Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_trans_f32.c@4:9cee975aadce, 2014-06-23 (annotated)

Committer:
mbed_official
Date:
Mon Jun 23 09:30:09 2014 +0100
Revision:
4:9cee975aadce
Parent:
3:7a284390b0ce 
Synchronized with git revision 6e7c7bcec41226f536474daae3c13d49e4c0e865



Full URL: https://github.com/mbedmicro/mbed/commit/6e7c7bcec41226f536474daae3c13d49e4c0e865/



Fix signed unsigned compare in dsp library

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
mbed_official 3:7a284390b0ce 2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 3:7a284390b0ce 4 * $Date: 17. January 2013
mbed_official 3:7a284390b0ce 5 * $Revision: V1.4.1
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_mat_trans_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 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 *
mbed_official 3:7a284390b0ce 14 * Redistribution and use in source and binary forms, with or without
mbed_official 3:7a284390b0ce 15 * modification, are permitted provided that the following conditions
mbed_official 3:7a284390b0ce 16 * are met:
mbed_official 3:7a284390b0ce 17 * - Redistributions of source code must retain the above copyright
mbed_official 3:7a284390b0ce 18 * notice, this list of conditions and the following disclaimer.
mbed_official 3:7a284390b0ce 19 * - Redistributions in binary form must reproduce the above copyright
mbed_official 3:7a284390b0ce 20 * notice, this list of conditions and the following disclaimer in
mbed_official 3:7a284390b0ce 21 * the documentation and/or other materials provided with the
mbed_official 3:7a284390b0ce 22 * distribution.
mbed_official 3:7a284390b0ce 23 * - Neither the name of ARM LIMITED nor the names of its contributors
mbed_official 3:7a284390b0ce 24 * may be used to endorse or promote products derived from this
mbed_official 3:7a284390b0ce 25 * software without specific prior written permission.
mbed_official 3:7a284390b0ce 26 *
mbed_official 3:7a284390b0ce 27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
mbed_official 3:7a284390b0ce 28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
mbed_official 3:7a284390b0ce 29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
mbed_official 3:7a284390b0ce 30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
mbed_official 3:7a284390b0ce 31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
mbed_official 3:7a284390b0ce 32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
mbed_official 3:7a284390b0ce 33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
mbed_official 3:7a284390b0ce 34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
mbed_official 3:7a284390b0ce 35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
mbed_official 3:7a284390b0ce 36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
mbed_official 3:7a284390b0ce 37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
mbed_official 3:7a284390b0ce 38 * POSSIBILITY OF SUCH DAMAGE.
emilmont 1:fdd22bb7aa52 39 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 40
emilmont 1:fdd22bb7aa52 41 /**
emilmont 1:fdd22bb7aa52 42 * @defgroup MatrixTrans Matrix Transpose
emilmont 1:fdd22bb7aa52 43 *
emilmont 1:fdd22bb7aa52 44 * Tranposes a matrix.
emilmont 1:fdd22bb7aa52 45 * 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 46 * \image html MatrixTranspose.gif "Transpose of a 3 x 3 matrix"
emilmont 1:fdd22bb7aa52 47 */
emilmont 1:fdd22bb7aa52 48
emilmont 1:fdd22bb7aa52 49 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 50
emilmont 1:fdd22bb7aa52 51 /**
emilmont 1:fdd22bb7aa52 52 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 53 */
emilmont 1:fdd22bb7aa52 54
emilmont 1:fdd22bb7aa52 55 /**
emilmont 1:fdd22bb7aa52 56 * @addtogroup MatrixTrans
emilmont 1:fdd22bb7aa52 57 * @{
emilmont 1:fdd22bb7aa52 58 */
emilmont 1:fdd22bb7aa52 59
emilmont 1:fdd22bb7aa52 60 /**
emilmont 1:fdd22bb7aa52 61 * @brief Floating-point matrix transpose.
emilmont 1:fdd22bb7aa52 62 * @param[in] *pSrc points to the input matrix
emilmont 1:fdd22bb7aa52 63 * @param[out] *pDst points to the output matrix
emilmont 2:da51fb522205 64 * @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code>
emilmont 1:fdd22bb7aa52 65 * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 66 */
emilmont 1:fdd22bb7aa52 67
emilmont 1:fdd22bb7aa52 68
emilmont 1:fdd22bb7aa52 69 arm_status arm_mat_trans_f32(
emilmont 1:fdd22bb7aa52 70 const arm_matrix_instance_f32 * pSrc,
emilmont 1:fdd22bb7aa52 71 arm_matrix_instance_f32 * pDst)
emilmont 1:fdd22bb7aa52 72 {
emilmont 1:fdd22bb7aa52 73 float32_t *pIn = pSrc->pData; /* input data matrix pointer */
emilmont 1:fdd22bb7aa52 74 float32_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 75 float32_t *px; /* Temporary output data matrix pointer */
emilmont 1:fdd22bb7aa52 76 uint16_t nRows = pSrc->numRows; /* number of rows */
emilmont 1:fdd22bb7aa52 77 uint16_t nColumns = pSrc->numCols; /* number of columns */
emilmont 1:fdd22bb7aa52 78
mbed_official 3:7a284390b0ce 79 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 uint16_t blkCnt, i = 0u, row = nRows; /* loop counters */
emilmont 1:fdd22bb7aa52 84 arm_status status; /* status of matrix transpose */
emilmont 1:fdd22bb7aa52 85
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 88
emilmont 1:fdd22bb7aa52 89
emilmont 1:fdd22bb7aa52 90 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 91 if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
emilmont 1:fdd22bb7aa52 92 {
emilmont 1:fdd22bb7aa52 93 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 94 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 95 }
emilmont 1:fdd22bb7aa52 96 else
emilmont 1:fdd22bb7aa52 97 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 98
emilmont 1:fdd22bb7aa52 99 {
emilmont 1:fdd22bb7aa52 100 /* Matrix transpose by exchanging the rows with columns */
emilmont 1:fdd22bb7aa52 101 /* row loop */
emilmont 1:fdd22bb7aa52 102 do
emilmont 1:fdd22bb7aa52 103 {
emilmont 1:fdd22bb7aa52 104 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 105 blkCnt = nColumns >> 2;
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 /* The pointer px is set to starting address of the column being processed */
emilmont 1:fdd22bb7aa52 108 px = pOut + i;
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 111 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 112 while(blkCnt > 0u) /* column loop */
emilmont 1:fdd22bb7aa52 113 {
emilmont 1:fdd22bb7aa52 114 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 115 *px = *pIn++;
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 118 px += nRows;
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 121 *px = *pIn++;
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 124 px += nRows;
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 127 *px = *pIn++;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 130 px += nRows;
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 133 *px = *pIn++;
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 136 px += nRows;
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 139 blkCnt--;
emilmont 1:fdd22bb7aa52 140 }
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /* Perform matrix transpose for last 3 samples here. */
emilmont 1:fdd22bb7aa52 143 blkCnt = nColumns % 0x4u;
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 146 {
emilmont 1:fdd22bb7aa52 147 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 148 *px = *pIn++;
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 151 px += nRows;
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 154 blkCnt--;
emilmont 1:fdd22bb7aa52 155 }
emilmont 1:fdd22bb7aa52 156
emilmont 1:fdd22bb7aa52 157 #else
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 160
emilmont 1:fdd22bb7aa52 161 uint16_t col, i = 0u, row = nRows; /* loop counters */
emilmont 1:fdd22bb7aa52 162 arm_status status; /* status of matrix transpose */
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 166
emilmont 1:fdd22bb7aa52 167 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 168 if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
emilmont 1:fdd22bb7aa52 169 {
emilmont 1:fdd22bb7aa52 170 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 171 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 172 }
emilmont 1:fdd22bb7aa52 173 else
emilmont 1:fdd22bb7aa52 174 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 175
emilmont 1:fdd22bb7aa52 176 {
emilmont 1:fdd22bb7aa52 177 /* Matrix transpose by exchanging the rows with columns */
emilmont 1:fdd22bb7aa52 178 /* row loop */
emilmont 1:fdd22bb7aa52 179 do
emilmont 1:fdd22bb7aa52 180 {
emilmont 1:fdd22bb7aa52 181 /* The pointer px is set to starting address of the column being processed */
emilmont 1:fdd22bb7aa52 182 px = pOut + i;
emilmont 1:fdd22bb7aa52 183
emilmont 1:fdd22bb7aa52 184 /* Initialize column loop counter */
emilmont 1:fdd22bb7aa52 185 col = nColumns;
emilmont 1:fdd22bb7aa52 186
emilmont 1:fdd22bb7aa52 187 while(col > 0u)
emilmont 1:fdd22bb7aa52 188 {
emilmont 1:fdd22bb7aa52 189 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 190 *px = *pIn++;
emilmont 1:fdd22bb7aa52 191
emilmont 1:fdd22bb7aa52 192 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 193 px += nRows;
emilmont 1:fdd22bb7aa52 194
emilmont 1:fdd22bb7aa52 195 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 196 col--;
emilmont 1:fdd22bb7aa52 197 }
emilmont 1:fdd22bb7aa52 198
mbed_official 3:7a284390b0ce 199 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 200
emilmont 1:fdd22bb7aa52 201 i++;
emilmont 1:fdd22bb7aa52 202
emilmont 1:fdd22bb7aa52 203 /* Decrement the row loop counter */
emilmont 1:fdd22bb7aa52 204 row--;
emilmont 1:fdd22bb7aa52 205
emilmont 1:fdd22bb7aa52 206 } while(row > 0u); /* row loop end */
emilmont 1:fdd22bb7aa52 207
emilmont 1:fdd22bb7aa52 208 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 209 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 210 }
emilmont 1:fdd22bb7aa52 211
emilmont 1:fdd22bb7aa52 212 /* Return to application */
emilmont 1:fdd22bb7aa52 213 return (status);
emilmont 1:fdd22bb7aa52 214 }
emilmont 1:fdd22bb7aa52 215
emilmont 1:fdd22bb7aa52 216 /**
emilmont 1:fdd22bb7aa52 217 * @} end of MatrixTrans group
emilmont 1:fdd22bb7aa52 218 */