The CMSIS DSP 5 library
Dependents: Nucleo-Heart-Rate ejercicioVrms2 PROYECTOFINAL ejercicioVrms ... more
functions/BasicMathFunctions/arm_dot_prod_f32.c@3:4098b9d3d571, 2018-06-21 (annotated)
- Committer:
- xorjoep
- Date:
- Thu Jun 21 11:56:27 2018 +0000
- Revision:
- 3:4098b9d3d571
- Parent:
- 1:24714b45cd1b
headers is a folder not a library
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
xorjoep | 1:24714b45cd1b | 1 | /* ---------------------------------------------------------------------- |
xorjoep | 1:24714b45cd1b | 2 | * Project: CMSIS DSP Library |
xorjoep | 1:24714b45cd1b | 3 | * Title: arm_dot_prod_f32.c |
xorjoep | 1:24714b45cd1b | 4 | * Description: Floating-point dot product |
xorjoep | 1:24714b45cd1b | 5 | * |
xorjoep | 1:24714b45cd1b | 6 | * $Date: 27. January 2017 |
xorjoep | 1:24714b45cd1b | 7 | * $Revision: V.1.5.1 |
xorjoep | 1:24714b45cd1b | 8 | * |
xorjoep | 1:24714b45cd1b | 9 | * Target Processor: Cortex-M cores |
xorjoep | 1:24714b45cd1b | 10 | * -------------------------------------------------------------------- */ |
xorjoep | 1:24714b45cd1b | 11 | /* |
xorjoep | 1:24714b45cd1b | 12 | * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved. |
xorjoep | 1:24714b45cd1b | 13 | * |
xorjoep | 1:24714b45cd1b | 14 | * SPDX-License-Identifier: Apache-2.0 |
xorjoep | 1:24714b45cd1b | 15 | * |
xorjoep | 1:24714b45cd1b | 16 | * Licensed under the Apache License, Version 2.0 (the License); you may |
xorjoep | 1:24714b45cd1b | 17 | * not use this file except in compliance with the License. |
xorjoep | 1:24714b45cd1b | 18 | * You may obtain a copy of the License at |
xorjoep | 1:24714b45cd1b | 19 | * |
xorjoep | 1:24714b45cd1b | 20 | * www.apache.org/licenses/LICENSE-2.0 |
xorjoep | 1:24714b45cd1b | 21 | * |
xorjoep | 1:24714b45cd1b | 22 | * Unless required by applicable law or agreed to in writing, software |
xorjoep | 1:24714b45cd1b | 23 | * distributed under the License is distributed on an AS IS BASIS, WITHOUT |
xorjoep | 1:24714b45cd1b | 24 | * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
xorjoep | 1:24714b45cd1b | 25 | * See the License for the specific language governing permissions and |
xorjoep | 1:24714b45cd1b | 26 | * limitations under the License. |
xorjoep | 1:24714b45cd1b | 27 | */ |
xorjoep | 1:24714b45cd1b | 28 | |
xorjoep | 1:24714b45cd1b | 29 | #include "arm_math.h" |
xorjoep | 1:24714b45cd1b | 30 | |
xorjoep | 1:24714b45cd1b | 31 | /** |
xorjoep | 1:24714b45cd1b | 32 | * @ingroup groupMath |
xorjoep | 1:24714b45cd1b | 33 | */ |
xorjoep | 1:24714b45cd1b | 34 | |
xorjoep | 1:24714b45cd1b | 35 | /** |
xorjoep | 1:24714b45cd1b | 36 | * @defgroup dot_prod Vector Dot Product |
xorjoep | 1:24714b45cd1b | 37 | * |
xorjoep | 1:24714b45cd1b | 38 | * Computes the dot product of two vectors. |
xorjoep | 1:24714b45cd1b | 39 | * The vectors are multiplied element-by-element and then summed. |
xorjoep | 1:24714b45cd1b | 40 | * |
xorjoep | 1:24714b45cd1b | 41 | * <pre> |
xorjoep | 1:24714b45cd1b | 42 | * sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1] |
xorjoep | 1:24714b45cd1b | 43 | * </pre> |
xorjoep | 1:24714b45cd1b | 44 | * |
xorjoep | 1:24714b45cd1b | 45 | * There are separate functions for floating-point, Q7, Q15, and Q31 data types. |
xorjoep | 1:24714b45cd1b | 46 | */ |
xorjoep | 1:24714b45cd1b | 47 | |
xorjoep | 1:24714b45cd1b | 48 | /** |
xorjoep | 1:24714b45cd1b | 49 | * @addtogroup dot_prod |
xorjoep | 1:24714b45cd1b | 50 | * @{ |
xorjoep | 1:24714b45cd1b | 51 | */ |
xorjoep | 1:24714b45cd1b | 52 | |
xorjoep | 1:24714b45cd1b | 53 | /** |
xorjoep | 1:24714b45cd1b | 54 | * @brief Dot product of floating-point vectors. |
xorjoep | 1:24714b45cd1b | 55 | * @param[in] *pSrcA points to the first input vector |
xorjoep | 1:24714b45cd1b | 56 | * @param[in] *pSrcB points to the second input vector |
xorjoep | 1:24714b45cd1b | 57 | * @param[in] blockSize number of samples in each vector |
xorjoep | 1:24714b45cd1b | 58 | * @param[out] *result output result returned here |
xorjoep | 1:24714b45cd1b | 59 | * @return none. |
xorjoep | 1:24714b45cd1b | 60 | */ |
xorjoep | 1:24714b45cd1b | 61 | |
xorjoep | 1:24714b45cd1b | 62 | |
xorjoep | 1:24714b45cd1b | 63 | void arm_dot_prod_f32( |
xorjoep | 1:24714b45cd1b | 64 | float32_t * pSrcA, |
xorjoep | 1:24714b45cd1b | 65 | float32_t * pSrcB, |
xorjoep | 1:24714b45cd1b | 66 | uint32_t blockSize, |
xorjoep | 1:24714b45cd1b | 67 | float32_t * result) |
xorjoep | 1:24714b45cd1b | 68 | { |
xorjoep | 1:24714b45cd1b | 69 | float32_t sum = 0.0f; /* Temporary result storage */ |
xorjoep | 1:24714b45cd1b | 70 | uint32_t blkCnt; /* loop counter */ |
xorjoep | 1:24714b45cd1b | 71 | |
xorjoep | 1:24714b45cd1b | 72 | |
xorjoep | 1:24714b45cd1b | 73 | #if defined (ARM_MATH_DSP) |
xorjoep | 1:24714b45cd1b | 74 | |
xorjoep | 1:24714b45cd1b | 75 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
xorjoep | 1:24714b45cd1b | 76 | /*loop Unrolling */ |
xorjoep | 1:24714b45cd1b | 77 | blkCnt = blockSize >> 2U; |
xorjoep | 1:24714b45cd1b | 78 | |
xorjoep | 1:24714b45cd1b | 79 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
xorjoep | 1:24714b45cd1b | 80 | ** a second loop below computes the remaining 1 to 3 samples. */ |
xorjoep | 1:24714b45cd1b | 81 | while (blkCnt > 0U) |
xorjoep | 1:24714b45cd1b | 82 | { |
xorjoep | 1:24714b45cd1b | 83 | /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */ |
xorjoep | 1:24714b45cd1b | 84 | /* Calculate dot product and then store the result in a temporary buffer */ |
xorjoep | 1:24714b45cd1b | 85 | sum += (*pSrcA++) * (*pSrcB++); |
xorjoep | 1:24714b45cd1b | 86 | sum += (*pSrcA++) * (*pSrcB++); |
xorjoep | 1:24714b45cd1b | 87 | sum += (*pSrcA++) * (*pSrcB++); |
xorjoep | 1:24714b45cd1b | 88 | sum += (*pSrcA++) * (*pSrcB++); |
xorjoep | 1:24714b45cd1b | 89 | |
xorjoep | 1:24714b45cd1b | 90 | /* Decrement the loop counter */ |
xorjoep | 1:24714b45cd1b | 91 | blkCnt--; |
xorjoep | 1:24714b45cd1b | 92 | } |
xorjoep | 1:24714b45cd1b | 93 | |
xorjoep | 1:24714b45cd1b | 94 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
xorjoep | 1:24714b45cd1b | 95 | ** No loop unrolling is used. */ |
xorjoep | 1:24714b45cd1b | 96 | blkCnt = blockSize % 0x4U; |
xorjoep | 1:24714b45cd1b | 97 | |
xorjoep | 1:24714b45cd1b | 98 | #else |
xorjoep | 1:24714b45cd1b | 99 | |
xorjoep | 1:24714b45cd1b | 100 | /* Run the below code for Cortex-M0 */ |
xorjoep | 1:24714b45cd1b | 101 | |
xorjoep | 1:24714b45cd1b | 102 | /* Initialize blkCnt with number of samples */ |
xorjoep | 1:24714b45cd1b | 103 | blkCnt = blockSize; |
xorjoep | 1:24714b45cd1b | 104 | |
xorjoep | 1:24714b45cd1b | 105 | #endif /* #if defined (ARM_MATH_DSP) */ |
xorjoep | 1:24714b45cd1b | 106 | |
xorjoep | 1:24714b45cd1b | 107 | |
xorjoep | 1:24714b45cd1b | 108 | while (blkCnt > 0U) |
xorjoep | 1:24714b45cd1b | 109 | { |
xorjoep | 1:24714b45cd1b | 110 | /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */ |
xorjoep | 1:24714b45cd1b | 111 | /* Calculate dot product and then store the result in a temporary buffer. */ |
xorjoep | 1:24714b45cd1b | 112 | sum += (*pSrcA++) * (*pSrcB++); |
xorjoep | 1:24714b45cd1b | 113 | |
xorjoep | 1:24714b45cd1b | 114 | /* Decrement the loop counter */ |
xorjoep | 1:24714b45cd1b | 115 | blkCnt--; |
xorjoep | 1:24714b45cd1b | 116 | } |
xorjoep | 1:24714b45cd1b | 117 | /* Store the result back in the destination buffer */ |
xorjoep | 1:24714b45cd1b | 118 | *result = sum; |
xorjoep | 1:24714b45cd1b | 119 | } |
xorjoep | 1:24714b45cd1b | 120 | |
xorjoep | 1:24714b45cd1b | 121 | /** |
xorjoep | 1:24714b45cd1b | 122 | * @} end of dot_prod group |
xorjoep | 1:24714b45cd1b | 123 | */ |