Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_add_q31.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_add_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 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 *
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 * @addtogroup MatrixAdd
emilmont 1:fdd22bb7aa52 47 * @{
emilmont 1:fdd22bb7aa52 48 */
emilmont 1:fdd22bb7aa52 49
emilmont 1:fdd22bb7aa52 50 /**
emilmont 1:fdd22bb7aa52 51 * @brief Q31 matrix addition.
emilmont 1:fdd22bb7aa52 52 * @param[in] *pSrcA points to the first input matrix structure
emilmont 1:fdd22bb7aa52 53 * @param[in] *pSrcB points to the second input matrix structure
emilmont 1:fdd22bb7aa52 54 * @param[out] *pDst points to output matrix structure
emilmont 1:fdd22bb7aa52 55 * @return The function returns either
emilmont 1:fdd22bb7aa52 56 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 57 *
emilmont 1:fdd22bb7aa52 58 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 59 * \par
emilmont 1:fdd22bb7aa52 60 * The function uses saturating arithmetic.
emilmont 1:fdd22bb7aa52 61 * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.
emilmont 1:fdd22bb7aa52 62 */
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 arm_status arm_mat_add_q31(
emilmont 1:fdd22bb7aa52 65 const arm_matrix_instance_q31 * pSrcA,
emilmont 1:fdd22bb7aa52 66 const arm_matrix_instance_q31 * pSrcB,
emilmont 1:fdd22bb7aa52 67 arm_matrix_instance_q31 * pDst)
emilmont 1:fdd22bb7aa52 68 {
emilmont 1:fdd22bb7aa52 69 q31_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */
emilmont 1:fdd22bb7aa52 70 q31_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */
emilmont 1:fdd22bb7aa52 71 q31_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 72 q31_t inA1, inB1; /* temporary variables */
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 75
emilmont 1:fdd22bb7aa52 76 q31_t inA2, inB2; /* temporary variables */
emilmont 1:fdd22bb7aa52 77 q31_t out1, out2; /* temporary variables */
emilmont 1:fdd22bb7aa52 78
emilmont 1:fdd22bb7aa52 79 #endif // #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 82 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 83 arm_status status; /* status of matrix addition */
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 86 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 87 if((pSrcA->numRows != pSrcB->numRows) ||
emilmont 1:fdd22bb7aa52 88 (pSrcA->numCols != pSrcB->numCols) ||
emilmont 1:fdd22bb7aa52 89 (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols))
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
emilmont 1:fdd22bb7aa52 96 {
emilmont 1:fdd22bb7aa52 97 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 98 numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols;
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 105 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 106
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)
emilmont 1:fdd22bb7aa52 111 {
emilmont 1:fdd22bb7aa52 112 /* C(m,n) = A(m,n) + B(m,n) */
emilmont 1:fdd22bb7aa52 113 /* Add, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 114 /* Read values from source A */
emilmont 1:fdd22bb7aa52 115 inA1 = pIn1[0];
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* Read values from source B */
emilmont 1:fdd22bb7aa52 118 inB1 = pIn2[0];
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 /* Read values from source A */
emilmont 1:fdd22bb7aa52 121 inA2 = pIn1[1];
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* Add and saturate */
emilmont 1:fdd22bb7aa52 124 out1 = __QADD(inA1, inB1);
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* Read values from source B */
emilmont 1:fdd22bb7aa52 127 inB2 = pIn2[1];
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* Read values from source A */
emilmont 1:fdd22bb7aa52 130 inA1 = pIn1[2];
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* Add and saturate */
emilmont 1:fdd22bb7aa52 133 out2 = __QADD(inA2, inB2);
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 /* Read values from source B */
emilmont 1:fdd22bb7aa52 136 inB1 = pIn2[2];
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 /* Store result in destination */
emilmont 1:fdd22bb7aa52 139 pOut[0] = out1;
emilmont 1:fdd22bb7aa52 140 pOut[1] = out2;
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /* Read values from source A */
emilmont 1:fdd22bb7aa52 143 inA2 = pIn1[3];
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 /* Read values from source B */
emilmont 1:fdd22bb7aa52 146 inB2 = pIn2[3];
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 /* Add and saturate */
emilmont 1:fdd22bb7aa52 149 out1 = __QADD(inA1, inB1);
emilmont 1:fdd22bb7aa52 150 out2 = __QADD(inA2, inB2);
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 /* Store result in destination */
emilmont 1:fdd22bb7aa52 153 pOut[2] = out1;
emilmont 1:fdd22bb7aa52 154 pOut[3] = out2;
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 157 pIn1 += 4u;
emilmont 1:fdd22bb7aa52 158 pIn2 += 4u;
emilmont 1:fdd22bb7aa52 159 pOut += 4u;
emilmont 1:fdd22bb7aa52 160
emilmont 1:fdd22bb7aa52 161 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 162 blkCnt--;
emilmont 1:fdd22bb7aa52 163 }
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 166 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 167 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 168
emilmont 1:fdd22bb7aa52 169 #else
emilmont 1:fdd22bb7aa52 170
emilmont 1:fdd22bb7aa52 171 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 172
emilmont 1:fdd22bb7aa52 173 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 174 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 175
emilmont 1:fdd22bb7aa52 176
emilmont 1:fdd22bb7aa52 177 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 178
emilmont 1:fdd22bb7aa52 179 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 180 {
emilmont 1:fdd22bb7aa52 181 /* C(m,n) = A(m,n) + B(m,n) */
emilmont 1:fdd22bb7aa52 182 /* Add, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 183 inA1 = *pIn1++;
emilmont 1:fdd22bb7aa52 184 inB1 = *pIn2++;
emilmont 1:fdd22bb7aa52 185
emilmont 1:fdd22bb7aa52 186 inA1 = __QADD(inA1, inB1);
emilmont 1:fdd22bb7aa52 187
emilmont 1:fdd22bb7aa52 188 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 189 blkCnt--;
emilmont 1:fdd22bb7aa52 190
emilmont 1:fdd22bb7aa52 191 *pOut++ = inA1;
emilmont 1:fdd22bb7aa52 192
emilmont 1:fdd22bb7aa52 193 }
emilmont 1:fdd22bb7aa52 194
emilmont 1:fdd22bb7aa52 195 /* set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 196 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 197 }
emilmont 1:fdd22bb7aa52 198
emilmont 1:fdd22bb7aa52 199 /* Return to application */
emilmont 1:fdd22bb7aa52 200 return (status);
emilmont 1:fdd22bb7aa52 201 }
emilmont 1:fdd22bb7aa52 202
emilmont 1:fdd22bb7aa52 203 /**
emilmont 1:fdd22bb7aa52 204 * @} end of MatrixAdd group
emilmont 1:fdd22bb7aa52 205 */