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_f32.c | 143 +++++++++++++--------------- 1 file changed, 68 insertions(+), 75 deletions(-) (limited to 'DSP/Source/BasicMathFunctions/arm_abs_f32.c') diff --git a/DSP/Source/BasicMathFunctions/arm_abs_f32.c b/DSP/Source/BasicMathFunctions/arm_abs_f32.c index f88ef95..a7d2624 100644 --- a/DSP/Source/BasicMathFunctions/arm_abs_f32.c +++ b/DSP/Source/BasicMathFunctions/arm_abs_f32.c @@ -3,13 +3,13 @@ * Title: arm_abs_f32.c * Description: Floating-point 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 * @@ -30,124 +30,117 @@ #include /** - * @ingroup groupMath + @ingroup groupMath */ /** - * @defgroup BasicAbs Vector Absolute Value - * - * Computes the absolute value of a vector on an element-by-element basis. - * - * 
- *     pDst[n] = abs(pSrc[n]),   0 <= n < blockSize.
- *
- * - * The functions support in-place computation allowing the source and - * destination pointers to reference the same memory buffer. - * There are separate functions for floating-point, Q7, Q15, and Q31 data types. + @defgroup BasicAbs Vector Absolute Value + + Computes the absolute value of a vector on an element-by-element basis. + + 
+      pDst[n] = abs(pSrc[n]),   0 <= n < blockSize.
+
+ + The functions support in-place computation allowing the source and + destination pointers to reference the same memory buffer. + There are separate functions for floating-point, Q7, Q15, and Q31 data types. */ /** - * @addtogroup BasicAbs - * @{ + @addtogroup BasicAbs + @{ */ /** - * @brief Floating-point 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. + @brief Floating-point 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 */ void arm_abs_f32( - float32_t * pSrc, - float32_t * pDst, - uint32_t blockSize) + const float32_t * pSrc, + float32_t * pDst, + uint32_t blockSize) { - uint32_t blkCnt; /* loop counter */ - -#if defined (ARM_MATH_DSP) + uint32_t blkCnt; /* Loop counter */ - /* Run the below code for Cortex-M4 and Cortex-M3 */ - float32_t in1, in2, in3, in4; /* temporary variables */ - - /*loop Unrolling */ - 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| */ - /* Calculate absolute and then store the results in the destination buffer. */ - /* read sample from source */ - in1 = *pSrc; - in2 = *(pSrc + 1); - in3 = *(pSrc + 2); +#if defined(ARM_MATH_NEON) + float32x4_t vec1; + float32x4_t res; - /* find absolute value */ - in1 = fabsf(in1); + /* Compute 4 outputs at a time */ + blkCnt = blockSize >> 2U; - /* read sample from source */ - in4 = *(pSrc + 3); + while (blkCnt > 0U) + { + /* C = |A| */ - /* find absolute value */ - in2 = fabsf(in2); + /* Calculate absolute values and then store the results in the destination buffer. */ + vec1 = vld1q_f32(pSrc); + res = vabsq_f32(vec1); + vst1q_f32(pDst, res); - /* read sample from source */ - *pDst = in1; + /* Increment pointers */ + pSrc += 4; + pDst += 4; + + /* Decrement the loop counter */ + blkCnt--; + } - /* find absolute value */ - in3 = fabsf(in3); + /* Tail */ + blkCnt = blockSize & 0x3; - /* find absolute value */ - in4 = fabsf(in4); +#else +#if defined (ARM_MATH_LOOPUNROLL) - /* store result to destination */ - *(pDst + 1) = in2; + /* Loop unrolling: Compute 4 outputs at a time */ + blkCnt = blockSize >> 2U; - /* store result to destination */ - *(pDst + 2) = in3; + while (blkCnt > 0U) + { + /* C = |A| */ - /* store result to destination */ - *(pDst + 3) = in4; + /* Calculate absolute and store result in destination buffer. */ + *pDst++ = fabsf(*pSrc++); + *pDst++ = fabsf(*pSrc++); - /* Update source pointer to process next sampels */ - pSrc += 4U; + *pDst++ = fabsf(*pSrc++); - /* Update destination pointer to process next sampels */ - pDst += 4U; + *pDst++ = fabsf(*pSrc++); - /* 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 /* #if defined (ARM_MATH_DSP) */ +#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ +#endif /* #if defined(ARM_MATH_NEON) */ while (blkCnt > 0U) { /* C = |A| */ - /* Calculate absolute and then store the results in the destination buffer. */ + + /* Calculate absolute and store result in destination buffer. */ *pDst++ = fabsf(*pSrc++); - /* Decrement the loop counter */ + /* Decrement loop counter */ blkCnt--; } + } /** - * @} end of BasicAbs group + @} end of BasicAbs group */ -- cgit