The CMSIS DSP 5 library
Dependents: Nucleo-Heart-Rate ejercicioVrms2 PROYECTOFINAL ejercicioVrms ... more
functions/MatrixFunctions/arm_mat_add_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_mat_add_f32.c |
xorjoep | 1:24714b45cd1b | 4 | * Description: Floating-point matrix addition |
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 groupMatrix |
xorjoep | 1:24714b45cd1b | 33 | */ |
xorjoep | 1:24714b45cd1b | 34 | |
xorjoep | 1:24714b45cd1b | 35 | /** |
xorjoep | 1:24714b45cd1b | 36 | * @defgroup MatrixAdd Matrix Addition |
xorjoep | 1:24714b45cd1b | 37 | * |
xorjoep | 1:24714b45cd1b | 38 | * Adds two matrices. |
xorjoep | 1:24714b45cd1b | 39 | * \image html MatrixAddition.gif "Addition of two 3 x 3 matrices" |
xorjoep | 1:24714b45cd1b | 40 | * |
xorjoep | 1:24714b45cd1b | 41 | * The functions check to make sure that |
xorjoep | 1:24714b45cd1b | 42 | * <code>pSrcA</code>, <code>pSrcB</code>, and <code>pDst</code> have the same |
xorjoep | 1:24714b45cd1b | 43 | * number of rows and columns. |
xorjoep | 1:24714b45cd1b | 44 | */ |
xorjoep | 1:24714b45cd1b | 45 | |
xorjoep | 1:24714b45cd1b | 46 | /** |
xorjoep | 1:24714b45cd1b | 47 | * @addtogroup MatrixAdd |
xorjoep | 1:24714b45cd1b | 48 | * @{ |
xorjoep | 1:24714b45cd1b | 49 | */ |
xorjoep | 1:24714b45cd1b | 50 | |
xorjoep | 1:24714b45cd1b | 51 | |
xorjoep | 1:24714b45cd1b | 52 | /** |
xorjoep | 1:24714b45cd1b | 53 | * @brief Floating-point matrix addition. |
xorjoep | 1:24714b45cd1b | 54 | * @param[in] *pSrcA points to the first input matrix structure |
xorjoep | 1:24714b45cd1b | 55 | * @param[in] *pSrcB points to the second input matrix structure |
xorjoep | 1:24714b45cd1b | 56 | * @param[out] *pDst points to output matrix structure |
xorjoep | 1:24714b45cd1b | 57 | * @return The function returns either |
xorjoep | 1:24714b45cd1b | 58 | * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking. |
xorjoep | 1:24714b45cd1b | 59 | */ |
xorjoep | 1:24714b45cd1b | 60 | |
xorjoep | 1:24714b45cd1b | 61 | arm_status arm_mat_add_f32( |
xorjoep | 1:24714b45cd1b | 62 | const arm_matrix_instance_f32 * pSrcA, |
xorjoep | 1:24714b45cd1b | 63 | const arm_matrix_instance_f32 * pSrcB, |
xorjoep | 1:24714b45cd1b | 64 | arm_matrix_instance_f32 * pDst) |
xorjoep | 1:24714b45cd1b | 65 | { |
xorjoep | 1:24714b45cd1b | 66 | float32_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */ |
xorjoep | 1:24714b45cd1b | 67 | float32_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */ |
xorjoep | 1:24714b45cd1b | 68 | float32_t *pOut = pDst->pData; /* output data matrix pointer */ |
xorjoep | 1:24714b45cd1b | 69 | |
xorjoep | 1:24714b45cd1b | 70 | #if defined (ARM_MATH_DSP) |
xorjoep | 1:24714b45cd1b | 71 | |
xorjoep | 1:24714b45cd1b | 72 | float32_t inA1, inA2, inB1, inB2, out1, out2; /* temporary variables */ |
xorjoep | 1:24714b45cd1b | 73 | |
xorjoep | 1:24714b45cd1b | 74 | #endif // #if defined (ARM_MATH_DSP) |
xorjoep | 1:24714b45cd1b | 75 | |
xorjoep | 1:24714b45cd1b | 76 | uint32_t numSamples; /* total number of elements in the matrix */ |
xorjoep | 1:24714b45cd1b | 77 | uint32_t blkCnt; /* loop counters */ |
xorjoep | 1:24714b45cd1b | 78 | arm_status status; /* status of matrix addition */ |
xorjoep | 1:24714b45cd1b | 79 | |
xorjoep | 1:24714b45cd1b | 80 | #ifdef ARM_MATH_MATRIX_CHECK |
xorjoep | 1:24714b45cd1b | 81 | /* Check for matrix mismatch condition */ |
xorjoep | 1:24714b45cd1b | 82 | if ((pSrcA->numRows != pSrcB->numRows) || |
xorjoep | 1:24714b45cd1b | 83 | (pSrcA->numCols != pSrcB->numCols) || |
xorjoep | 1:24714b45cd1b | 84 | (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols)) |
xorjoep | 1:24714b45cd1b | 85 | { |
xorjoep | 1:24714b45cd1b | 86 | /* Set status as ARM_MATH_SIZE_MISMATCH */ |
xorjoep | 1:24714b45cd1b | 87 | status = ARM_MATH_SIZE_MISMATCH; |
xorjoep | 1:24714b45cd1b | 88 | } |
xorjoep | 1:24714b45cd1b | 89 | else |
xorjoep | 1:24714b45cd1b | 90 | #endif |
xorjoep | 1:24714b45cd1b | 91 | { |
xorjoep | 1:24714b45cd1b | 92 | |
xorjoep | 1:24714b45cd1b | 93 | /* Total number of samples in the input matrix */ |
xorjoep | 1:24714b45cd1b | 94 | numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols; |
xorjoep | 1:24714b45cd1b | 95 | |
xorjoep | 1:24714b45cd1b | 96 | #if defined (ARM_MATH_DSP) |
xorjoep | 1:24714b45cd1b | 97 | |
xorjoep | 1:24714b45cd1b | 98 | /* Loop unrolling */ |
xorjoep | 1:24714b45cd1b | 99 | blkCnt = numSamples >> 2U; |
xorjoep | 1:24714b45cd1b | 100 | |
xorjoep | 1:24714b45cd1b | 101 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
xorjoep | 1:24714b45cd1b | 102 | ** a second loop below computes the remaining 1 to 3 samples. */ |
xorjoep | 1:24714b45cd1b | 103 | while (blkCnt > 0U) |
xorjoep | 1:24714b45cd1b | 104 | { |
xorjoep | 1:24714b45cd1b | 105 | /* C(m,n) = A(m,n) + B(m,n) */ |
xorjoep | 1:24714b45cd1b | 106 | /* Add and then store the results in the destination buffer. */ |
xorjoep | 1:24714b45cd1b | 107 | /* Read values from source A */ |
xorjoep | 1:24714b45cd1b | 108 | inA1 = pIn1[0]; |
xorjoep | 1:24714b45cd1b | 109 | |
xorjoep | 1:24714b45cd1b | 110 | /* Read values from source B */ |
xorjoep | 1:24714b45cd1b | 111 | inB1 = pIn2[0]; |
xorjoep | 1:24714b45cd1b | 112 | |
xorjoep | 1:24714b45cd1b | 113 | /* Read values from source A */ |
xorjoep | 1:24714b45cd1b | 114 | inA2 = pIn1[1]; |
xorjoep | 1:24714b45cd1b | 115 | |
xorjoep | 1:24714b45cd1b | 116 | /* out = sourceA + sourceB */ |
xorjoep | 1:24714b45cd1b | 117 | out1 = inA1 + inB1; |
xorjoep | 1:24714b45cd1b | 118 | |
xorjoep | 1:24714b45cd1b | 119 | /* Read values from source B */ |
xorjoep | 1:24714b45cd1b | 120 | inB2 = pIn2[1]; |
xorjoep | 1:24714b45cd1b | 121 | |
xorjoep | 1:24714b45cd1b | 122 | /* Read values from source A */ |
xorjoep | 1:24714b45cd1b | 123 | inA1 = pIn1[2]; |
xorjoep | 1:24714b45cd1b | 124 | |
xorjoep | 1:24714b45cd1b | 125 | /* out = sourceA + sourceB */ |
xorjoep | 1:24714b45cd1b | 126 | out2 = inA2 + inB2; |
xorjoep | 1:24714b45cd1b | 127 | |
xorjoep | 1:24714b45cd1b | 128 | /* Read values from source B */ |
xorjoep | 1:24714b45cd1b | 129 | inB1 = pIn2[2]; |
xorjoep | 1:24714b45cd1b | 130 | |
xorjoep | 1:24714b45cd1b | 131 | /* Store result in destination */ |
xorjoep | 1:24714b45cd1b | 132 | pOut[0] = out1; |
xorjoep | 1:24714b45cd1b | 133 | pOut[1] = out2; |
xorjoep | 1:24714b45cd1b | 134 | |
xorjoep | 1:24714b45cd1b | 135 | /* Read values from source A */ |
xorjoep | 1:24714b45cd1b | 136 | inA2 = pIn1[3]; |
xorjoep | 1:24714b45cd1b | 137 | |
xorjoep | 1:24714b45cd1b | 138 | /* Read values from source B */ |
xorjoep | 1:24714b45cd1b | 139 | inB2 = pIn2[3]; |
xorjoep | 1:24714b45cd1b | 140 | |
xorjoep | 1:24714b45cd1b | 141 | /* out = sourceA + sourceB */ |
xorjoep | 1:24714b45cd1b | 142 | out1 = inA1 + inB1; |
xorjoep | 1:24714b45cd1b | 143 | |
xorjoep | 1:24714b45cd1b | 144 | /* out = sourceA + sourceB */ |
xorjoep | 1:24714b45cd1b | 145 | out2 = inA2 + inB2; |
xorjoep | 1:24714b45cd1b | 146 | |
xorjoep | 1:24714b45cd1b | 147 | /* Store result in destination */ |
xorjoep | 1:24714b45cd1b | 148 | pOut[2] = out1; |
xorjoep | 1:24714b45cd1b | 149 | |
xorjoep | 1:24714b45cd1b | 150 | /* Store result in destination */ |
xorjoep | 1:24714b45cd1b | 151 | pOut[3] = out2; |
xorjoep | 1:24714b45cd1b | 152 | |
xorjoep | 1:24714b45cd1b | 153 | |
xorjoep | 1:24714b45cd1b | 154 | /* update pointers to process next sampels */ |
xorjoep | 1:24714b45cd1b | 155 | pIn1 += 4U; |
xorjoep | 1:24714b45cd1b | 156 | pIn2 += 4U; |
xorjoep | 1:24714b45cd1b | 157 | pOut += 4U; |
xorjoep | 1:24714b45cd1b | 158 | /* Decrement the loop counter */ |
xorjoep | 1:24714b45cd1b | 159 | blkCnt--; |
xorjoep | 1:24714b45cd1b | 160 | } |
xorjoep | 1:24714b45cd1b | 161 | |
xorjoep | 1:24714b45cd1b | 162 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. |
xorjoep | 1:24714b45cd1b | 163 | ** No loop unrolling is used. */ |
xorjoep | 1:24714b45cd1b | 164 | blkCnt = numSamples % 0x4U; |
xorjoep | 1:24714b45cd1b | 165 | |
xorjoep | 1:24714b45cd1b | 166 | #else |
xorjoep | 1:24714b45cd1b | 167 | |
xorjoep | 1:24714b45cd1b | 168 | /* Run the below code for Cortex-M0 */ |
xorjoep | 1:24714b45cd1b | 169 | |
xorjoep | 1:24714b45cd1b | 170 | /* Initialize blkCnt with number of samples */ |
xorjoep | 1:24714b45cd1b | 171 | blkCnt = numSamples; |
xorjoep | 1:24714b45cd1b | 172 | |
xorjoep | 1:24714b45cd1b | 173 | #endif /* #if defined (ARM_MATH_DSP) */ |
xorjoep | 1:24714b45cd1b | 174 | |
xorjoep | 1:24714b45cd1b | 175 | while (blkCnt > 0U) |
xorjoep | 1:24714b45cd1b | 176 | { |
xorjoep | 1:24714b45cd1b | 177 | /* C(m,n) = A(m,n) + B(m,n) */ |
xorjoep | 1:24714b45cd1b | 178 | /* Add and then store the results in the destination buffer. */ |
xorjoep | 1:24714b45cd1b | 179 | *pOut++ = (*pIn1++) + (*pIn2++); |
xorjoep | 1:24714b45cd1b | 180 | |
xorjoep | 1:24714b45cd1b | 181 | /* Decrement the loop counter */ |
xorjoep | 1:24714b45cd1b | 182 | blkCnt--; |
xorjoep | 1:24714b45cd1b | 183 | } |
xorjoep | 1:24714b45cd1b | 184 | |
xorjoep | 1:24714b45cd1b | 185 | /* set status as ARM_MATH_SUCCESS */ |
xorjoep | 1:24714b45cd1b | 186 | status = ARM_MATH_SUCCESS; |
xorjoep | 1:24714b45cd1b | 187 | |
xorjoep | 1:24714b45cd1b | 188 | } |
xorjoep | 1:24714b45cd1b | 189 | |
xorjoep | 1:24714b45cd1b | 190 | /* Return to application */ |
xorjoep | 1:24714b45cd1b | 191 | return (status); |
xorjoep | 1:24714b45cd1b | 192 | } |
xorjoep | 1:24714b45cd1b | 193 | |
xorjoep | 1:24714b45cd1b | 194 | /** |
xorjoep | 1:24714b45cd1b | 195 | * @} end of MatrixAdd group |
xorjoep | 1:24714b45cd1b | 196 | */ |