mbed official / mbed-dsp

CMSIS DSP library

Dependents:   performance_timer Surfboard_ gps2rtty Capstone ... more

Legacy Warning

This is an mbed 2 library. To learn more about mbed OS 5, visit the docs.

cmsis_dsp/BasicMathFunctions/arm_dot_prod_q7.c@1:fdd22bb7aa52, 2012-11-28 (annotated)

Committer:
emilmont
Date:
Wed Nov 28 12:30:09 2012 +0000
Revision:
1:fdd22bb7aa52
Child:
2:da51fb522205
DSP library code

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 1:fdd22bb7aa52 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 1:fdd22bb7aa52 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 * Title: arm_dot_prod_q7.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Q7 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 Q7 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 1.7 x 1.7 = 2.14 format and these
emilmont 1:fdd22bb7aa52 58 * results are added to an accumulator in 18.14 format.
emilmont 1:fdd22bb7aa52 59 * Nonsaturating additions are used and there is no danger of wrap around as long as
emilmont 1:fdd22bb7aa52 60 * the vectors are less than 2^18 elements long.
emilmont 1:fdd22bb7aa52 61 * The return result is in 18.14 format.
emilmont 1:fdd22bb7aa52 62 */
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 void arm_dot_prod_q7(
emilmont 1:fdd22bb7aa52 65 q7_t * pSrcA,
emilmont 1:fdd22bb7aa52 66 q7_t * pSrcB,
emilmont 1:fdd22bb7aa52 67 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 68 q31_t * result)
emilmont 1:fdd22bb7aa52 69 {
emilmont 1:fdd22bb7aa52 70 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 71
emilmont 1:fdd22bb7aa52 72 q31_t sum = 0; /* Temporary variables to store output */
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 75
emilmont 1:fdd22bb7aa52 76 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 q31_t input1, input2; /* Temporary variables to store input */
emilmont 1:fdd22bb7aa52 79 q31_t inA1, inA2, inB1, inB2; /* Temporary variables to store input */
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 84 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 85
emilmont 1:fdd22bb7aa52 86 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 87 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 88 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 89 {
emilmont 1:fdd22bb7aa52 90 /* read 4 samples at a time from sourceA */
emilmont 1:fdd22bb7aa52 91 input1 = *__SIMD32(pSrcA)++;
emilmont 1:fdd22bb7aa52 92 /* read 4 samples at a time from sourceB */
emilmont 1:fdd22bb7aa52 93 input2 = *__SIMD32(pSrcB)++;
emilmont 1:fdd22bb7aa52 94
emilmont 1:fdd22bb7aa52 95 /* extract two q7_t samples to q15_t samples */
emilmont 1:fdd22bb7aa52 96 inA1 = __SXTB16(__ROR(input1, 8));
emilmont 1:fdd22bb7aa52 97 /* extract reminaing two samples */
emilmont 1:fdd22bb7aa52 98 inA2 = __SXTB16(input1);
emilmont 1:fdd22bb7aa52 99 /* extract two q7_t samples to q15_t samples */
emilmont 1:fdd22bb7aa52 100 inB1 = __SXTB16(__ROR(input2, 8));
emilmont 1:fdd22bb7aa52 101 /* extract reminaing two samples */
emilmont 1:fdd22bb7aa52 102 inB2 = __SXTB16(input2);
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* multiply and accumulate two samples at a time */
emilmont 1:fdd22bb7aa52 105 sum = __SMLAD(inA1, inB1, sum);
emilmont 1:fdd22bb7aa52 106 sum = __SMLAD(inA2, inB2, sum);
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 109 blkCnt--;
emilmont 1:fdd22bb7aa52 110 }
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 113 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 114 blkCnt = blockSize % 0x4u;
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 /* Dot product and then store the results in a temporary buffer. */
emilmont 1:fdd22bb7aa52 120 sum = __SMLAD(*pSrcA++, *pSrcB++, sum);
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 #else
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 133 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 136 {
emilmont 1:fdd22bb7aa52 137 /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
emilmont 1:fdd22bb7aa52 138 /* Dot product and then store the results in a temporary buffer. */
emilmont 1:fdd22bb7aa52 139 sum += (q31_t) ((q15_t) * pSrcA++ * *pSrcB++);
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 142 blkCnt--;
emilmont 1:fdd22bb7aa52 143 }
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 /* Store the result in the destination buffer in 18.14 format */
emilmont 1:fdd22bb7aa52 149 *result = sum;
emilmont 1:fdd22bb7aa52 150 }
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 /**
emilmont 1:fdd22bb7aa52 153 * @} end of dot_prod group
emilmont 1:fdd22bb7aa52 154 */