Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_trans_q15.c@2:da51fb522205, 2013-05-30 (annotated)

Committer:
emilmont
Date:
Thu May 30 17:10:11 2013 +0100
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
emilmont 1:fdd22bb7aa52 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
emilmont 1:fdd22bb7aa52 4 * $Date: 15. February 2012
emilmont 2:da51fb522205 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_mat_trans_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q15 matrix transpose.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
emilmont 1:fdd22bb7aa52 14 * Version 1.1.0 2012/02/15
emilmont 1:fdd22bb7aa52 15 * Updated with more optimizations, bug fixes and minor API changes.
emilmont 1:fdd22bb7aa52 16 *
emilmont 1:fdd22bb7aa52 17 * Version 1.0.10 2011/7/15
emilmont 1:fdd22bb7aa52 18 * Big Endian support added and Merged M0 and M3/M4 Source code.
emilmont 1:fdd22bb7aa52 19 *
emilmont 1:fdd22bb7aa52 20 * Version 1.0.3 2010/11/29
emilmont 1:fdd22bb7aa52 21 * Re-organized the CMSIS folders and updated documentation.
emilmont 1:fdd22bb7aa52 22 *
emilmont 1:fdd22bb7aa52 23 * Version 1.0.2 2010/11/11
emilmont 1:fdd22bb7aa52 24 * Documentation updated.
emilmont 1:fdd22bb7aa52 25 *
emilmont 1:fdd22bb7aa52 26 * Version 1.0.1 2010/10/05
emilmont 1:fdd22bb7aa52 27 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 28 *
emilmont 1:fdd22bb7aa52 29 * Version 1.0.0 2010/09/20
emilmont 1:fdd22bb7aa52 30 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 31 *
emilmont 1:fdd22bb7aa52 32 * Version 0.0.5 2010/04/26
emilmont 1:fdd22bb7aa52 33 * incorporated review comments and updated with latest CMSIS layer
emilmont 1:fdd22bb7aa52 34 *
emilmont 1:fdd22bb7aa52 35 * Version 0.0.3 2010/03/10
emilmont 1:fdd22bb7aa52 36 * Initial version
emilmont 1:fdd22bb7aa52 37 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 38
emilmont 1:fdd22bb7aa52 39 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 40
emilmont 1:fdd22bb7aa52 41 /**
emilmont 1:fdd22bb7aa52 42 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 43 */
emilmont 1:fdd22bb7aa52 44
emilmont 1:fdd22bb7aa52 45 /**
emilmont 1:fdd22bb7aa52 46 * @addtogroup MatrixTrans
emilmont 1:fdd22bb7aa52 47 * @{
emilmont 1:fdd22bb7aa52 48 */
emilmont 1:fdd22bb7aa52 49
emilmont 1:fdd22bb7aa52 50 /*
emilmont 1:fdd22bb7aa52 51 * @brief Q15 matrix transpose.
emilmont 1:fdd22bb7aa52 52 * @param[in] *pSrc points to the input matrix
emilmont 1:fdd22bb7aa52 53 * @param[out] *pDst points to the output matrix
emilmont 2:da51fb522205 54 * @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code>
emilmont 1:fdd22bb7aa52 55 * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 56 */
emilmont 1:fdd22bb7aa52 57
emilmont 1:fdd22bb7aa52 58 arm_status arm_mat_trans_q15(
emilmont 1:fdd22bb7aa52 59 const arm_matrix_instance_q15 * pSrc,
emilmont 1:fdd22bb7aa52 60 arm_matrix_instance_q15 * pDst)
emilmont 1:fdd22bb7aa52 61 {
emilmont 1:fdd22bb7aa52 62 q15_t *pSrcA = pSrc->pData; /* input data matrix pointer */
emilmont 1:fdd22bb7aa52 63 q15_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 64 uint16_t nRows = pSrc->numRows; /* number of nRows */
emilmont 1:fdd22bb7aa52 65 uint16_t nColumns = pSrc->numCols; /* number of nColumns */
emilmont 1:fdd22bb7aa52 66 uint16_t col, row = nRows, i = 0u; /* row and column loop counters */
emilmont 1:fdd22bb7aa52 67 arm_status status; /* status of matrix transpose */
emilmont 1:fdd22bb7aa52 68
emilmont 1:fdd22bb7aa52 69 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 70
emilmont 1:fdd22bb7aa52 71 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 72 #ifndef UNALIGNED_SUPPORT_DISABLE
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 q31_t in; /* variable to hold temporary output */
emilmont 1:fdd22bb7aa52 75
emilmont 1:fdd22bb7aa52 76 #else
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 q15_t in;
emilmont 1:fdd22bb7aa52 79
emilmont 2:da51fb522205 80 #endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 86 if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
emilmont 1:fdd22bb7aa52 87 {
emilmont 1:fdd22bb7aa52 88 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 89 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 90 }
emilmont 1:fdd22bb7aa52 91 else
emilmont 1:fdd22bb7aa52 92 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 {
emilmont 1:fdd22bb7aa52 95 /* Matrix transpose by exchanging the rows with columns */
emilmont 1:fdd22bb7aa52 96 /* row loop */
emilmont 1:fdd22bb7aa52 97 do
emilmont 1:fdd22bb7aa52 98 {
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 /* Apply loop unrolling and exchange the columns with row elements */
emilmont 1:fdd22bb7aa52 101 col = nColumns >> 2u;
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 /* The pointer pOut is set to starting address of the column being processed */
emilmont 1:fdd22bb7aa52 104 pOut = pDst->pData + i;
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 107 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 108 while(col > 0u)
emilmont 1:fdd22bb7aa52 109 {
emilmont 1:fdd22bb7aa52 110 #ifndef UNALIGNED_SUPPORT_DISABLE
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* Read two elements from the row */
emilmont 1:fdd22bb7aa52 113 in = *__SIMD32(pSrcA)++;
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* Unpack and store one element in the destination */
emilmont 1:fdd22bb7aa52 116 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 *pOut = (q15_t) in;
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 #else
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122 *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 123
emilmont 1:fdd22bb7aa52 124 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* Update the pointer pOut to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 127 pOut += nRows;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* Unpack and store the second element in the destination */
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 #else
emilmont 1:fdd22bb7aa52 136
emilmont 1:fdd22bb7aa52 137 *pOut = (q15_t) in;
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /* Update the pointer pOut to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 142 pOut += nRows;
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 /* Read two elements from the row */
emilmont 1:fdd22bb7aa52 145 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 in = *__SIMD32(pSrcA)++;
emilmont 1:fdd22bb7aa52 148
emilmont 1:fdd22bb7aa52 149 #else
emilmont 1:fdd22bb7aa52 150
emilmont 1:fdd22bb7aa52 151 in = *__SIMD32(pSrcA)++;
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* Unpack and store one element in the destination */
emilmont 1:fdd22bb7aa52 156 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 157
emilmont 1:fdd22bb7aa52 158 *pOut = (q15_t) in;
emilmont 1:fdd22bb7aa52 159
emilmont 1:fdd22bb7aa52 160 #else
emilmont 1:fdd22bb7aa52 161
emilmont 1:fdd22bb7aa52 162 *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 /* Update the pointer pOut to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 167 pOut += nRows;
emilmont 1:fdd22bb7aa52 168
emilmont 1:fdd22bb7aa52 169 /* Unpack and store the second element in the destination */
emilmont 1:fdd22bb7aa52 170 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 171
emilmont 1:fdd22bb7aa52 172 *pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 #else
emilmont 1:fdd22bb7aa52 175
emilmont 1:fdd22bb7aa52 176 *pOut = (q15_t) in;
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 179
emilmont 2:da51fb522205 180 #else
emilmont 1:fdd22bb7aa52 181 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 182 in = *pSrcA++;
emilmont 1:fdd22bb7aa52 183
emilmont 1:fdd22bb7aa52 184 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 185 *pOut = in;
emilmont 1:fdd22bb7aa52 186
emilmont 1:fdd22bb7aa52 187 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 188 pOut += nRows;
emilmont 1:fdd22bb7aa52 189
emilmont 1:fdd22bb7aa52 190 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 191 in = *pSrcA++;
emilmont 1:fdd22bb7aa52 192
emilmont 1:fdd22bb7aa52 193 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 194 *pOut = in;
emilmont 1:fdd22bb7aa52 195
emilmont 1:fdd22bb7aa52 196 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 197 pOut += nRows;
emilmont 1:fdd22bb7aa52 198
emilmont 1:fdd22bb7aa52 199 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 200 in = *pSrcA++;
emilmont 1:fdd22bb7aa52 201
emilmont 1:fdd22bb7aa52 202 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 203 *pOut = in;
emilmont 1:fdd22bb7aa52 204
emilmont 1:fdd22bb7aa52 205 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 206 pOut += nRows;
emilmont 1:fdd22bb7aa52 207
emilmont 1:fdd22bb7aa52 208 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 209 in = *pSrcA++;
emilmont 1:fdd22bb7aa52 210
emilmont 1:fdd22bb7aa52 211 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 212 *pOut = in;
emilmont 1:fdd22bb7aa52 213
emilmont 2:da51fb522205 214 #endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */
emilmont 1:fdd22bb7aa52 215
emilmont 1:fdd22bb7aa52 216 /* Update the pointer pOut to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 217 pOut += nRows;
emilmont 1:fdd22bb7aa52 218
emilmont 1:fdd22bb7aa52 219 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 220 col--;
emilmont 1:fdd22bb7aa52 221 }
emilmont 1:fdd22bb7aa52 222
emilmont 1:fdd22bb7aa52 223 /* Perform matrix transpose for last 3 samples here. */
emilmont 1:fdd22bb7aa52 224 col = nColumns % 0x4u;
emilmont 1:fdd22bb7aa52 225
emilmont 1:fdd22bb7aa52 226 #else
emilmont 1:fdd22bb7aa52 227
emilmont 1:fdd22bb7aa52 228 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 229
emilmont 1:fdd22bb7aa52 230 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 231
emilmont 1:fdd22bb7aa52 232 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 233 if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
emilmont 1:fdd22bb7aa52 234 {
emilmont 1:fdd22bb7aa52 235 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 236 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 237 }
emilmont 1:fdd22bb7aa52 238 else
emilmont 1:fdd22bb7aa52 239 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 240
emilmont 1:fdd22bb7aa52 241 {
emilmont 1:fdd22bb7aa52 242 /* Matrix transpose by exchanging the rows with columns */
emilmont 1:fdd22bb7aa52 243 /* row loop */
emilmont 1:fdd22bb7aa52 244 do
emilmont 1:fdd22bb7aa52 245 {
emilmont 1:fdd22bb7aa52 246 /* The pointer pOut is set to starting address of the column being processed */
emilmont 1:fdd22bb7aa52 247 pOut = pDst->pData + i;
emilmont 1:fdd22bb7aa52 248
emilmont 1:fdd22bb7aa52 249 /* Initialize column loop counter */
emilmont 1:fdd22bb7aa52 250 col = nColumns;
emilmont 1:fdd22bb7aa52 251
emilmont 1:fdd22bb7aa52 252 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 253
emilmont 1:fdd22bb7aa52 254 while(col > 0u)
emilmont 1:fdd22bb7aa52 255 {
emilmont 1:fdd22bb7aa52 256 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 257 *pOut = *pSrcA++;
emilmont 1:fdd22bb7aa52 258
emilmont 1:fdd22bb7aa52 259 /* Update the pointer pOut to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 260 pOut += nRows;
emilmont 1:fdd22bb7aa52 261
emilmont 1:fdd22bb7aa52 262 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 263 col--;
emilmont 1:fdd22bb7aa52 264 }
emilmont 1:fdd22bb7aa52 265
emilmont 1:fdd22bb7aa52 266 i++;
emilmont 1:fdd22bb7aa52 267
emilmont 1:fdd22bb7aa52 268 /* Decrement the row loop counter */
emilmont 1:fdd22bb7aa52 269 row--;
emilmont 1:fdd22bb7aa52 270
emilmont 1:fdd22bb7aa52 271 } while(row > 0u);
emilmont 1:fdd22bb7aa52 272
emilmont 1:fdd22bb7aa52 273 /* set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 274 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 275 }
emilmont 1:fdd22bb7aa52 276 /* Return to application */
emilmont 1:fdd22bb7aa52 277 return (status);
emilmont 1:fdd22bb7aa52 278 }
emilmont 1:fdd22bb7aa52 279
emilmont 1:fdd22bb7aa52 280 /**
emilmont 1:fdd22bb7aa52 281 * @} end of MatrixTrans group
emilmont 1:fdd22bb7aa52 282 */