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_scale_q7.c | 110 +++++++++++++-------------- 1 file changed, 51 insertions(+), 59 deletions(-) (limited to 'DSP/Source/BasicMathFunctions/arm_scale_q7.c') diff --git a/DSP/Source/BasicMathFunctions/arm_scale_q7.c b/DSP/Source/BasicMathFunctions/arm_scale_q7.c index 6cf1bbb..cb967d2 100644 --- a/DSP/Source/BasicMathFunctions/arm_scale_q7.c +++ b/DSP/Source/BasicMathFunctions/arm_scale_q7.c @@ -3,13 +3,13 @@ * Title: arm_scale_q7.c * Description: Multiplies a Q7 vector by a scalar * - * $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 * @@ -29,109 +29,101 @@ #include "arm_math.h" /** - * @ingroup groupMath + @ingroup groupMath */ /** - * @addtogroup scale - * @{ + @addtogroup BasicScale + @{ */ /** - * @brief Multiplies a Q7 vector by a scalar. - * @param[in] *pSrc points to the input vector - * @param[in] scaleFract fractional portion of the scale value - * @param[in] shift number of bits to shift the result by - * @param[out] *pDst points to the output vector - * @param[in] blockSize number of samples in the vector - * @return none. - * - * Scaling and Overflow Behavior: - * \par - * The input data *pSrc and scaleFract are in 1.7 format. - * These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format. + @brief Multiplies a Q7 vector by a scalar. + @param[in] pSrc points to the input vector + @param[in] scaleFract fractional portion of the scale value + @param[in] shift number of bits to shift the result by + @param[out] pDst points to the output vector + @param[in] blockSize number of samples in each vector + @return none + + @par Scaling and Overflow Behavior + The input data *pSrc and scaleFract are in 1.7 format. + These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format. */ void arm_scale_q7( - q7_t * pSrc, - q7_t scaleFract, - int8_t shift, - q7_t * pDst, - uint32_t blockSize) + const q7_t * pSrc, + q7_t scaleFract, + int8_t shift, + q7_t * pDst, + uint32_t blockSize) { - int8_t kShift = 7 - shift; /* shift to apply after scaling */ - uint32_t blkCnt; /* loop counter */ - -#if defined (ARM_MATH_DSP) + uint32_t blkCnt; /* Loop counter */ + int8_t kShift = 7 - shift; /* Shift to apply after scaling */ -/* Run the below code for Cortex-M4 and Cortex-M3 */ - q7_t in1, in2, in3, in4, out1, out2, out3, out4; /* Temporary variables to store input & output */ +#if defined (ARM_MATH_LOOPUNROLL) +#if defined (ARM_MATH_DSP) + q7_t in1, in2, in3, in4; /* Temporary input variables */ + q7_t out1, out2, out3, out4; /* Temporary output variables */ +#endif - /*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 * scale */ + +#if defined (ARM_MATH_DSP) /* Reading 4 inputs from memory */ in1 = *pSrc++; in2 = *pSrc++; in3 = *pSrc++; in4 = *pSrc++; - /* C = A * scale */ - /* Scale the inputs and then store the results in the temporary variables. */ + /* Scale inputs and store result in the temporary variable. */ out1 = (q7_t) (__SSAT(((in1) * scaleFract) >> kShift, 8)); out2 = (q7_t) (__SSAT(((in2) * scaleFract) >> kShift, 8)); out3 = (q7_t) (__SSAT(((in3) * scaleFract) >> kShift, 8)); out4 = (q7_t) (__SSAT(((in4) * scaleFract) >> kShift, 8)); - /* Packing the individual outputs into 32bit and storing in - * destination buffer in single write */ - *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4); + /* Pack and store result in destination buffer (in single write) */ + write_q7x4_ia (&pDst, __PACKq7(out1, out2, out3, out4)); +#else + *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8)); + *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8)); + *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8)); + *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8)); +#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; - while (blkCnt > 0U) - { - /* C = A * scale */ - /* Scale the input and then store the result in the destination buffer. */ - *pDst++ = (q7_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 8)); - - /* Decrement the loop counter */ - blkCnt--; - } - #else - /* Run the below code for Cortex-M0 */ - /* Initialize blkCnt with number of samples */ blkCnt = blockSize; +#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ + while (blkCnt > 0U) { /* C = A * scale */ - /* Scale the input and then store the result in the destination buffer. */ - *pDst++ = (q7_t) (__SSAT((((q15_t) * pSrc++ * scaleFract) >> kShift), 8)); - /* Decrement the loop counter */ + /* Scale input and store result in destination buffer. */ + *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8)); + + /* Decrement loop counter */ blkCnt--; } -#endif /* #if defined (ARM_MATH_DSP) */ - } /** - * @} end of scale group + @} end of BasicScale group */ -- cgit