Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_dot_prod_q15.c@2:da51fb522205, 2013-05-30 (annotated)

Committer:
emilmont
Date:
Thu May 30 17:10:11 2013 +0100
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
emilmont 1:fdd22bb7aa52 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
emilmont 1:fdd22bb7aa52 4 * $Date: 15. February 2012
emilmont 2:da51fb522205 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_dot_prod_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q15 dot product.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
emilmont 1:fdd22bb7aa52 14 * Version 1.1.0 2012/02/15
emilmont 1:fdd22bb7aa52 15 * Updated with more optimizations, bug fixes and minor API changes.
emilmont 1:fdd22bb7aa52 16 *
emilmont 1:fdd22bb7aa52 17 * Version 1.0.10 2011/7/15
emilmont 1:fdd22bb7aa52 18 * Big Endian support added and Merged M0 and M3/M4 Source code.
emilmont 1:fdd22bb7aa52 19 *
emilmont 1:fdd22bb7aa52 20 * Version 1.0.3 2010/11/29
emilmont 1:fdd22bb7aa52 21 * Re-organized the CMSIS folders and updated documentation.
emilmont 1:fdd22bb7aa52 22 *
emilmont 1:fdd22bb7aa52 23 * Version 1.0.2 2010/11/11
emilmont 1:fdd22bb7aa52 24 * Documentation updated.
emilmont 1:fdd22bb7aa52 25 *
emilmont 1:fdd22bb7aa52 26 * Version 1.0.1 2010/10/05
emilmont 1:fdd22bb7aa52 27 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 28 *
emilmont 1:fdd22bb7aa52 29 * Version 1.0.0 2010/09/20
emilmont 1:fdd22bb7aa52 30 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 31 *
emilmont 1:fdd22bb7aa52 32 * Version 0.0.7 2010/06/10
emilmont 1:fdd22bb7aa52 33 * Misra-C changes done
emilmont 1:fdd22bb7aa52 34 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 35
emilmont 1:fdd22bb7aa52 36 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 37
emilmont 1:fdd22bb7aa52 38 /**
emilmont 1:fdd22bb7aa52 39 * @ingroup groupMath
emilmont 1:fdd22bb7aa52 40 */
emilmont 1:fdd22bb7aa52 41
emilmont 1:fdd22bb7aa52 42 /**
emilmont 1:fdd22bb7aa52 43 * @addtogroup dot_prod
emilmont 1:fdd22bb7aa52 44 * @{
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @brief Dot product of Q15 vectors.
emilmont 1:fdd22bb7aa52 49 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 50 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 51 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 52 * @param[out] *result output result returned here
emilmont 1:fdd22bb7aa52 53 * @return none.
emilmont 1:fdd22bb7aa52 54 *
emilmont 1:fdd22bb7aa52 55 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 56 * \par
emilmont 1:fdd22bb7aa52 57 * The intermediate multiplications are in 1.15 x 1.15 = 2.30 format and these
emilmont 1:fdd22bb7aa52 58 * results are added to a 64-bit accumulator in 34.30 format.
emilmont 1:fdd22bb7aa52 59 * Nonsaturating additions are used and given that there are 33 guard bits in the accumulator
emilmont 1:fdd22bb7aa52 60 * there is no risk of overflow.
emilmont 1:fdd22bb7aa52 61 * The return result is in 34.30 format.
emilmont 1:fdd22bb7aa52 62 */
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 void arm_dot_prod_q15(
emilmont 1:fdd22bb7aa52 65 q15_t * pSrcA,
emilmont 1:fdd22bb7aa52 66 q15_t * pSrcB,
emilmont 1:fdd22bb7aa52 67 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 68 q63_t * result)
emilmont 1:fdd22bb7aa52 69 {
emilmont 1:fdd22bb7aa52 70 q63_t sum = 0; /* Temporary result storage */
emilmont 1:fdd22bb7aa52 71 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 72
emilmont 1:fdd22bb7aa52 73 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 79 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 82 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 83 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 84 {
emilmont 1:fdd22bb7aa52 85 /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
emilmont 1:fdd22bb7aa52 86 /* Calculate dot product and then store the result in a temporary buffer. */
emilmont 1:fdd22bb7aa52 87 sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
emilmont 1:fdd22bb7aa52 88 sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
emilmont 1:fdd22bb7aa52 89
emilmont 1:fdd22bb7aa52 90 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 91 blkCnt--;
emilmont 1:fdd22bb7aa52 92 }
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 95 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 96 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 97
emilmont 1:fdd22bb7aa52 98 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 99 {
emilmont 1:fdd22bb7aa52 100 /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
emilmont 1:fdd22bb7aa52 101 /* Calculate dot product and then store the results in a temporary buffer. */
emilmont 1:fdd22bb7aa52 102 sum = __SMLALD(*pSrcA++, *pSrcB++, sum);
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 105 blkCnt--;
emilmont 1:fdd22bb7aa52 106 }
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 #else
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 114 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 117 {
emilmont 1:fdd22bb7aa52 118 /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
emilmont 1:fdd22bb7aa52 119 /* Calculate dot product and then store the results in a temporary buffer. */
emilmont 1:fdd22bb7aa52 120 sum += (q63_t) ((q31_t) * pSrcA++ * *pSrcB++);
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 123 blkCnt--;
emilmont 1:fdd22bb7aa52 124 }
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 /* Store the result in the destination buffer in 34.30 format */
emilmont 1:fdd22bb7aa52 129 *result = sum;
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 }
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 /**
emilmont 1:fdd22bb7aa52 134 * @} end of dot_prod group
emilmont 1:fdd22bb7aa52 135 */