Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_trans_f32.c@1:fdd22bb7aa52, 2012-11-28 (annotated)

Committer:
emilmont
Date:
Wed Nov 28 12:30:09 2012 +0000
Revision:
1:fdd22bb7aa52
Child:
2:da51fb522205
DSP library code

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 1:fdd22bb7aa52 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 1:fdd22bb7aa52 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 * Title: arm_mat_trans_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Floating-point 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 /**
emilmont 1:fdd22bb7aa52 40 * @defgroup MatrixTrans Matrix Transpose
emilmont 1:fdd22bb7aa52 41 *
emilmont 1:fdd22bb7aa52 42 * Tranposes a matrix.
emilmont 1:fdd22bb7aa52 43 * Transposing an <code>M x N</code> matrix flips it around the center diagonal and results in an <code>N x M</code> matrix.
emilmont 1:fdd22bb7aa52 44 * \image html MatrixTranspose.gif "Transpose of a 3 x 3 matrix"
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 48
emilmont 1:fdd22bb7aa52 49 /**
emilmont 1:fdd22bb7aa52 50 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 51 */
emilmont 1:fdd22bb7aa52 52
emilmont 1:fdd22bb7aa52 53 /**
emilmont 1:fdd22bb7aa52 54 * @addtogroup MatrixTrans
emilmont 1:fdd22bb7aa52 55 * @{
emilmont 1:fdd22bb7aa52 56 */
emilmont 1:fdd22bb7aa52 57
emilmont 1:fdd22bb7aa52 58 /**
emilmont 1:fdd22bb7aa52 59 * @brief Floating-point matrix transpose.
emilmont 1:fdd22bb7aa52 60 * @param[in] *pSrc points to the input matrix
emilmont 1:fdd22bb7aa52 61 * @param[out] *pDst points to the output matrix
emilmont 1:fdd22bb7aa52 62 * @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code>
emilmont 1:fdd22bb7aa52 63 * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 64 */
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66
emilmont 1:fdd22bb7aa52 67 arm_status arm_mat_trans_f32(
emilmont 1:fdd22bb7aa52 68 const arm_matrix_instance_f32 * pSrc,
emilmont 1:fdd22bb7aa52 69 arm_matrix_instance_f32 * pDst)
emilmont 1:fdd22bb7aa52 70 {
emilmont 1:fdd22bb7aa52 71 float32_t *pIn = pSrc->pData; /* input data matrix pointer */
emilmont 1:fdd22bb7aa52 72 float32_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 73 float32_t *px; /* Temporary output data matrix pointer */
emilmont 1:fdd22bb7aa52 74 uint16_t nRows = pSrc->numRows; /* number of rows */
emilmont 1:fdd22bb7aa52 75 uint16_t nColumns = pSrc->numCols; /* number of columns */
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 78
emilmont 1:fdd22bb7aa52 79 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 uint16_t blkCnt, i = 0u, row = nRows; /* loop counters */
emilmont 1:fdd22bb7aa52 82 arm_status status; /* status of matrix transpose */
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87
emilmont 1:fdd22bb7aa52 88 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 89 if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
emilmont 1:fdd22bb7aa52 90 {
emilmont 1:fdd22bb7aa52 91 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 92 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 93 }
emilmont 1:fdd22bb7aa52 94 else
emilmont 1:fdd22bb7aa52 95 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 96
emilmont 1:fdd22bb7aa52 97 {
emilmont 1:fdd22bb7aa52 98 /* Matrix transpose by exchanging the rows with columns */
emilmont 1:fdd22bb7aa52 99 /* row loop */
emilmont 1:fdd22bb7aa52 100 do
emilmont 1:fdd22bb7aa52 101 {
emilmont 1:fdd22bb7aa52 102 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 103 blkCnt = nColumns >> 2;
emilmont 1:fdd22bb7aa52 104
emilmont 1:fdd22bb7aa52 105 /* The pointer px is set to starting address of the column being processed */
emilmont 1:fdd22bb7aa52 106 px = pOut + i;
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 109 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 110 while(blkCnt > 0u) /* column loop */
emilmont 1:fdd22bb7aa52 111 {
emilmont 1:fdd22bb7aa52 112 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 113 *px = *pIn++;
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 116 px += nRows;
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 119 *px = *pIn++;
emilmont 1:fdd22bb7aa52 120
emilmont 1:fdd22bb7aa52 121 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 122 px += nRows;
emilmont 1:fdd22bb7aa52 123
emilmont 1:fdd22bb7aa52 124 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 125 *px = *pIn++;
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 128 px += nRows;
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 131 *px = *pIn++;
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 134 px += nRows;
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 137 blkCnt--;
emilmont 1:fdd22bb7aa52 138 }
emilmont 1:fdd22bb7aa52 139
emilmont 1:fdd22bb7aa52 140 /* Perform matrix transpose for last 3 samples here. */
emilmont 1:fdd22bb7aa52 141 blkCnt = nColumns % 0x4u;
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 144 {
emilmont 1:fdd22bb7aa52 145 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 146 *px = *pIn++;
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 149 px += nRows;
emilmont 1:fdd22bb7aa52 150
emilmont 1:fdd22bb7aa52 151 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 152 blkCnt--;
emilmont 1:fdd22bb7aa52 153 }
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 #else
emilmont 1:fdd22bb7aa52 156
emilmont 1:fdd22bb7aa52 157 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 uint16_t col, i = 0u, row = nRows; /* loop counters */
emilmont 1:fdd22bb7aa52 160 arm_status status; /* status of matrix transpose */
emilmont 1:fdd22bb7aa52 161
emilmont 1:fdd22bb7aa52 162
emilmont 1:fdd22bb7aa52 163 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 166 if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
emilmont 1:fdd22bb7aa52 167 {
emilmont 1:fdd22bb7aa52 168 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 169 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 170 }
emilmont 1:fdd22bb7aa52 171 else
emilmont 1:fdd22bb7aa52 172 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 {
emilmont 1:fdd22bb7aa52 175 /* Matrix transpose by exchanging the rows with columns */
emilmont 1:fdd22bb7aa52 176 /* row loop */
emilmont 1:fdd22bb7aa52 177 do
emilmont 1:fdd22bb7aa52 178 {
emilmont 1:fdd22bb7aa52 179 /* The pointer px is set to starting address of the column being processed */
emilmont 1:fdd22bb7aa52 180 px = pOut + i;
emilmont 1:fdd22bb7aa52 181
emilmont 1:fdd22bb7aa52 182 /* Initialize column loop counter */
emilmont 1:fdd22bb7aa52 183 col = nColumns;
emilmont 1:fdd22bb7aa52 184
emilmont 1:fdd22bb7aa52 185 while(col > 0u)
emilmont 1:fdd22bb7aa52 186 {
emilmont 1:fdd22bb7aa52 187 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 188 *px = *pIn++;
emilmont 1:fdd22bb7aa52 189
emilmont 1:fdd22bb7aa52 190 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 191 px += nRows;
emilmont 1:fdd22bb7aa52 192
emilmont 1:fdd22bb7aa52 193 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 194 col--;
emilmont 1:fdd22bb7aa52 195 }
emilmont 1:fdd22bb7aa52 196
emilmont 1:fdd22bb7aa52 197 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 198
emilmont 1:fdd22bb7aa52 199 i++;
emilmont 1:fdd22bb7aa52 200
emilmont 1:fdd22bb7aa52 201 /* Decrement the row loop counter */
emilmont 1:fdd22bb7aa52 202 row--;
emilmont 1:fdd22bb7aa52 203
emilmont 1:fdd22bb7aa52 204 } while(row > 0u); /* row loop end */
emilmont 1:fdd22bb7aa52 205
emilmont 1:fdd22bb7aa52 206 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 207 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 208 }
emilmont 1:fdd22bb7aa52 209
emilmont 1:fdd22bb7aa52 210 /* Return to application */
emilmont 1:fdd22bb7aa52 211 return (status);
emilmont 1:fdd22bb7aa52 212 }
emilmont 1:fdd22bb7aa52 213
emilmont 1:fdd22bb7aa52 214 /**
emilmont 1:fdd22bb7aa52 215 * @} end of MatrixTrans group
emilmont 1:fdd22bb7aa52 216 */