From 96d6da4e252b06dcfdc041e7df23e86161c33007 Mon Sep 17 00:00:00 2001 From: rihab kouki Date: Tue, 28 Jul 2020 11:24:49 +0100 Subject: Official ARM version: v5.6.0 --- DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c | 110 ++++++++++------------- 1 file changed, 47 insertions(+), 63 deletions(-) (limited to 'DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c') diff --git a/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c b/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c index 67ae887..76cd577 100644 --- a/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c +++ b/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c @@ -3,13 +3,13 @@ * Title: arm_dot_prod_q31.c * Description: Q31 dot product * - * $Date: 27. January 2017 - * $Revision: V.1.5.1 + * $Date: 18. March 2019 + * $Revision: V1.6.0 * * Target Processor: Cortex-M cores * -------------------------------------------------------------------- */ /* - * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved. + * Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved. * * SPDX-License-Identifier: Apache-2.0 * @@ -29,103 +29,87 @@ #include "arm_math.h" /** - * @ingroup groupMath + @ingroup groupMath */ /** - * @addtogroup dot_prod - * @{ + @addtogroup BasicDotProd + @{ */ /** - * @brief Dot product of Q31 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. - * - * Scaling and Overflow Behavior: - * \par - * The intermediate multiplications are in 1.31 x 1.31 = 2.62 format and these - * are truncated to 2.48 format by discarding the lower 14 bits. - * The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format. - * There are 15 guard bits in the accumulator and there is no risk of overflow as long as - * the length of the vectors is less than 2^16 elements. - * The return result is in 16.48 format. + @brief Dot product of Q31 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 + + @par Scaling and Overflow Behavior + The intermediate multiplications are in 1.31 x 1.31 = 2.62 format and these + are truncated to 2.48 format by discarding the lower 14 bits. + The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format. + There are 15 guard bits in the accumulator and there is no risk of overflow as long as + the length of the vectors is less than 2^16 elements. + The return result is in 16.48 format. */ void arm_dot_prod_q31( - q31_t * pSrcA, - q31_t * pSrcB, - uint32_t blockSize, - q63_t * result) + const q31_t * pSrcA, + const q31_t * pSrcB, + uint32_t blockSize, + q63_t * result) { - q63_t sum = 0; /* Temporary result storage */ - uint32_t blkCnt; /* loop counter */ - - -#if defined (ARM_MATH_DSP) + uint32_t blkCnt; /* Loop counter */ + q63_t sum = 0; /* Temporary return variable */ -/* Run the below code for Cortex-M4 and Cortex-M3 */ - q31_t inA1, inA2, inA3, inA4; - q31_t inB1, inB2, inB3, inB4; +#if defined (ARM_MATH_LOOPUNROLL) - /*loop Unrolling */ + /* Loop unrolling: Compute 4 outputs at a time */ 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. */ - inA1 = *pSrcA++; - inA2 = *pSrcA++; - inA3 = *pSrcA++; - inA4 = *pSrcA++; - inB1 = *pSrcB++; - inB2 = *pSrcB++; - inB3 = *pSrcB++; - inB4 = *pSrcB++; - - sum += ((q63_t) inA1 * inB1) >> 14U; - sum += ((q63_t) inA2 * inB2) >> 14U; - sum += ((q63_t) inA3 * inB3) >> 14U; - sum += ((q63_t) inA4 * inB4) >> 14U; - - /* Decrement the loop counter */ + + /* Calculate dot product and store result in a temporary buffer. */ + sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U; + + sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U; + + sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U; + + sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U; + + /* Decrement loop counter */ blkCnt--; } - /* If the blockSize is not a multiple of 4, compute any remaining output samples here. - ** No loop unrolling is used. */ + /* Loop unrolling: Compute remaining outputs */ blkCnt = blockSize % 0x4U; #else - /* Run the below code for Cortex-M0 */ - /* Initialize blkCnt with number of samples */ blkCnt = blockSize; -#endif /* #if defined (ARM_MATH_DSP) */ - +#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ 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 += ((q63_t) * pSrcA++ * *pSrcB++) >> 14U; - /* Decrement the loop counter */ + /* Calculate dot product and store result in a temporary buffer. */ + sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U; + + /* Decrement loop counter */ blkCnt--; } - /* Store the result in the destination buffer in 16.48 format */ + /* Store result in destination buffer in 16.48 format */ *result = sum; } /** - * @} end of dot_prod group + @} end of BasicDotProd group */ -- cgit