold output value      */
+  q31_t b0;                                      /*  Temporary variable to hold bo value          */
+  q31_t b1, a1;                                  /*  Filter coefficients                          */
+  q31_t state_in, state_out;                     /*  Filter state variables                       */
+  q31_t acc;                                     /*  Accumulator                                  */
+  int32_t shift = (int32_t) (15 - S->postShift); /*  Post shift                                   */
+  q15_t *pState = S->pState;                     /*  State pointer                                */
+  q15_t *pCoeffs = S->pCoeffs;                   /*  Coefficient pointer                          */
+  uint32_t sample, stage = S->numStages;         /*  Stage loop counter                           */
+
+
+
+  do
+  {
+
+    /* Read the b0 and 0 coefficients using SIMD  */
+    b0 = *__SIMD32(pCoeffs)++;
+
+    /* Read the b1 and b2 coefficients using SIMD */
+    b1 = *__SIMD32(pCoeffs)++;
+
+    /* Read the a1 and a2 coefficients using SIMD */
+    a1 = *__SIMD32(pCoeffs)++;
+
+    /* Read the input state values from the state buffer:  x[n-1], x[n-2] */
+    state_in = *__SIMD32(pState)++;
+
+    /* Read the output state values from the state buffer:  y[n-1], y[n-2] */
+    state_out = *__SIMD32(pState)--;
+
+    /* Apply loop unrolling and compute 2 output values simultaneously. */
+    /*      The variable acc hold output values that are being computed:       
+     *    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]       
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]       
+     */
+    sample = blockSize >> 1u;
+
+    /* First part of the processing with loop unrolling.  Compute 2 outputs at a time.    
+     ** a second loop below computes the remaining 1 sample. */
+    while(sample > 0u)
+    {
+
+      /* Read the input */
+      in = *__SIMD32(pIn)++;
+
+      /* out =  b0 * x[n] + 0 * 0 */
+      out = __SMUAD(b0, in);
+      /* acc =  b1 * x[n-1] + acc +=  b2 * x[n-2] + out */
+      acc = __SMLAD(b1, state_in, out);
+      /* acc +=  a1 * y[n-1] + acc +=  a2 * y[n-2] */
+      acc = __SMLAD(a1, state_out, acc);
+
+      /* The result is converted from 3.29 to 1.31 and then saturation is applied */
+      out = __SSAT((acc >> shift), 16);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      /* x[n-N], x[n-N-1] are packed together to make state_in of type q31 */
+      /* y[n-N], y[n-N-1] are packed together to make state_out of type q31 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      state_in = __PKHBT(in, state_in, 16);
+      state_out = __PKHBT(out, state_out, 16);
+
+#else
+
+      state_in = __PKHBT(state_in >> 16, (in >> 16), 16);
+      state_out = __PKHBT(state_out >> 16, (out), 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* out =  b0 * x[n] + 0 * 0 */
+      out = __SMUADX(b0, in);
+      /* acc0 =  b1 * x[n-1] , acc0 +=  b2 * x[n-2] + out */
+      acc = __SMLAD(b1, state_in, out);
+      /* acc +=  a1 * y[n-1] + acc +=  a2 * y[n-2] */
+      acc = __SMLAD(a1, state_out, acc);
+
+      /* The result is converted from 3.29 to 1.31 and then saturation is applied */
+      out = __SSAT((acc >> shift), 16);
+
+
+      /* Store the output in the destination buffer. */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pOut)++ = __PKHBT(state_out, out, 16);
+
+#else
+
+      *__SIMD32(pOut)++ = __PKHBT(out, state_out >> 16, 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      /* x[n-N], x[n-N-1] are packed together to make state_in of type q31 */
+      /* y[n-N], y[n-N-1] are packed together to make state_out of type q31 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      state_in = __PKHBT(in >> 16, state_in, 16);
+      state_out = __PKHBT(out, state_out, 16);
+
+#else
+
+      state_in = __PKHBT(state_in >> 16, in, 16);
+      state_out = __PKHBT(state_out >> 16, out, 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+
+      /* Decrement the loop counter */
+      sample--;
+
+    }
+
+    /* If the blockSize is not a multiple of 2, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+
+    if((blockSize & 0x1u) != 0u)
+    {
+      /* Read the input */
+      in = *pIn++;
+
+      /* out =  b0 * x[n] + 0 * 0 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      out = __SMUAD(b0, in);
+
+#else
+
+      out = __SMUADX(b0, in);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* acc =  b1 * x[n-1], acc +=  b2 * x[n-2] + out */
+      acc = __SMLAD(b1, state_in, out);
+      /* acc +=  a1 * y[n-1] + acc +=  a2 * y[n-2] */
+      acc = __SMLAD(a1, state_out, acc);
+
+      /* The result is converted from 3.29 to 1.31 and then saturation is applied */
+      out = __SSAT((acc >> shift), 16);
+
+      /* Store the output in the destination buffer. */
+      *pOut++ = (q15_t) out;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      /* x[n-N], x[n-N-1] are packed together to make state_in of type q31 */
+      /* y[n-N], y[n-N-1] are packed together to make state_out of type q31 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      state_in = __PKHBT(in, state_in, 16);
+      state_out = __PKHBT(out, state_out, 16);
+
+#else
+
+      state_in = __PKHBT(state_in >> 16, in, 16);
+      state_out = __PKHBT(state_out >> 16, out, 16);
+
+#endif /*   #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+    }
+
+    /*  The first stage goes from the input buffer to the output buffer.  */
+    /*  Subsequent (numStages - 1) occur in-place in the output buffer  */
+    pIn = pDst;
+
+    /* Reset the output pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the state array */
+    *__SIMD32(pState)++ = state_in;
+    *__SIMD32(pState)++ = state_out;
+
+
+    /* Decrement the loop counter */
+    stage--;
+
+  } while(stage > 0u);
+}
+
+
+/**    
+ * @} end of BiquadCascadeDF1 group    
+ */

libs/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_fast_q31.c

@@ -0,0 +1,275 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_fast_q31.c    
+*    
+* Description:	Processing function for the    
+*				Q31 Fast Biquad cascade DirectFormI(DF1) filter.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.9  2010/08/27     
+*    Initial version    
+*    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ *    
+ * @param[in]  *S        points to an instance of the Q31 Biquad cascade structure.    
+ * @param[in]  *pSrc     points to the block of input data.    
+ * @param[out] *pDst     points to the block of output data.    
+ * @param[in]  blockSize number of samples to process per call.    
+ * @return 	   none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * This function is optimized for speed at the expense of fixed-point precision and overflow protection.    
+ * The result of each 1.31 x 1.31 multiplication is truncated to 2.30 format.    
+ * These intermediate results are added to a 2.30 accumulator.    
+ * Finally, the accumulator is saturated and converted to a 1.31 result.    
+ * The fast version has the same overflow behavior as the standard version and provides less precision since it discards the low 32 bits of each multiplication result.    
+ * In order to avoid overflows completely the input signal must be scaled down by two bits and lie in the range [-0.25 +0.25). Use the intialization function    
+ * arm_biquad_cascade_df1_init_q31() to initialize filter structure.    
+ *    
+ * \par    
+ * Refer to the function <code>arm_biquad_cascade_df1_q31()</code> for a slower implementation of this function which uses 64-bit accumulation to provide higher precision.  Both the slow and the fast versions use the same instance structure.    
+ * Use the function <code>arm_biquad_cascade_df1_init_q31()</code> to initialize the filter structure.    
+ */
+
+void arm_biquad_cascade_df1_fast_q31(
+  const arm_biquad_casd_df1_inst_q31 * S,
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  q31_t acc;                                     /*  accumulator                   */
+  q31_t Xn1, Xn2, Yn1, Yn2;                      /*  Filter state variables        */
+  q31_t b0, b1, b2, a1, a2;                      /*  Filter coefficients           */
+  q31_t *pIn = pSrc;                             /*  input pointer initialization  */
+  q31_t *pOut = pDst;                            /*  output pointer initialization */
+  q31_t *pState = S->pState;                     /*  pState pointer initialization */
+  q31_t *pCoeffs = S->pCoeffs;                   /*  coeff pointer initialization  */
+  q31_t Xn;                                      /*  temporary input               */
+  int32_t shift = (int32_t) S->postShift + 1;    /*  Shift to be applied to the output */
+  uint32_t sample, stage = S->numStages;         /*  loop counters                     */
+
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the state values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* Apply loop unrolling and compute 4 output values simultaneously. */
+    /*      The variables acc ... acc3 hold output values that are being computed:       
+     *       
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]       
+     */
+
+    sample = blockSize >> 2u;
+
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.       
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q31_t) (((q63_t) b1 * Xn1) >> 32);
+      /* acc +=  b1 * x[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b0 * (Xn))) >> 32);
+      /* acc +=  b[2] * x[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn2))) >> 32);
+      /* acc +=  a1 * y[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn1))) >> 32);
+      /* acc +=  a2 * y[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn2))) >> 32);
+
+      /* The result is converted to 1.31 , Yn2 variable is reused */
+      Yn2 = acc << shift;
+
+      /* Read the second input */
+      Xn2 = *(pIn + 1u);
+
+      /* Store the output in the destination buffer. */
+      *pOut = Yn2;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q31_t) (((q63_t) b0 * (Xn2)) >> 32);
+      /* acc +=  b1 * x[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn))) >> 32);
+      /* acc +=  b[2] * x[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn1))) >> 32);
+      /* acc +=  a1 * y[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn2))) >> 32);
+      /* acc +=  a2 * y[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn1))) >> 32);
+
+      /* The result is converted to 1.31, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Read the third input  */
+      Xn1 = *(pIn + 2u);
+
+      /* Store the output in the destination buffer. */
+      *(pOut + 1u) = Yn1;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q31_t) (((q63_t) b0 * (Xn1)) >> 32);
+      /* acc +=  b1 * x[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn2))) >> 32);
+      /* acc +=  b[2] * x[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn))) >> 32);
+      /* acc +=  a1 * y[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn1))) >> 32);
+      /* acc +=  a2 * y[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn2))) >> 32);
+
+      /* The result is converted to 1.31, Yn2 variable is reused  */
+      Yn2 = acc << shift;
+
+      /* Read the forth input */
+      Xn = *(pIn + 3u);
+
+      /* Store the output in the destination buffer. */
+      *(pOut + 2u) = Yn2;
+      pIn += 4u;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q31_t) (((q63_t) b0 * (Xn)) >> 32);
+      /* acc +=  b1 * x[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn1))) >> 32);
+      /* acc +=  b[2] * x[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn2))) >> 32);
+      /* acc +=  a1 * y[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn2))) >> 32);
+      /* acc +=  a2 * y[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn1))) >> 32);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      Xn2 = Xn1;
+
+      /* The result is converted to 1.31, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Xn1 = Xn     */
+      Xn1 = Xn;
+
+      /* Store the output in the destination buffer. */
+      *(pOut + 3u) = Yn1;
+      pOut += 4u;
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.       
+     ** No loop unrolling is used. */
+    sample = (blockSize & 0x3u);
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q31_t) (((q63_t) b0 * (Xn)) >> 32);
+      /* acc +=  b1 * x[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn1))) >> 32);
+      /* acc +=  b[2] * x[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn2))) >> 32);
+      /* acc +=  a1 * y[n-1] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn1))) >> 32);
+      /* acc +=  a2 * y[n-2] */
+      acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn2))) >> 32);
+      /* The result is converted to 1.31  */
+      acc = acc << shift;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      Yn1 = acc;
+
+      /* Store the output in the destination buffer. */
+      *pOut++ = acc;
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /*  The first stage goes from the input buffer to the output buffer. */
+    /*  Subsequent stages occur in-place in the output buffer */
+    pIn = pDst;
+
+    /* Reset to destination pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = Xn1;
+    *pState++ = Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+  } while(--stage);
+}
+
+/**    
+  * @} end of BiquadCascadeDF1 group    
+  */

libs/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_init_f32.c

@@ -0,0 +1,107 @@
+/*-----------------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:        arm_biquad_cascade_df1_init_f32.c    
+*    
+* Description:  floating-point Biquad cascade DirectFormI(DF1) filter initialization function.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.5  2010/04/26     
+* 	 incorporated review comments and updated with latest CMSIS layer    
+*    
+* Version 0.0.3  2010/03/10     
+*    Initial version    
+* ---------------------------------------------------------------------------*/
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ * @brief  Initialization function for the floating-point Biquad cascade filter.    
+ * @param[in,out] *S           points to an instance of the floating-point Biquad cascade structure.    
+ * @param[in]     numStages    number of 2nd order stages in the filter.    
+ * @param[in]     *pCoeffs     points to the filter coefficients array.    
+ * @param[in]     *pState      points to the state array.    
+ * @return        none    
+ *    
+ *    
+ * <b>Coefficient and State Ordering:</b>    
+ *    
+ * \par    
+ * The coefficients are stored in the array <code>pCoeffs</code> in the following order:    
+ * <pre>    
+ *     {b10, b11, b12, a11, a12, b20, b21, b22, a21, a22, ...}    
+ * </pre>    
+ *    
+ * \par    
+ * where <code>b1x</code> and <code>a1x</code> are the coefficients for the first stage,    
+ * <code>b2x</code> and <code>a2x</code> are the coefficients for the second stage,    
+ * and so on.  The <code>pCoeffs</code> array contains a total of <code>5*numStages</code> values.    
+ *    
+ * \par    
+ * The <code>pState</code> is a pointer to state array.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the <code>pState</code> array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ *    
+ */
+
+void arm_biquad_cascade_df1_init_f32(
+  arm_biquad_casd_df1_inst_f32 * S,
+  uint8_t numStages,
+  float32_t * pCoeffs,
+  float32_t * pState)
+{
+  /* Assign filter stages */
+  S->numStages = numStages;
+
+  /* Assign coefficient pointer */
+  S->pCoeffs = pCoeffs;
+
+  /* Clear state buffer and size is always 4 * numStages */
+  memset(pState, 0, (4u * (uint32_t) numStages) * sizeof(float32_t));
+
+  /* Assign state pointer */
+  S->pState = pState;
+}
+
+/**    
+ * @} end of BiquadCascadeDF1 group    
+ */

libs/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_init_q15.c

@@ -0,0 +1,109 @@
+/*-----------------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:        arm_biquad_cascade_df1_init_q15.c    
+*    
+* Description:  Q15 Biquad cascade DirectFormI(DF1) filter initialization function.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+*    
+* Version 0.0.5  2010/04/26     
+* 	 incorporated review comments and updated with latest CMSIS layer    
+*    
+* Version 0.0.3  2010/03/10     
+*    Initial version    
+* ---------------------------------------------------------------------------*/
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ *    
+ * @param[in,out] *S           points to an instance of the Q15 Biquad cascade structure.    
+ * @param[in]     numStages    number of 2nd order stages in the filter.    
+ * @param[in]     *pCoeffs     points to the filter coefficients.    
+ * @param[in]     *pState      points to the state buffer.    
+ * @param[in]     postShift    Shift to be applied to the accumulator result. Varies according to the coefficients format    
+ * @return        none    
+ *    
+ * <b>Coefficient and State Ordering:</b>    
+ *    
+ * \par    
+ * The coefficients are stored in the array <code>pCoeffs</code> in the following order:    
+ * <pre>    
+ *     {b10, 0, b11, b12, a11, a12, b20, 0, b21, b22, a21, a22, ...}    
+ * </pre>    
+ * where <code>b1x</code> and <code>a1x</code> are the coefficients for the first stage,    
+ * <code>b2x</code> and <code>a2x</code> are the coefficients for the second stage,    
+ * and so on.  The <code>pCoeffs</code> array contains a total of <code>6*numStages</code> values.    
+ * The zero coefficient between <code>b1</code> and <code>b2</code> facilities  use of 16-bit SIMD instructions on the Cortex-M4.    
+ *    
+ * \par    
+ * The state variables are stored in the array <code>pState</code>.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the <code>pState</code> array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ */
+
+void arm_biquad_cascade_df1_init_q15(
+  arm_biquad_casd_df1_inst_q15 * S,
+  uint8_t numStages,
+  q15_t * pCoeffs,
+  q15_t * pState,
+  int8_t postShift)
+{
+  /* Assign filter stages */
+  S->numStages = numStages;
+
+  /* Assign postShift to be applied to the output */
+  S->postShift = postShift;
+
+  /* Assign coefficient pointer */
+  S->pCoeffs = pCoeffs;
+
+  /* Clear state buffer and size is always 4 * numStages */
+  memset(pState, 0, (4u * (uint32_t) numStages) * sizeof(q15_t));
+
+  /* Assign state pointer */
+  S->pState = pState;
+}
+
+/**    
+ * @} end of BiquadCascadeDF1 group    
+ */