Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_add_q31.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_add_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q31 matrix addition
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 MatrixAdd
emilmont 1:fdd22bb7aa52 49 * @{
emilmont 1:fdd22bb7aa52 50 */
emilmont 1:fdd22bb7aa52 51
emilmont 1:fdd22bb7aa52 52 /**
emilmont 1:fdd22bb7aa52 53 * @brief Q31 matrix addition.
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 arm_status arm_mat_add_q31(
emilmont 1:fdd22bb7aa52 67 const arm_matrix_instance_q31 * pSrcA,
emilmont 1:fdd22bb7aa52 68 const arm_matrix_instance_q31 * pSrcB,
emilmont 1:fdd22bb7aa52 69 arm_matrix_instance_q31 * pDst)
emilmont 1:fdd22bb7aa52 70 {
emilmont 1:fdd22bb7aa52 71 q31_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */
emilmont 1:fdd22bb7aa52 72 q31_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */
emilmont 1:fdd22bb7aa52 73 q31_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 74 q31_t inA1, inB1; /* temporary variables */
emilmont 1:fdd22bb7aa52 75
mbed_official 3:7a284390b0ce 76 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 q31_t inA2, inB2; /* temporary variables */
emilmont 1:fdd22bb7aa52 79 q31_t out1, out2; /* temporary variables */
emilmont 1:fdd22bb7aa52 80
mbed_official 3:7a284390b0ce 81 #endif // #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 84 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 85 arm_status status; /* status of matrix addition */
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 88 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 89 if((pSrcA->numRows != pSrcB->numRows) ||
emilmont 1:fdd22bb7aa52 90 (pSrcA->numCols != pSrcB->numCols) ||
emilmont 1:fdd22bb7aa52 91 (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols))
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
emilmont 1:fdd22bb7aa52 98 {
emilmont 1:fdd22bb7aa52 99 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 100 numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols;
emilmont 1:fdd22bb7aa52 101
mbed_official 3:7a284390b0ce 102 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 107 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 108
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)
emilmont 1:fdd22bb7aa52 113 {
emilmont 1:fdd22bb7aa52 114 /* C(m,n) = A(m,n) + B(m,n) */
emilmont 1:fdd22bb7aa52 115 /* Add, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 116 /* Read values from source A */
emilmont 1:fdd22bb7aa52 117 inA1 = pIn1[0];
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119 /* Read values from source B */
emilmont 1:fdd22bb7aa52 120 inB1 = pIn2[0];
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122 /* Read values from source A */
emilmont 1:fdd22bb7aa52 123 inA2 = pIn1[1];
emilmont 1:fdd22bb7aa52 124
emilmont 1:fdd22bb7aa52 125 /* Add and saturate */
emilmont 1:fdd22bb7aa52 126 out1 = __QADD(inA1, inB1);
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 /* Read values from source B */
emilmont 1:fdd22bb7aa52 129 inB2 = pIn2[1];
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 /* Read values from source A */
emilmont 1:fdd22bb7aa52 132 inA1 = pIn1[2];
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 /* Add and saturate */
emilmont 1:fdd22bb7aa52 135 out2 = __QADD(inA2, inB2);
emilmont 1:fdd22bb7aa52 136
emilmont 1:fdd22bb7aa52 137 /* Read values from source B */
emilmont 1:fdd22bb7aa52 138 inB1 = pIn2[2];
emilmont 1:fdd22bb7aa52 139
emilmont 1:fdd22bb7aa52 140 /* Store result in destination */
emilmont 1:fdd22bb7aa52 141 pOut[0] = out1;
emilmont 1:fdd22bb7aa52 142 pOut[1] = out2;
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 /* Read values from source A */
emilmont 1:fdd22bb7aa52 145 inA2 = pIn1[3];
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 /* Read values from source B */
emilmont 1:fdd22bb7aa52 148 inB2 = pIn2[3];
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 /* Add and saturate */
emilmont 1:fdd22bb7aa52 151 out1 = __QADD(inA1, inB1);
emilmont 1:fdd22bb7aa52 152 out2 = __QADD(inA2, inB2);
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 /* Store result in destination */
emilmont 1:fdd22bb7aa52 155 pOut[2] = out1;
emilmont 1:fdd22bb7aa52 156 pOut[3] = out2;
emilmont 1:fdd22bb7aa52 157
emilmont 1:fdd22bb7aa52 158 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 159 pIn1 += 4u;
emilmont 1:fdd22bb7aa52 160 pIn2 += 4u;
emilmont 1:fdd22bb7aa52 161 pOut += 4u;
emilmont 1:fdd22bb7aa52 162
emilmont 1:fdd22bb7aa52 163 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 164 blkCnt--;
emilmont 1:fdd22bb7aa52 165 }
emilmont 1:fdd22bb7aa52 166
emilmont 1:fdd22bb7aa52 167 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 168 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 169 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 170
emilmont 1:fdd22bb7aa52 171 #else
emilmont 1:fdd22bb7aa52 172
emilmont 1:fdd22bb7aa52 173 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 174
emilmont 1:fdd22bb7aa52 175 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 176 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178
mbed_official 3:7a284390b0ce 179 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 180
emilmont 1:fdd22bb7aa52 181 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 182 {
emilmont 1:fdd22bb7aa52 183 /* C(m,n) = A(m,n) + B(m,n) */
emilmont 1:fdd22bb7aa52 184 /* Add, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 185 inA1 = *pIn1++;
emilmont 1:fdd22bb7aa52 186 inB1 = *pIn2++;
emilmont 1:fdd22bb7aa52 187
emilmont 1:fdd22bb7aa52 188 inA1 = __QADD(inA1, inB1);
emilmont 1:fdd22bb7aa52 189
emilmont 1:fdd22bb7aa52 190 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 191 blkCnt--;
emilmont 1:fdd22bb7aa52 192
emilmont 1:fdd22bb7aa52 193 *pOut++ = inA1;
emilmont 1:fdd22bb7aa52 194
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 MatrixAdd group
emilmont 1:fdd22bb7aa52 207 */