Diff: cmsis_dsp/ComplexMathFunctions/arm_cmplx_mult_cmplx_q15.c

Revision:

1:fdd22bb7aa52

Child:

2:da51fb522205

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cmsis_dsp/ComplexMathFunctions/arm_cmplx_mult_cmplx_q15.c	Wed Nov 28 12:30:09 2012 +0000
@@ -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    
+ */