1 files changed, 143 insertions, 0 deletions
diff --git a/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q31.c b/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q31.c
new file mode 100644
index 000000000..37ec8e25e
--- /dev/null
+++ b/src/modules/mathlib/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    
+ */