From 9c59a184dba820975e5da6fcd5d248aee87f7e2f Mon Sep 17 00:00:00 2001 From: Clyne Sullivan Date: Sun, 2 Feb 2025 11:26:53 -0500 Subject: add l476 implementation --- .../DSP/Source/BasicMathFunctions/arm_negate_f32.c | 337 +++++++++------------ 1 file changed, 145 insertions(+), 192 deletions(-) (limited to 'Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_negate_f32.c') diff --git a/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_negate_f32.c b/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_negate_f32.c index 4f243cd..5b2268c 100644 --- a/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_negate_f32.c +++ b/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_negate_f32.c @@ -1,192 +1,145 @@ -/* ---------------------------------------------------------------------- - * Project: CMSIS DSP Library - * Title: arm_negate_f32.c - * Description: Negates floating-point vectors - * - * $Date: 23 April 2021 - * $Revision: V1.9.0 - * - * Target Processor: Cortex-M and Cortex-A cores - * -------------------------------------------------------------------- */ -/* - * Copyright (C) 2010-2021 ARM Limited or its affiliates. All rights reserved. - * - * SPDX-License-Identifier: Apache-2.0 - * - * Licensed under the Apache License, Version 2.0 (the License); you may - * not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an AS IS BASIS, WITHOUT - * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -#include "dsp/basic_math_functions.h" - -/** - @ingroup groupMath - */ - -/** - @defgroup BasicNegate Vector Negate - - Negates the elements of a vector. - - 
-      pDst[n] = -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 BasicNegate - @{ - */ - -/** - @brief Negates the elements of a floating-point vector. - @param[in] pSrc points to input vector. - @param[out] pDst points to output vector. - @param[in] blockSize number of samples in each vector. - @return none - */ - -#if defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) - -#include "arm_helium_utils.h" - -void arm_negate_f32( - const float32_t * pSrc, - float32_t * pDst, - uint32_t blockSize) -{ - uint32_t blkCnt; /* Loop counter */ - f32x4_t vec1; - f32x4_t res; - - - /* Compute 4 outputs at a time */ - blkCnt = blockSize >> 2U; - while (blkCnt > 0U) - { - /* C = |A| */ - - /* Calculate absolute values and then store the results in the destination buffer. */ - vec1 = vld1q(pSrc); - res = vnegq(vec1); - vst1q(pDst, res); - - /* Increment pointers */ - pSrc += 4; - pDst += 4; - - /* Decrement the loop counter */ - blkCnt--; - } - - /* Tail */ - blkCnt = blockSize & 0x3; - if (blkCnt > 0U) - { - /* C = |A| */ - mve_pred16_t p0 = vctp32q(blkCnt); - vec1 = vld1q((float32_t const *) pSrc); - vstrwq_p(pDst, vnegq(vec1), p0); - } - -} - -#else -void arm_negate_f32( - const float32_t * pSrc, - float32_t * pDst, - uint32_t blockSize) -{ - uint32_t blkCnt; /* Loop counter */ - -#if defined(ARM_MATH_NEON_EXPERIMENTAL) && !defined(ARM_MATH_AUTOVECTORIZE) - f32x4_t vec1; - f32x4_t res; - - /* Compute 4 outputs at a time */ - blkCnt = blockSize >> 2U; - - while (blkCnt > 0U) - { - /* C = -A */ - - /* Negate and then store the results in the destination buffer. */ - vec1 = vld1q_f32(pSrc); - res = vnegq_f32(vec1); - vst1q_f32(pDst, res); - - /* Increment pointers */ - pSrc += 4; - pDst += 4; - - /* Decrement the loop counter */ - blkCnt--; - } - - /* Tail */ - blkCnt = blockSize & 0x3; - -#else -#if defined (ARM_MATH_LOOPUNROLL) && !defined(ARM_MATH_AUTOVECTORIZE) - - /* Loop unrolling: Compute 4 outputs at a time */ - blkCnt = blockSize >> 2U; - - while (blkCnt > 0U) - { - /* C = -A */ - - /* Negate and store result in destination buffer. */ - *pDst++ = -*pSrc++; - - *pDst++ = -*pSrc++; - - *pDst++ = -*pSrc++; - - *pDst++ = -*pSrc++; - - /* Decrement loop counter */ - blkCnt--; - } - - /* Loop unrolling: Compute remaining outputs */ - blkCnt = blockSize % 0x4U; - -#else - - /* Initialize blkCnt with number of samples */ - blkCnt = blockSize; - -#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ -#endif /* #if defined(ARM_MATH_NEON_EXPERIMENTAL) */ - - while (blkCnt > 0U) - { - /* C = -A */ - - /* Negate and store result in destination buffer. */ - *pDst++ = -*pSrc++; - - /* Decrement loop counter */ - blkCnt--; - } - -} -#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */ - -/** - @} end of BasicNegate group - */ +/* ---------------------------------------------------------------------- + * Project: CMSIS DSP Library + * Title: arm_negate_f32.c + * Description: Negates floating-point vectors + * + * $Date: 18. March 2019 + * $Revision: V1.6.0 + * + * Target Processor: Cortex-M cores + * -------------------------------------------------------------------- */ +/* + * Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved. + * + * SPDX-License-Identifier: Apache-2.0 + * + * Licensed under the Apache License, Version 2.0 (the License); you may + * not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an AS IS BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +#include "arm_math.h" + +/** + @ingroup groupMath + */ + +/** + @defgroup BasicNegate Vector Negate + + Negates the elements of a vector. + + 
+      pDst[n] = -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 BasicNegate + @{ + */ + +/** + @brief Negates the elements of a floating-point vector. + @param[in] pSrc points to input vector. + @param[out] pDst points to output vector. + @param[in] blockSize number of samples in each vector. + @return none + */ + +void arm_negate_f32( + const float32_t * pSrc, + float32_t * pDst, + uint32_t blockSize) +{ + uint32_t blkCnt; /* Loop counter */ + +#if defined(ARM_MATH_NEON_EXPERIMENTAL) + float32x4_t vec1; + float32x4_t res; + + /* Compute 4 outputs at a time */ + blkCnt = blockSize >> 2U; + + while (blkCnt > 0U) + { + /* C = -A */ + + /* Negate and then store the results in the destination buffer. */ + vec1 = vld1q_f32(pSrc); + res = vnegq_f32(vec1); + vst1q_f32(pDst, res); + + /* Increment pointers */ + pSrc += 4; + pDst += 4; + + /* Decrement the loop counter */ + blkCnt--; + } + + /* Tail */ + blkCnt = blockSize & 0x3; + +#else +#if defined (ARM_MATH_LOOPUNROLL) + + /* Loop unrolling: Compute 4 outputs at a time */ + blkCnt = blockSize >> 2U; + + while (blkCnt > 0U) + { + /* C = -A */ + + /* Negate and store result in destination buffer. */ + *pDst++ = -*pSrc++; + + *pDst++ = -*pSrc++; + + *pDst++ = -*pSrc++; + + *pDst++ = -*pSrc++; + + /* Decrement loop counter */ + blkCnt--; + } + + /* Loop unrolling: Compute remaining outputs */ + blkCnt = blockSize % 0x4U; + +#else + + /* Initialize blkCnt with number of samples */ + blkCnt = blockSize; + +#endif /* #if defined (ARM_MATH_LOOPUNROLL) */ +#endif /* #if defined(ARM_MATH_NEON_EXPERIMENTAL) */ + + while (blkCnt > 0U) + { + /* C = -A */ + + /* Negate and store result in destination buffer. */ + *pDst++ = -*pSrc++; + + /* Decrement loop counter */ + blkCnt--; + } + +} + +/** + @} end of BasicNegate group + */ -- cgit v1.2.3