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_shift_q15.c | 213 +++++++++++--------------- 1 file changed, 89 insertions(+), 124 deletions(-) (limited to 'DSP/Source/BasicMathFunctions/arm_shift_q15.c') diff --git a/DSP/Source/BasicMathFunctions/arm_shift_q15.c b/DSP/Source/BasicMathFunctions/arm_shift_q15.c index d2cd037..8a15155 100644 --- a/DSP/Source/BasicMathFunctions/arm_shift_q15.c +++ b/DSP/Source/BasicMathFunctions/arm_shift_q15.c @@ -3,13 +3,13 @@ * Title: arm_shift_q15.c * Description: Shifts the elements of a Q15 vector by a specified number of bits * - * $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 * @@ -29,208 +29,173 @@ #include "arm_math.h" /** - * @ingroup groupMath + @ingroup groupMath */ /** - * @addtogroup shift - * @{ + @addtogroup BasicShift + @{ */ /** - * @brief Shifts the elements of a Q15 vector a specified number of bits. - * @param[in] *pSrc points to the input vector - * @param[in] shiftBits number of bits to shift. A positive value shifts left; a negative value shifts right. - * @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 function uses saturating arithmetic. - * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated. + @brief Shifts the elements of a Q15 vector a specified number of bits + @param[in] pSrc points to the input vector + @param[in] shiftBits number of bits to shift. A positive value shifts left; a negative value shifts right. + @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 function uses saturating arithmetic. + Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated. */ void arm_shift_q15( - q15_t * pSrc, - int8_t shiftBits, - q15_t * pDst, - uint32_t blockSize) + const q15_t * pSrc, + int8_t shiftBits, + q15_t * pDst, + uint32_t blockSize) { - uint32_t blkCnt; /* loop counter */ - uint8_t sign; /* Sign of shiftBits */ - -#if defined (ARM_MATH_DSP) - -/* Run the below code for Cortex-M4 and Cortex-M3 */ + uint32_t blkCnt; /* Loop counter */ + uint8_t sign = (shiftBits & 0x80); /* Sign of shiftBits */ - q15_t in1, in2; /* Temporary variables */ +#if defined (ARM_MATH_LOOPUNROLL) +#if defined (ARM_MATH_DSP) + q15_t in1, in2; /* Temporary input variables */ +#endif - /*loop Unrolling */ + /* Loop unrolling: Compute 4 outputs at a time */ blkCnt = blockSize >> 2U; - /* Getting the sign of shiftBits */ - sign = (shiftBits & 0x80); - /* If the shift value is positive then do right shift else left shift */ if (sign == 0U) { - /* 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) { - /* Read 2 inputs */ - in1 = *pSrc++; - in2 = *pSrc++; /* C = A << shiftBits */ - /* Shift the inputs and then store the results in the destination buffer. */ -#ifndef ARM_MATH_BIG_ENDIAN - *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16), - __SSAT((in2 << shiftBits), 16), 16); +#if defined (ARM_MATH_DSP) + /* read 2 samples from source */ + in1 = *pSrc++; + in2 = *pSrc++; + /* Shift the inputs and then store the results in the destination buffer. */ +#ifndef ARM_MATH_BIG_ENDIAN + write_q15x2_ia (&pDst, __PKHBT(__SSAT((in1 << shiftBits), 16), + __SSAT((in2 << shiftBits), 16), 16)); #else + write_q15x2_ia (&pDst, __PKHBT(__SSAT((in2 << shiftBits), 16), + __SSAT((in1 << shiftBits), 16), 16)); +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16), - __SSAT((in1 << shiftBits), 16), 16); - -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - + /* read 2 samples from source */ in1 = *pSrc++; in2 = *pSrc++; -#ifndef ARM_MATH_BIG_ENDIAN - - *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16), - __SSAT((in2 << shiftBits), 16), 16); - +#ifndef ARM_MATH_BIG_ENDIAN + write_q15x2_ia (&pDst, __PKHBT(__SSAT((in1 << shiftBits), 16), + __SSAT((in2 << shiftBits), 16), 16)); #else + write_q15x2_ia (&pDst, __PKHBT(__SSAT((in2 << shiftBits), 16), + __SSAT((in1 << shiftBits), 16), 16)); +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16), - __SSAT((in1 << shiftBits), 16), 16); - -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - - /* Decrement the loop counter */ - blkCnt--; - } - - /* If the blockSize is not a multiple of 4, compute any remaining output samples here. - ** No loop unrolling is used. */ - blkCnt = blockSize % 0x4U; - - while (blkCnt > 0U) - { - /* C = A << shiftBits */ - /* Shift and then store the results in the destination buffer. */ - *pDst++ = __SSAT((*pSrc++ << shiftBits), 16); +#else + *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16); + *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16); + *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16); + *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16); +#endif - /* Decrement the loop counter */ + /* Decrement loop counter */ blkCnt--; } } else { - /* 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) { - /* Read 2 inputs */ + /* C = A >> shiftBits */ + +#if defined (ARM_MATH_DSP) + /* read 2 samples from source */ in1 = *pSrc++; in2 = *pSrc++; - /* C = A >> shiftBits */ /* Shift the inputs and then store the results in the destination buffer. */ -#ifndef ARM_MATH_BIG_ENDIAN - - *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits), - (in2 >> -shiftBits), 16); - +#ifndef ARM_MATH_BIG_ENDIAN + write_q15x2_ia (&pDst, __PKHBT((in1 >> -shiftBits), + (in2 >> -shiftBits), 16)); #else + write_q15x2_ia (&pDst, __PKHBT((in2 >> -shiftBits), + (in1 >> -shiftBits), 16)); +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits), - (in1 >> -shiftBits), 16); - -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - + /* read 2 samples from source */ in1 = *pSrc++; in2 = *pSrc++; -#ifndef ARM_MATH_BIG_ENDIAN - - *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits), - (in2 >> -shiftBits), 16); - +#ifndef ARM_MATH_BIG_ENDIAN + write_q15x2_ia (&pDst, __PKHBT((in1 >> -shiftBits), + (in2 >> -shiftBits), 16)); #else + write_q15x2_ia (&pDst, __PKHBT((in2 >> -shiftBits), + (in1 >> -shiftBits), 16)); +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits), - (in1 >> -shiftBits), 16); - -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ - - /* Decrement the loop counter */ - blkCnt--; - } - - /* If the blockSize is not a multiple of 4, compute any remaining output samples here. - ** No loop unrolling is used. */ - blkCnt = blockSize % 0x4U; - - while (blkCnt > 0U) - { - /* C = A >> shiftBits */ - /* Shift the inputs and then store the results in the destination buffer. */ +#else + *pDst++ = (*pSrc++ >> -shiftBits); + *pDst++ = (*pSrc++ >> -shiftBits); + *pDst++ = (*pSrc++ >> -shiftBits); *pDst++ = (*pSrc++ >> -shiftBits); +#endif - /* Decrement the loop counter */ + /* Decrement loop counter */ blkCnt--; } } + /* Loop unrolling: Compute remaining outputs */ + blkCnt = blockSize % 0x4U; + #else - /* Run the below code for Cortex-M0 */ + /* Initialize blkCnt with number of samples */ + blkCnt = blockSize; - /* Getting the sign of shiftBits */ - sign = (shiftBits & 0x80); +#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ /* If the shift value is positive then do right shift else left shift */ if (sign == 0U) { - /* Initialize blkCnt with number of samples */ - blkCnt = blockSize; - while (blkCnt > 0U) { /* C = A << shiftBits */ - /* Shift and then store the results in the destination buffer. */ - *pDst++ = __SSAT(((q31_t) * pSrc++ << shiftBits), 16); - /* Decrement the loop counter */ + /* Shift input and store result in destination buffer. */ + *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16); + + /* Decrement loop counter */ blkCnt--; } } else { - /* Initialize blkCnt with number of samples */ - blkCnt = blockSize; - while (blkCnt > 0U) { /* C = A >> shiftBits */ - /* Shift the inputs and then store the results in the destination buffer. */ + + /* Shift input and store result in destination buffer. */ *pDst++ = (*pSrc++ >> -shiftBits); - /* Decrement the loop counter */ + /* Decrement loop counter */ blkCnt--; } } -#endif /* #if defined (ARM_MATH_DSP) */ - } /** - * @} end of shift group + @} end of BasicShift group */ -- cgit