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/StatisticsFunctions/arm_rms_f32.c | 368 ++++++++++----------- 1 file changed, 176 insertions(+), 192 deletions(-) (limited to 'Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_rms_f32.c') diff --git a/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_rms_f32.c b/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_rms_f32.c index cb45752..4f316fb 100644 --- a/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_rms_f32.c +++ b/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_rms_f32.c @@ -1,192 +1,176 @@ -/* ---------------------------------------------------------------------- - * Project: CMSIS DSP Library - * Title: arm_rms_f32.c - * Description: Root mean square value of the elements of a floating-point vector - * - * $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/statistics_functions.h" - -/** - @ingroup groupStats - */ - -/** - @defgroup RMS Root mean square (RMS) - - Calculates the Root Mean Square of the elements in the input vector. - The underlying algorithm is used: - - 
-      Result = sqrt(((pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]) / blockSize));
-
- - There are separate functions for floating point, Q31, and Q15 data types. - */ - -/** - @addtogroup RMS - @{ - */ - -/** - @brief Root Mean Square of the elements of a floating-point vector. - @param[in] pSrc points to the input vector - @param[in] blockSize number of samples in input vector - @param[out] pResult root mean square value returned here - @return none - */ - -#if defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) -void arm_rms_f32( - const float32_t * pSrc, - uint32_t blockSize, - float32_t * pResult) -{ - float32_t pow = 0.0f; - - arm_power_f32(pSrc, blockSize, &pow); - - /* Compute Rms and store the result in the destination */ - arm_sqrt_f32(pow / (float32_t) blockSize, pResult); -} -#else -#if defined(ARM_MATH_NEON) && !defined(ARM_MATH_AUTOVECTORIZE) -void arm_rms_f32( - const float32_t * pSrc, - uint32_t blockSize, - float32_t * pResult) -{ - float32_t sum = 0.0f; /* accumulator */ - float32_t in; /* Temporary variable to store input value */ - uint32_t blkCnt; /* loop counter */ - - float32x4_t sumV = vdupq_n_f32(0.0f); /* Temporary result storage */ - float32x2_t sumV2; - float32x4_t inV; - - blkCnt = blockSize >> 2U; - - /* Compute 4 outputs at a time. - ** a second loop below computes the remaining 1 to 3 samples. */ - while (blkCnt > 0U) - { - /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ - /* Compute Power and then store the result in a temporary variable, sum. */ - inV = vld1q_f32(pSrc); - sumV = vmlaq_f32(sumV, inV, inV); - pSrc += 4; - - /* Decrement the loop counter */ - blkCnt--; - } - - sumV2 = vpadd_f32(vget_low_f32(sumV),vget_high_f32(sumV)); - sum = vget_lane_f32(sumV2, 0) + vget_lane_f32(sumV2, 1); - - /* 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[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ - /* compute power and then store the result in a temporary variable, sum. */ - in = *pSrc++; - sum += in * in; - - /* Decrement the loop counter */ - blkCnt--; - } - - /* Compute Rms and store the result in the destination */ - arm_sqrt_f32(sum / (float32_t) blockSize, pResult); -} -#else -void arm_rms_f32( - const float32_t * pSrc, - uint32_t blockSize, - float32_t * pResult) -{ - uint32_t blkCnt; /* Loop counter */ - float32_t sum = 0.0f; /* Temporary result storage */ - float32_t in; /* Temporary variable to store input value */ - -#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[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */ - - in = *pSrc++; - /* Compute sum of squares and store result in a temporary variable, sum. */ - sum += in * in; - - in = *pSrc++; - sum += in * in; - - in = *pSrc++; - sum += in * in; - - in = *pSrc++; - sum += in * in; - - /* 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) */ - - while (blkCnt > 0U) - { - /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */ - - in = *pSrc++; - /* Compute sum of squares and store result in a temporary variable. */ - sum += ( in * in); - - /* Decrement loop counter */ - blkCnt--; - } - - /* Compute Rms and store result in destination */ - arm_sqrt_f32(sum / (float32_t) blockSize, pResult); -} -#endif /* #if defined(ARM_MATH_NEON) */ -#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */ - -/** - @} end of RMS group - */ +/* ---------------------------------------------------------------------- + * Project: CMSIS DSP Library + * Title: arm_rms_f32.c + * Description: Root mean square value of the elements of a floating-point vector + * + * $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 groupStats + */ + +/** + @defgroup RMS Root mean square (RMS) + + Calculates the Root Mean Square of the elements in the input vector. + The underlying algorithm is used: + + 
+      Result = sqrt(((pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]) / blockSize));
+
+ + There are separate functions for floating point, Q31, and Q15 data types. + */ + +/** + @addtogroup RMS + @{ + */ + +/** + @brief Root Mean Square of the elements of a floating-point vector. + @param[in] pSrc points to the input vector + @param[in] blockSize number of samples in input vector + @param[out] pResult root mean square value returned here + @return none + */ +#if defined(ARM_MATH_NEON) +void arm_rms_f32( + const float32_t * pSrc, + uint32_t blockSize, + float32_t * pResult) +{ + float32_t sum = 0.0f; /* accumulator */ + float32_t in; /* Temporary variable to store input value */ + uint32_t blkCnt; /* loop counter */ + + float32x4_t sumV = vdupq_n_f32(0.0f); /* Temporary result storage */ + float32x2_t sumV2; + float32x4_t inV; + + blkCnt = blockSize >> 2U; + + /* Compute 4 outputs at a time. + ** a second loop below computes the remaining 1 to 3 samples. */ + while (blkCnt > 0U) + { + /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ + /* Compute Power and then store the result in a temporary variable, sum. */ + inV = vld1q_f32(pSrc); + sumV = vmlaq_f32(sumV, inV, inV); + pSrc += 4; + + /* Decrement the loop counter */ + blkCnt--; + } + + sumV2 = vpadd_f32(vget_low_f32(sumV),vget_high_f32(sumV)); + sum = sumV2[0] + sumV2[1]; + + /* 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[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ + /* compute power and then store the result in a temporary variable, sum. */ + in = *pSrc++; + sum += in * in; + + /* Decrement the loop counter */ + blkCnt--; + } + + /* Compute Rms and store the result in the destination */ + arm_sqrt_f32(sum / (float32_t) blockSize, pResult); +} +#else +void arm_rms_f32( + const float32_t * pSrc, + uint32_t blockSize, + float32_t * pResult) +{ + uint32_t blkCnt; /* Loop counter */ + float32_t sum = 0.0f; /* Temporary result storage */ + float32_t in; /* Temporary variable to store input value */ + +#if defined (ARM_MATH_LOOPUNROLL) + + /* Loop unrolling: Compute 4 outputs at a time */ + blkCnt = blockSize >> 2U; + + while (blkCnt > 0U) + { + /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */ + + in = *pSrc++; + /* Compute sum of squares and store result in a temporary variable, sum. */ + sum += in * in; + + in = *pSrc++; + sum += in * in; + + in = *pSrc++; + sum += in * in; + + in = *pSrc++; + sum += in * in; + + /* 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) */ + + while (blkCnt > 0U) + { + /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */ + + in = *pSrc++; + /* Compute sum of squares and store result in a temporary variable. */ + sum += ( in * in); + + /* Decrement loop counter */ + blkCnt--; + } + + /* Compute Rms and store result in destination */ + arm_sqrt_f32(sum / (float32_t) blockSize, pResult); +} +#endif /* #if defined(ARM_MATH_NEON) */ + +/** + @} end of RMS group + */ -- cgit v1.2.3