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/MatrixFunctions/arm_mat_sub_q15.c | 112 +++++++++++++-------------- 1 file changed, 54 insertions(+), 58 deletions(-) (limited to 'DSP/Source/MatrixFunctions/arm_mat_sub_q15.c') diff --git a/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c b/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c index 28e659f..5d5e5d0 100644 --- a/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c +++ b/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c @@ -3,13 +3,13 @@ * Title: arm_mat_sub_q15.c * Description: Q15 Matrix subtraction * - * $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 * @@ -29,112 +29,108 @@ #include "arm_math.h" /** - * @ingroup groupMatrix + @ingroup groupMatrix */ /** - * @addtogroup MatrixSub - * @{ + @addtogroup MatrixSub + @{ */ /** - * @brief Q15 matrix subtraction. - * @param[in] *pSrcA points to the first input matrix structure - * @param[in] *pSrcB points to the second input matrix structure - * @param[out] *pDst points to output matrix structure - * @return The function returns either - * ARM_MATH_SIZE_MISMATCH or ARM_MATH_SUCCESS based on the outcome of size checking. - * - * Scaling and Overflow Behavior: - * \par - * The function uses saturating arithmetic. - * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated. + @brief Q15 matrix subtraction. + @param[in] pSrcA points to the first input matrix structure + @param[in] pSrcB points to the second input matrix structure + @param[out] pDst points to output matrix structure + @return execution status + - \ref ARM_MATH_SUCCESS : Operation successful + - \ref ARM_MATH_SIZE_MISMATCH : Matrix size check failed + + @par Scaling and Overflow Behavior + The function uses saturating arithmetic. + Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated. */ arm_status arm_mat_sub_q15( const arm_matrix_instance_q15 * pSrcA, const arm_matrix_instance_q15 * pSrcB, - arm_matrix_instance_q15 * pDst) + arm_matrix_instance_q15 * pDst) { - q15_t *pInA = pSrcA->pData; /* input data matrix pointer A */ - q15_t *pInB = pSrcB->pData; /* input data matrix pointer B */ - q15_t *pOut = pDst->pData; /* output data matrix pointer */ - uint32_t numSamples; /* total number of elements in the matrix */ - uint32_t blkCnt; /* loop counters */ - arm_status status; /* status of matrix subtraction */ + q15_t *pInA = pSrcA->pData; /* input data matrix pointer A */ + q15_t *pInB = pSrcB->pData; /* input data matrix pointer B */ + q15_t *pOut = pDst->pData; /* output data matrix pointer */ + uint32_t numSamples; /* total number of elements in the matrix */ + uint32_t blkCnt; /* loop counters */ + arm_status status; /* status of matrix subtraction */ #ifdef ARM_MATH_MATRIX_CHECK - /* Check for matrix mismatch condition */ if ((pSrcA->numRows != pSrcB->numRows) || - (pSrcA->numCols != pSrcB->numCols) || - (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols)) + (pSrcA->numCols != pSrcB->numCols) || + (pSrcA->numRows != pDst->numRows) || + (pSrcA->numCols != pDst->numCols) ) { /* Set status as ARM_MATH_SIZE_MISMATCH */ status = ARM_MATH_SIZE_MISMATCH; } else -#endif /* #ifdef ARM_MATH_MATRIX_CHECK */ +#endif /* #ifdef ARM_MATH_MATRIX_CHECK */ { - /* Total number of samples in the input matrix */ + /* Total number of samples in input matrix */ numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols; -#if defined (ARM_MATH_DSP) - - /* Run the below code for Cortex-M4 and Cortex-M3 */ +#if defined (ARM_MATH_LOOPUNROLL) - /* Apply loop unrolling */ + /* Loop unrolling: Compute 4 outputs at a time */ 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(m,n) = A(m,n) - B(m,n) */ - /* Subtract, Saturate and then store the results in the destination buffer. */ - *__SIMD32(pOut)++ = __QSUB16(*__SIMD32(pInA)++, *__SIMD32(pInB)++); - *__SIMD32(pOut)++ = __QSUB16(*__SIMD32(pInA)++, *__SIMD32(pInB)++); - /* Decrement the loop counter */ + /* Subtract, Saturate and store result in destination buffer. */ +#if defined (ARM_MATH_DSP) + write_q15x2_ia (&pOut, __QSUB16(read_q15x2_ia ((q15_t **) &pInA), read_q15x2_ia ((q15_t **) &pInB))); + write_q15x2_ia (&pOut, __QSUB16(read_q15x2_ia ((q15_t **) &pInA), read_q15x2_ia ((q15_t **) &pInB))); +#else + *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16); + *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16); + *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16); + *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16); +#endif + + /* 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 = numSamples % 0x4U; - while (blkCnt > 0U) - { - /* C(m,n) = A(m,n) - B(m,n) */ - /* Subtract and then store the results in the destination buffer. */ - *pOut++ = (q15_t) __QSUB16(*pInA++, *pInB++); - - /* Decrement the loop counter */ - blkCnt--; - } - #else - /* Run the below code for Cortex-M0 */ - /* Initialize blkCnt with number of samples */ blkCnt = numSamples; +#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ + while (blkCnt > 0U) { /* C(m,n) = A(m,n) - B(m,n) */ - /* Subtract and then store the results in the destination buffer. */ + + /* Subtract and store result in destination buffer. */ +#if defined (ARM_MATH_DSP) + *pOut++ = (q15_t) __QSUB16(*pInA++, *pInB++); +#else *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16); +#endif - /* Decrement the loop counter */ + /* Decrement loop counter */ blkCnt--; } -#endif /* #if defined (ARM_MATH_DSP) */ - /* Set status as ARM_MATH_SUCCESS */ status = ARM_MATH_SUCCESS; } @@ -144,5 +140,5 @@ arm_status arm_mat_sub_q15( } /** - * @} end of MatrixSub group + @} end of MatrixSub group */ -- cgit