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_abs_q7.c | 139 +++++++++++++---------------- 1 file changed, 64 insertions(+), 75 deletions(-) (limited to 'DSP/Source/BasicMathFunctions/arm_abs_q7.c') diff --git a/DSP/Source/BasicMathFunctions/arm_abs_q7.c b/DSP/Source/BasicMathFunctions/arm_abs_q7.c index d0acbfc..a6c4a6c 100644 --- a/DSP/Source/BasicMathFunctions/arm_abs_q7.c +++ b/DSP/Source/BasicMathFunctions/arm_abs_q7.c @@ -3,13 +3,13 @@ * Title: arm_abs_q7.c * Description: Q7 vector absolute value * - * $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 * @@ -29,117 +29,106 @@ #include "arm_math.h" /** - * @ingroup groupMath + @ingroup groupMath */ /** - * @addtogroup BasicAbs - * @{ + @addtogroup BasicAbs + @{ */ /** - * @brief Q7 vector absolute value. - * @param[in] *pSrc points to the input buffer - * @param[out] *pDst points to the output buffer - * @param[in] blockSize number of samples in each vector - * @return none. - * - * \par Conditions for optimum performance - * Input and output buffers should be aligned by 32-bit - * - * - * Scaling and Overflow Behavior: - * \par - * The function uses saturating arithmetic. - * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F. + @brief Q7 vector absolute value. + @param[in] pSrc points to the input vector + @param[out] pDst points to the output vector + @param[in] blockSize number of samples in each vector + @return none + + @par Conditions for optimum performance + Input and output buffers should be aligned by 32-bit + @par Scaling and Overflow Behavior + The function uses saturating arithmetic. + The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F. */ void arm_abs_q7( - q7_t * pSrc, - q7_t * pDst, - uint32_t blockSize) + const q7_t * pSrc, + q7_t * pDst, + uint32_t blockSize) { - uint32_t blkCnt; /* loop counter */ - q7_t in; /* Input value1 */ - -#if defined (ARM_MATH_DSP) + uint32_t blkCnt; /* Loop counter */ + q7_t in; /* Temporary input variable */ - /* Run the below code for Cortex-M4 and Cortex-M3 */ - q31_t in1, in2, in3, in4; /* temporary input variables */ - q31_t out1, out2, out3, out4; /* temporary output variables */ +#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| */ - /* Read inputs */ - in1 = (q31_t) * pSrc; - in2 = (q31_t) * (pSrc + 1); - in3 = (q31_t) * (pSrc + 2); - - /* find absolute value */ - out1 = (in1 > 0) ? in1 : (q31_t)__QSUB8(0, in1); - - /* read input */ - in4 = (q31_t) * (pSrc + 3); - - /* find absolute value */ - out2 = (in2 > 0) ? in2 : (q31_t)__QSUB8(0, in2); - /* store result to destination */ - *pDst = (q7_t) out1; - - /* find absolute value */ - out3 = (in3 > 0) ? in3 : (q31_t)__QSUB8(0, in3); - - /* find absolute value */ - out4 = (in4 > 0) ? in4 : (q31_t)__QSUB8(0, in4); - - /* store result to destination */ - *(pDst + 1) = (q7_t) out2; + /* Calculate absolute of input (if -1 then saturated to 0x7f) and store result in destination buffer. */ + in = *pSrc++; +#if defined (ARM_MATH_DSP) + *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in); +#else + *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in); +#endif - /* store result to destination */ - *(pDst + 2) = (q7_t) out3; + in = *pSrc++; +#if defined (ARM_MATH_DSP) + *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in); +#else + *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in); +#endif - /* store result to destination */ - *(pDst + 3) = (q7_t) out4; + in = *pSrc++; +#if defined (ARM_MATH_DSP) + *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in); +#else + *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in); +#endif - /* update pointers to process next samples */ - pSrc += 4U; - pDst += 4U; + in = *pSrc++; +#if defined (ARM_MATH_DSP) + *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in); +#else + *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in); +#endif - /* Decrement the loop counter */ + /* 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 /* #define ARM_MATH_CM0_FAMILY */ +#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ while (blkCnt > 0U) { /* C = |A| */ - /* Read the input */ - in = *pSrc++; - /* Store the Absolute result in the destination buffer */ - *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? 0x7f : -in); + /* Calculate absolute of input (if -1 then saturated to 0x7f) and store result in destination buffer. */ + in = *pSrc++; +#if defined (ARM_MATH_DSP) + *pDst++ = (in > 0) ? in : (q7_t) __QSUB(0, in); +#else + *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in); +#endif - /* Decrement the loop counter */ + /* Decrement loop counter */ blkCnt--; } + } /** - * @} end of BasicAbs group + @} end of BasicAbs group */ -- cgit