Laxmi Kant Tiwari / mbed-dsp

Important changes to repositories hosted on mbed.com

Mbed hosted mercurial repositories are deprecated and are due to be permanently deleted in July 2026.

To keep a copy of this software download the repository Zip archive or clone locally using Mercurial.

It is also possible to export all your personal repositories from the account settings page.

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_sub_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_sub_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Floating-point matrix subtraction.
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 * @defgroup MatrixSub Matrix Subtraction
emilmont 1:fdd22bb7aa52 47 *
emilmont 1:fdd22bb7aa52 48 * Subtract two matrices.
emilmont 1:fdd22bb7aa52 49 * \image html MatrixSubtraction.gif "Subraction of two 3 x 3 matrices"
emilmont 1:fdd22bb7aa52 50 *
emilmont 1:fdd22bb7aa52 51 * The functions check to make sure that
emilmont 1:fdd22bb7aa52 52 * <code>pSrcA</code>, <code>pSrcB</code>, and <code>pDst</code> have the same
emilmont 1:fdd22bb7aa52 53 * number of rows and columns.
emilmont 1:fdd22bb7aa52 54 */
emilmont 1:fdd22bb7aa52 55
emilmont 1:fdd22bb7aa52 56 /**
emilmont 1:fdd22bb7aa52 57 * @addtogroup MatrixSub
emilmont 1:fdd22bb7aa52 58 * @{
emilmont 1:fdd22bb7aa52 59 */
emilmont 1:fdd22bb7aa52 60
emilmont 1:fdd22bb7aa52 61 /**
emilmont 1:fdd22bb7aa52 62 * @brief Floating-point matrix subtraction
emilmont 1:fdd22bb7aa52 63 * @param[in] *pSrcA points to the first input matrix structure
emilmont 1:fdd22bb7aa52 64 * @param[in] *pSrcB points to the second input matrix structure
emilmont 1:fdd22bb7aa52 65 * @param[out] *pDst points to output matrix structure
emilmont 1:fdd22bb7aa52 66 * @return The function returns either
emilmont 1:fdd22bb7aa52 67 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 68 */
emilmont 1:fdd22bb7aa52 69
emilmont 1:fdd22bb7aa52 70 arm_status arm_mat_sub_f32(
emilmont 1:fdd22bb7aa52 71 const arm_matrix_instance_f32 * pSrcA,
emilmont 1:fdd22bb7aa52 72 const arm_matrix_instance_f32 * pSrcB,
emilmont 1:fdd22bb7aa52 73 arm_matrix_instance_f32 * pDst)
emilmont 1:fdd22bb7aa52 74 {
emilmont 1:fdd22bb7aa52 75 float32_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */
emilmont 1:fdd22bb7aa52 76 float32_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */
emilmont 1:fdd22bb7aa52 77 float32_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 78
emilmont 1:fdd22bb7aa52 79 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 float32_t inA1, inA2, inB1, inB2, out1, out2; /* temporary variables */
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 #endif // #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 86 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 87 arm_status status; /* status of matrix subtraction */
emilmont 1:fdd22bb7aa52 88
emilmont 1:fdd22bb7aa52 89 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 90 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 91 if((pSrcA->numRows != pSrcB->numRows) ||
emilmont 1:fdd22bb7aa52 92 (pSrcA->numCols != pSrcB->numCols) ||
emilmont 1:fdd22bb7aa52 93 (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 94 {
emilmont 1:fdd22bb7aa52 95 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 96 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 97 }
emilmont 1:fdd22bb7aa52 98 else
emilmont 1:fdd22bb7aa52 99 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 100 {
emilmont 1:fdd22bb7aa52 101 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 102 numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols;
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 109 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 112 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 113 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 114 {
emilmont 1:fdd22bb7aa52 115 /* C(m,n) = A(m,n) - B(m,n) */
emilmont 1:fdd22bb7aa52 116 /* Subtract and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 117 /* Read values from source A */
emilmont 1:fdd22bb7aa52 118 inA1 = pIn1[0];
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 /* Read values from source B */
emilmont 1:fdd22bb7aa52 121 inB1 = pIn2[0];
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* Read values from source A */
emilmont 1:fdd22bb7aa52 124 inA2 = pIn1[1];
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* out = sourceA - sourceB */
emilmont 1:fdd22bb7aa52 127 out1 = inA1 - inB1;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* Read values from source B */
emilmont 1:fdd22bb7aa52 130 inB2 = pIn2[1];
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* Read values from source A */
emilmont 1:fdd22bb7aa52 133 inA1 = pIn1[2];
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 /* out = sourceA - sourceB */
emilmont 1:fdd22bb7aa52 136 out2 = inA2 - inB2;
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 /* Read values from source B */
emilmont 1:fdd22bb7aa52 139 inB1 = pIn2[2];
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /* Store result in destination */
emilmont 1:fdd22bb7aa52 142 pOut[0] = out1;
emilmont 1:fdd22bb7aa52 143 pOut[1] = out2;
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 /* Read values from source A */
emilmont 1:fdd22bb7aa52 146 inA2 = pIn1[3];
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 /* Read values from source B */
emilmont 1:fdd22bb7aa52 149 inB2 = pIn2[3];
emilmont 1:fdd22bb7aa52 150
emilmont 1:fdd22bb7aa52 151 /* out = sourceA - sourceB */
emilmont 1:fdd22bb7aa52 152 out1 = inA1 - inB1;
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* out = sourceA - sourceB */
emilmont 1:fdd22bb7aa52 156 out2 = inA2 - inB2;
emilmont 1:fdd22bb7aa52 157
emilmont 1:fdd22bb7aa52 158 /* Store result in destination */
emilmont 1:fdd22bb7aa52 159 pOut[2] = out1;
emilmont 1:fdd22bb7aa52 160
emilmont 1:fdd22bb7aa52 161 /* Store result in destination */
emilmont 1:fdd22bb7aa52 162 pOut[3] = out2;
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 166 pIn1 += 4u;
emilmont 1:fdd22bb7aa52 167 pIn2 += 4u;
emilmont 1:fdd22bb7aa52 168 pOut += 4u;
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 171 blkCnt--;
emilmont 1:fdd22bb7aa52 172 }
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 175 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 176 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 #else
emilmont 1:fdd22bb7aa52 179
emilmont 1:fdd22bb7aa52 180 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 181
emilmont 1:fdd22bb7aa52 182 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 183 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 184
emilmont 1:fdd22bb7aa52 185 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 186
emilmont 1:fdd22bb7aa52 187 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 188 {
emilmont 1:fdd22bb7aa52 189 /* C(m,n) = A(m,n) - B(m,n) */
emilmont 1:fdd22bb7aa52 190 /* Subtract and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 191 *pOut++ = (*pIn1++) - (*pIn2++);
emilmont 1:fdd22bb7aa52 192
emilmont 1:fdd22bb7aa52 193 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 194 blkCnt--;
emilmont 1:fdd22bb7aa52 195 }
emilmont 1:fdd22bb7aa52 196
emilmont 1:fdd22bb7aa52 197 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 198 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 199 }
emilmont 1:fdd22bb7aa52 200
emilmont 1:fdd22bb7aa52 201 /* Return to application */
emilmont 1:fdd22bb7aa52 202 return (status);
emilmont 1:fdd22bb7aa52 203 }
emilmont 1:fdd22bb7aa52 204
emilmont 1:fdd22bb7aa52 205 /**
emilmont 1:fdd22bb7aa52 206 * @} end of MatrixSub group
emilmont 1:fdd22bb7aa52 207 */