mbed official / mbed-dsp

CMSIS DSP library

Dependents:   performance_timer Surfboard_ gps2rtty Capstone ... more

Legacy Warning

This is an mbed 2 library. To learn more about mbed OS 5, visit the docs.

cmsis_dsp/MatrixFunctions/arm_mat_sub_q31.c@5:3762170b6d4d, 2015-11-20 (annotated)

Committer:
mbed_official
Date:
Fri Nov 20 08:45:18 2015 +0000
Revision:
5:3762170b6d4d
Parent:
3:7a284390b0ce 
Synchronized with git revision 2eb940b9a73af188d3004a2575fdfbb05febe62b



Full URL: https://github.com/mbedmicro/mbed/commit/2eb940b9a73af188d3004a2575fdfbb05febe62b/



Added option to build rpc library. closes #1426

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
mbed_official 5:3762170b6d4d 2 * Copyright (C) 2010-2014 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 5:3762170b6d4d 4 * $Date: 19. March 2015
mbed_official 5:3762170b6d4d 5 * $Revision: V.1.4.5
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_mat_sub_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q31 matrix subtraction
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 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @addtogroup MatrixSub
emilmont 1:fdd22bb7aa52 49 * @{
emilmont 1:fdd22bb7aa52 50 */
emilmont 1:fdd22bb7aa52 51
emilmont 1:fdd22bb7aa52 52 /**
emilmont 1:fdd22bb7aa52 53 * @brief Q31 matrix subtraction.
emilmont 1:fdd22bb7aa52 54 * @param[in] *pSrcA points to the first input matrix structure
emilmont 1:fdd22bb7aa52 55 * @param[in] *pSrcB points to the second input matrix structure
emilmont 1:fdd22bb7aa52 56 * @param[out] *pDst points to output matrix structure
emilmont 2:da51fb522205 57 * @return The function returns either
emilmont 1:fdd22bb7aa52 58 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 59 *
emilmont 1:fdd22bb7aa52 60 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 61 * \par
emilmont 1:fdd22bb7aa52 62 * The function uses saturating arithmetic.
emilmont 1:fdd22bb7aa52 63 * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.
emilmont 1:fdd22bb7aa52 64 */
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66
emilmont 1:fdd22bb7aa52 67 arm_status arm_mat_sub_q31(
emilmont 1:fdd22bb7aa52 68 const arm_matrix_instance_q31 * pSrcA,
emilmont 1:fdd22bb7aa52 69 const arm_matrix_instance_q31 * pSrcB,
emilmont 1:fdd22bb7aa52 70 arm_matrix_instance_q31 * pDst)
emilmont 1:fdd22bb7aa52 71 {
emilmont 1:fdd22bb7aa52 72 q31_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */
emilmont 1:fdd22bb7aa52 73 q31_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */
emilmont 1:fdd22bb7aa52 74 q31_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 75 q31_t inA1, inB1; /* temporary variables */
emilmont 1:fdd22bb7aa52 76
mbed_official 3:7a284390b0ce 77 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 78
emilmont 1:fdd22bb7aa52 79 q31_t inA2, inB2; /* temporary variables */
emilmont 1:fdd22bb7aa52 80 q31_t out1, out2; /* temporary variables */
emilmont 1:fdd22bb7aa52 81
mbed_official 3:7a284390b0ce 82 #endif // #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 85 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 86 arm_status status; /* status of matrix subtraction */
emilmont 1:fdd22bb7aa52 87
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
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
mbed_official 3:7a284390b0ce 104 #ifndef ARM_MATH_CM0_FAMILY
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, saturate 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 /* Subtract and saturate */
emilmont 1:fdd22bb7aa52 127 out1 = __QSUB(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 /* Subtract and saturate */
emilmont 1:fdd22bb7aa52 136 out2 = __QSUB(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 /* Subtract and saturate */
emilmont 1:fdd22bb7aa52 152 out1 = __QSUB(inA1, inB1);
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 /* Subtract and saturate */
emilmont 1:fdd22bb7aa52 155 out2 = __QSUB(inA2, inB2);
emilmont 1:fdd22bb7aa52 156
emilmont 1:fdd22bb7aa52 157 /* Store result in destination */
emilmont 1:fdd22bb7aa52 158 pOut[2] = out1;
emilmont 1:fdd22bb7aa52 159 pOut[3] = out2;
emilmont 1:fdd22bb7aa52 160
emilmont 1:fdd22bb7aa52 161 /* update pointers to process next samples */
emilmont 1:fdd22bb7aa52 162 pIn1 += 4u;
emilmont 1:fdd22bb7aa52 163 pIn2 += 4u;
emilmont 1:fdd22bb7aa52 164 pOut += 4u;
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 167 blkCnt--;
emilmont 1:fdd22bb7aa52 168 }
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 171 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 172 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 #else
emilmont 1:fdd22bb7aa52 175
emilmont 1:fdd22bb7aa52 176 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 179 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 180
mbed_official 3:7a284390b0ce 181 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 182
emilmont 1:fdd22bb7aa52 183 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 184 {
emilmont 1:fdd22bb7aa52 185 /* C(m,n) = A(m,n) - B(m,n) */
emilmont 1:fdd22bb7aa52 186 /* Subtract, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 187 inA1 = *pIn1++;
emilmont 1:fdd22bb7aa52 188 inB1 = *pIn2++;
emilmont 1:fdd22bb7aa52 189
emilmont 1:fdd22bb7aa52 190 inA1 = __QSUB(inA1, inB1);
emilmont 1:fdd22bb7aa52 191
emilmont 1:fdd22bb7aa52 192 *pOut++ = inA1;
emilmont 1:fdd22bb7aa52 193
emilmont 1:fdd22bb7aa52 194 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 195 blkCnt--;
emilmont 1:fdd22bb7aa52 196 }
emilmont 1:fdd22bb7aa52 197
emilmont 1:fdd22bb7aa52 198 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 199 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 200 }
emilmont 1:fdd22bb7aa52 201
emilmont 1:fdd22bb7aa52 202 /* Return to application */
emilmont 1:fdd22bb7aa52 203 return (status);
emilmont 1:fdd22bb7aa52 204 }
emilmont 1:fdd22bb7aa52 205
emilmont 1:fdd22bb7aa52 206 /**
emilmont 1:fdd22bb7aa52 207 * @} end of MatrixSub group
emilmont 1:fdd22bb7aa52 208 */