add STM32F40x porting (uncompleted)

git-svn-id: https://rt-thread.googlecode.com/svn/trunk@1769 bbd45198-f89e-11dd-88c7-29a3b14d5316

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/ARM/arm_cortexMx_math_Build.bat

+
+SET TMP=C:\Temp
+SET TEMP=C:\Temp
+
+SET UVEXE=C:\Keil\UV4\UV4.EXE
+
+%UVEXE% -rb arm_cortexM0x_math.uvproj -t"DSP_Lib CM0 LE" -o"DSP_Lib CM0 LE.txt"
+%UVEXE% -rb arm_cortexM0x_math.uvproj -t"DSP_Lib CM0 BE" -o"DSP_Lib CM0 BE.txt"
+%UVEXE% -rb arm_cortexM3x_math.uvproj -t"DSP_Lib CM3 LE" -o"DSP_Lib CM3 LE.txt"
+%UVEXE% -rb arm_cortexM3x_math.uvproj -t"DSP_Lib CM3 BE" -o"DSP_Lib CM3 BE.txt"
+%UVEXE% -rb arm_cortexM4x_math.uvproj -t"DSP_Lib CM4 LE" -o"DSP_Lib CM4 LE.txt"
+%UVEXE% -rb arm_cortexM4x_math.uvproj -t"DSP_Lib CM4 BE" -o"DSP_Lib CM4 BE.txt"
+%UVEXE% -rb arm_cortexM4x_math.uvproj -t"DSP_Lib CM4 LE FPU" -o"DSP_Lib CM4 LE FPU.txt"
+%UVEXE% -rb arm_cortexM4x_math.uvproj -t"DSP_Lib CM4 BE FPU" -o"DSP_Lib CM4 BE FPU.txt"
\ No newline at end of file

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_f32.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_abs_f32.c   
+*   
+* Description:	Vector absolute value.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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 */
+
+  /*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. */
+    *pDst++ = fabsf(*pSrc++);
+    *pDst++ = fabsf(*pSrc++);
+    *pDst++ = fabsf(*pSrc++);
+    *pDst++ = fabsf(*pSrc++);
+
+    /* 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   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q15.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_abs_q15.c   
+*   
+* Description:	Q15 vector absolute value.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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 : __SSAT(-in1, 16)),
+              ((in2 > 0) ? in2 : __SSAT(-in2, 16)), 16);
+
+#else
+
+
+    *__SIMD32(pDst)++ =
+      __PKHBT(((in2 > 0) ? in2 : __SSAT(-in2, 16)),
+              ((in1 > 0) ? in1 : __SSAT(-in1, 16)), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+    *__SIMD32(pDst)++ =
+      __PKHBT(((in1 > 0) ? in1 : __SSAT(-in1, 16)),
+              ((in2 > 0) ? in2 : __SSAT(-in2, 16)), 16);
+
+
+#else
+
+    *__SIMD32(pDst)++ =
+      __PKHBT(((in2 > 0) ? in2 : __SSAT(-in2, 16)),
+              ((in1 > 0) ? in1 : __SSAT(-in1, 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| */
+    /* Read the input */
+    in1 = *pSrc++;
+
+    /* Calculate absolute value of input and then store the result in the destination buffer. */
+    *pDst++ = (in1 > 0) ? in1 : __SSAT(-in1, 16);
+
+    /* 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 : __SSAT(-in, 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**   
+ * @} end of BasicAbs group   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q31.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_abs_q31.c   
+*   
+* Description:	Q31 vector absolute value.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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 */
+
+  /*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. */
+    in = *pSrc++;
+    *pDst++ = (in > 0) ? in : ((in == 0x80000000) ? 0x7fffffff : -in);
+    in = *pSrc++;
+    *pDst++ = (in > 0) ? in : ((in == 0x80000000) ? 0x7fffffff : -in);
+    in = *pSrc++;
+    *pDst++ = (in > 0) ? in : ((in == 0x80000000) ? 0x7fffffff : -in);
+    in = *pSrc++;
+    *pDst++ = (in > 0) ? in : ((in == 0x80000000) ? 0x7fffffff : -in);
+
+    /* 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   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q7.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_abs_q7.c   
+*   
+* Description:	Q7 vector absolute value.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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.   
+ *   
+ * <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 */
+
+#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;
+
+  /* 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 4 inputs */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    /* Store the Absolute result in the destination buffer by packing the 4 values in single cycle */
+    *__SIMD32(pDst)++ =
+      __PACKq7(((in1 > 0) ? in1 : __SSAT(-in1, 8)),
+               ((in2 > 0) ? in2 : __SSAT(-in2, 8)),
+               ((in3 > 0) ? in3 : __SSAT(-in3, 8)),
+               ((in4 > 0) ? in4 : __SSAT(-in4, 8)));
+
+    /* 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++;
+
+    /* Store the Absolute result in the destination buffer */
+    *pDst++ = (in1 > 0) ? in1 : __SSAT(-in1, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  q7_t in;                                       /* Temporary input varible */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read the input */
+    in = *pSrc++;
+
+    /* Store the Absolute result in the destination buffer */
+    *pDst++ = (in > 0) ? in : __SSAT(-in, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /*   #ifndef ARM_MATH_CM0   */
+
+}
+
+/**   
+ * @} end of BasicAbs group   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_f32.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_add_f32.c   
+*   
+* Description:	Floating-point vector addition.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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 */
+
+  /*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. */
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+    *pDst++ = (*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 + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**   
+ * @} end of BasicAdd group   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_add_q15.c   
+*   
+* Description:	Q15 vector addition   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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 */
+
+
+  /*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)++ = __QADD16(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
+    *__SIMD32(pDst)++ = __QADD16(*__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++ = (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   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q31.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_add_q31.c   
+*   
+* Description:	Q31 vector addition.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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 */
+
+
+  /*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. */
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
+    *pDst++ = __QADD(*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;
+
+  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   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q7.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_add_q7.c   
+*   
+* Description:	Q7 vector addition.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* 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   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_f32.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* Project: 	    CMSIS DSP Library   
+* Title:		arm_dot_prod_f32.c   
+*   
+* Description:	Floating-point dot product.   
+*   
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.0.10 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   
+ */

bsp/stm32f40x/Libraries/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_init_f32.c

+/* ----------------------------------------------------------------------   
+* Copyright (C) 2010 ARM Limited. All rights reserved.   
+*   
+* $Date:        15. July 2011  
+* $Revision: 	V1.0.10  
+*   
+* 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 1.0.10 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   
+ */