| 提交 | 用户 | age | ||
| bfc108 | 1 | /* ---------------------------------------------------------------------- |
| Q | 2 | * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
| 3 | * | |
| 4 | * $Date: 19. March 2015 | |
| 5 | * $Revision: V.1.4.5 | |
| 6 | * | |
| 7 | * Project: CMSIS DSP Library | |
| 8 | * Title: arm_mat_trans_q15.c | |
| 9 | * | |
| 10 | * Description: Q15 matrix transpose. | |
| 11 | * | |
| 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 | |
| 13 | * | |
| 14 | * Redistribution and use in source and binary forms, with or without | |
| 15 | * modification, are permitted provided that the following conditions | |
| 16 | * are met: | |
| 17 | * - Redistributions of source code must retain the above copyright | |
| 18 | * notice, this list of conditions and the following disclaimer. | |
| 19 | * - Redistributions in binary form must reproduce the above copyright | |
| 20 | * notice, this list of conditions and the following disclaimer in | |
| 21 | * the documentation and/or other materials provided with the | |
| 22 | * distribution. | |
| 23 | * - Neither the name of ARM LIMITED nor the names of its contributors | |
| 24 | * may be used to endorse or promote products derived from this | |
| 25 | * software without specific prior written permission. | |
| 26 | * | |
| 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
| 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
| 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS | |
| 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE | |
| 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, | |
| 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, | |
| 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | |
| 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER | |
| 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT | |
| 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN | |
| 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE | |
| 38 | * POSSIBILITY OF SUCH DAMAGE. | |
| 39 | * -------------------------------------------------------------------- */ | |
| 40 | ||
| 41 | #include "arm_math.h" | |
| 42 | ||
| 43 | /** | |
| 44 | * @ingroup groupMatrix | |
| 45 | */ | |
| 46 | ||
| 47 | /** | |
| 48 | * @addtogroup MatrixTrans | |
| 49 | * @{ | |
| 50 | */ | |
| 51 | ||
| 52 | /* | |
| 53 | * @brief Q15 matrix transpose. | |
| 54 | * @param[in] *pSrc points to the input matrix | |
| 55 | * @param[out] *pDst points to the output matrix | |
| 56 | * @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code> | |
| 57 | * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking. | |
| 58 | */ | |
| 59 | ||
| 60 | arm_status arm_mat_trans_q15( | |
| 61 | const arm_matrix_instance_q15 * pSrc, | |
| 62 | arm_matrix_instance_q15 * pDst) | |
| 63 | { | |
| 64 | q15_t *pSrcA = pSrc->pData; /* input data matrix pointer */ | |
| 65 | q15_t *pOut = pDst->pData; /* output data matrix pointer */ | |
| 66 | uint16_t nRows = pSrc->numRows; /* number of nRows */ | |
| 67 | uint16_t nColumns = pSrc->numCols; /* number of nColumns */ | |
| 68 | uint16_t col, row = nRows, i = 0u; /* row and column loop counters */ | |
| 69 | arm_status status; /* status of matrix transpose */ | |
| 70 | ||
| 71 | #ifndef ARM_MATH_CM0_FAMILY | |
| 72 | ||
| 73 | /* Run the below code for Cortex-M4 and Cortex-M3 */ | |
| 74 | #ifndef UNALIGNED_SUPPORT_DISABLE | |
| 75 | ||
| 76 | q31_t in; /* variable to hold temporary output */ | |
| 77 | ||
| 78 | #else | |
| 79 | ||
| 80 | q15_t in; | |
| 81 | ||
| 82 | #endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ | |
| 83 | ||
| 84 | #ifdef ARM_MATH_MATRIX_CHECK | |
| 85 | ||
| 86 | ||
| 87 | /* Check for matrix mismatch condition */ | |
| 88 | if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows)) | |
| 89 | { | |
| 90 | /* Set status as ARM_MATH_SIZE_MISMATCH */ | |
| 91 | status = ARM_MATH_SIZE_MISMATCH; | |
| 92 | } | |
| 93 | else | |
| 94 | #endif /* #ifdef ARM_MATH_MATRIX_CHECK */ | |
| 95 | ||
| 96 | { | |
| 97 | /* Matrix transpose by exchanging the rows with columns */ | |
| 98 | /* row loop */ | |
| 99 | do | |
| 100 | { | |
| 101 | ||
| 102 | /* Apply loop unrolling and exchange the columns with row elements */ | |
| 103 | col = nColumns >> 2u; | |
| 104 | ||
| 105 | /* The pointer pOut is set to starting address of the column being processed */ | |
| 106 | pOut = pDst->pData + i; | |
| 107 | ||
| 108 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. | |
| 109 | ** a second loop below computes the remaining 1 to 3 samples. */ | |
| 110 | while(col > 0u) | |
| 111 | { | |
| 112 | #ifndef UNALIGNED_SUPPORT_DISABLE | |
| 113 | ||
| 114 | /* Read two elements from the row */ | |
| 115 | in = *__SIMD32(pSrcA)++; | |
| 116 | ||
| 117 | /* Unpack and store one element in the destination */ | |
| 118 | #ifndef ARM_MATH_BIG_ENDIAN | |
| 119 | ||
| 120 | *pOut = (q15_t) in; | |
| 121 | ||
| 122 | #else | |
| 123 | ||
| 124 | *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); | |
| 125 | ||
| 126 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ | |
| 127 | ||
| 128 | /* Update the pointer pOut to point to the next row of the transposed matrix */ | |
| 129 | pOut += nRows; | |
| 130 | ||
| 131 | /* Unpack and store the second element in the destination */ | |
| 132 | ||
| 133 | #ifndef ARM_MATH_BIG_ENDIAN | |
| 134 | ||
| 135 | *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); | |
| 136 | ||
| 137 | #else | |
| 138 | ||
| 139 | *pOut = (q15_t) in; | |
| 140 | ||
| 141 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ | |
| 142 | ||
| 143 | /* Update the pointer pOut to point to the next row of the transposed matrix */ | |
| 144 | pOut += nRows; | |
| 145 | ||
| 146 | /* Read two elements from the row */ | |
| 147 | #ifndef ARM_MATH_BIG_ENDIAN | |
| 148 | ||
| 149 | in = *__SIMD32(pSrcA)++; | |
| 150 | ||
| 151 | #else | |
| 152 | ||
| 153 | in = *__SIMD32(pSrcA)++; | |
| 154 | ||
| 155 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ | |
| 156 | ||
| 157 | /* Unpack and store one element in the destination */ | |
| 158 | #ifndef ARM_MATH_BIG_ENDIAN | |
| 159 | ||
| 160 | *pOut = (q15_t) in; | |
| 161 | ||
| 162 | #else | |
| 163 | ||
| 164 | *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); | |
| 165 | ||
| 166 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ | |
| 167 | ||
| 168 | /* Update the pointer pOut to point to the next row of the transposed matrix */ | |
| 169 | pOut += nRows; | |
| 170 | ||
| 171 | /* Unpack and store the second element in the destination */ | |
| 172 | #ifndef ARM_MATH_BIG_ENDIAN | |
| 173 | ||
| 174 | *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); | |
| 175 | ||
| 176 | #else | |
| 177 | ||
| 178 | *pOut = (q15_t) in; | |
| 179 | ||
| 180 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ | |
| 181 | ||
| 182 | #else | |
| 183 | /* Read one element from the row */ | |
| 184 | in = *pSrcA++; | |
| 185 | ||
| 186 | /* Store one element in the destination */ | |
| 187 | *pOut = in; | |
| 188 | ||
| 189 | /* Update the pointer px to point to the next row of the transposed matrix */ | |
| 190 | pOut += nRows; | |
| 191 | ||
| 192 | /* Read one element from the row */ | |
| 193 | in = *pSrcA++; | |
| 194 | ||
| 195 | /* Store one element in the destination */ | |
| 196 | *pOut = in; | |
| 197 | ||
| 198 | /* Update the pointer px to point to the next row of the transposed matrix */ | |
| 199 | pOut += nRows; | |
| 200 | ||
| 201 | /* Read one element from the row */ | |
| 202 | in = *pSrcA++; | |
| 203 | ||
| 204 | /* Store one element in the destination */ | |
| 205 | *pOut = in; | |
| 206 | ||
| 207 | /* Update the pointer px to point to the next row of the transposed matrix */ | |
| 208 | pOut += nRows; | |
| 209 | ||
| 210 | /* Read one element from the row */ | |
| 211 | in = *pSrcA++; | |
| 212 | ||
| 213 | /* Store one element in the destination */ | |
| 214 | *pOut = in; | |
| 215 | ||
| 216 | #endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ | |
| 217 | ||
| 218 | /* Update the pointer pOut to point to the next row of the transposed matrix */ | |
| 219 | pOut += nRows; | |
| 220 | ||
| 221 | /* Decrement the column loop counter */ | |
| 222 | col--; | |
| 223 | } | |
| 224 | ||
| 225 | /* Perform matrix transpose for last 3 samples here. */ | |
| 226 | col = nColumns % 0x4u; | |
| 227 | ||
| 228 | #else | |
| 229 | ||
| 230 | /* Run the below code for Cortex-M0 */ | |
| 231 | ||
| 232 | #ifdef ARM_MATH_MATRIX_CHECK | |
| 233 | ||
| 234 | /* Check for matrix mismatch condition */ | |
| 235 | if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows)) | |
| 236 | { | |
| 237 | /* Set status as ARM_MATH_SIZE_MISMATCH */ | |
| 238 | status = ARM_MATH_SIZE_MISMATCH; | |
| 239 | } | |
| 240 | else | |
| 241 | #endif /* #ifdef ARM_MATH_MATRIX_CHECK */ | |
| 242 | ||
| 243 | { | |
| 244 | /* Matrix transpose by exchanging the rows with columns */ | |
| 245 | /* row loop */ | |
| 246 | do | |
| 247 | { | |
| 248 | /* The pointer pOut is set to starting address of the column being processed */ | |
| 249 | pOut = pDst->pData + i; | |
| 250 | ||
| 251 | /* Initialize column loop counter */ | |
| 252 | col = nColumns; | |
| 253 | ||
| 254 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ | |
| 255 | ||
| 256 | while(col > 0u) | |
| 257 | { | |
| 258 | /* Read and store the input element in the destination */ | |
| 259 | *pOut = *pSrcA++; | |
| 260 | ||
| 261 | /* Update the pointer pOut to point to the next row of the transposed matrix */ | |
| 262 | pOut += nRows; | |
| 263 | ||
| 264 | /* Decrement the column loop counter */ | |
| 265 | col--; | |
| 266 | } | |
| 267 | ||
| 268 | i++; | |
| 269 | ||
| 270 | /* Decrement the row loop counter */ | |
| 271 | row--; | |
| 272 | ||
| 273 | } while(row > 0u); | |
| 274 | ||
| 275 | /* set status as ARM_MATH_SUCCESS */ | |
| 276 | status = ARM_MATH_SUCCESS; | |
| 277 | } | |
| 278 | /* Return to application */ | |
| 279 | return (status); | |
| 280 | } | |
| 281 | ||
| 282 | /** | |
| 283 | * @} end of MatrixTrans group | |
| 284 | */ | |
