mbed official / mbed-dsp

CMSIS DSP library

Dependents:   KL25Z_FFT_Demo Hat_Board_v5_1 KL25Z_FFT_Demo_tony KL25Z_FFT_Demo_tony ... more

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_mult_q15.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_mult_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Q15 matrix multiplication.
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 MatrixMult
emilmont 1:fdd22bb7aa52 47 * @{
emilmont 1:fdd22bb7aa52 48 */
emilmont 1:fdd22bb7aa52 49
emilmont 1:fdd22bb7aa52 50
emilmont 1:fdd22bb7aa52 51 /**
emilmont 1:fdd22bb7aa52 52 * @brief Q15 matrix multiplication
emilmont 1:fdd22bb7aa52 53 * @param[in] *pSrcA points to the first input matrix structure
emilmont 1:fdd22bb7aa52 54 * @param[in] *pSrcB points to the second input matrix structure
emilmont 1:fdd22bb7aa52 55 * @param[out] *pDst points to output matrix structure
emilmont 1:fdd22bb7aa52 56 * @param[in] *pState points to the array for storing intermediate results
emilmont 1:fdd22bb7aa52 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 * @details
emilmont 1:fdd22bb7aa52 61 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 62 *
emilmont 1:fdd22bb7aa52 63 * \par
emilmont 1:fdd22bb7aa52 64 * The function is implemented using a 64-bit internal accumulator. The inputs to the
emilmont 1:fdd22bb7aa52 65 * multiplications are in 1.15 format and multiplications yield a 2.30 result.
emilmont 1:fdd22bb7aa52 66 * The 2.30 intermediate
emilmont 1:fdd22bb7aa52 67 * results are accumulated in a 64-bit accumulator in 34.30 format. This approach
emilmont 1:fdd22bb7aa52 68 * provides 33 guard bits and there is no risk of overflow. The 34.30 result is then
emilmont 1:fdd22bb7aa52 69 * truncated to 34.15 format by discarding the low 15 bits and then saturated to
emilmont 1:fdd22bb7aa52 70 * 1.15 format.
emilmont 1:fdd22bb7aa52 71 *
emilmont 1:fdd22bb7aa52 72 * \par
emilmont 1:fdd22bb7aa52 73 * Refer to <code>arm_mat_mult_fast_q15()</code> for a faster but less precise version of this function for Cortex-M3 and Cortex-M4.
emilmont 1:fdd22bb7aa52 74 *
emilmont 1:fdd22bb7aa52 75 */
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77 arm_status arm_mat_mult_q15(
emilmont 1:fdd22bb7aa52 78 const arm_matrix_instance_q15 * pSrcA,
emilmont 1:fdd22bb7aa52 79 const arm_matrix_instance_q15 * pSrcB,
emilmont 1:fdd22bb7aa52 80 arm_matrix_instance_q15 * pDst,
emilmont 1:fdd22bb7aa52 81 q15_t * pState)
emilmont 1:fdd22bb7aa52 82 {
emilmont 1:fdd22bb7aa52 83 q63_t sum; /* accumulator */
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 88
emilmont 1:fdd22bb7aa52 89 q15_t *pSrcBT = pState; /* input data matrix pointer for transpose */
emilmont 1:fdd22bb7aa52 90 q15_t *pInA = pSrcA->pData; /* input data matrix pointer A of Q15 type */
emilmont 1:fdd22bb7aa52 91 q15_t *pInB = pSrcB->pData; /* input data matrix pointer B of Q15 type */
emilmont 1:fdd22bb7aa52 92 q15_t *px; /* Temporary output data matrix pointer */
emilmont 1:fdd22bb7aa52 93 uint16_t numRowsA = pSrcA->numRows; /* number of rows of input matrix A */
emilmont 1:fdd22bb7aa52 94 uint16_t numColsB = pSrcB->numCols; /* number of columns of input matrix B */
emilmont 1:fdd22bb7aa52 95 uint16_t numColsA = pSrcA->numCols; /* number of columns of input matrix A */
emilmont 1:fdd22bb7aa52 96 uint16_t numRowsB = pSrcB->numRows; /* number of rows of input matrix A */
emilmont 1:fdd22bb7aa52 97 uint16_t col, i = 0u, row = numRowsB, colCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 98 arm_status status; /* status of matrix multiplication */
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 #ifndef UNALIGNED_SUPPORT_DISABLE
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 q31_t in; /* Temporary variable to hold the input value */
emilmont 1:fdd22bb7aa52 103 q31_t pSourceA1, pSourceB1, pSourceA2, pSourceB2;
emilmont 1:fdd22bb7aa52 104
emilmont 1:fdd22bb7aa52 105 #else
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 q15_t in; /* Temporary variable to hold the input value */
emilmont 1:fdd22bb7aa52 108 q15_t inA1, inB1, inA2, inB2;
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110 #endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 113 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 114 if((pSrcA->numCols != pSrcB->numRows) ||
emilmont 1:fdd22bb7aa52 115 (pSrcA->numRows != pDst->numRows) || (pSrcB->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 116 {
emilmont 1:fdd22bb7aa52 117 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 118 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 119 }
emilmont 1:fdd22bb7aa52 120 else
emilmont 1:fdd22bb7aa52 121 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 122 {
emilmont 1:fdd22bb7aa52 123 /* Matrix transpose */
emilmont 1:fdd22bb7aa52 124 do
emilmont 1:fdd22bb7aa52 125 {
emilmont 1:fdd22bb7aa52 126 /* Apply loop unrolling and exchange the columns with row elements */
emilmont 1:fdd22bb7aa52 127 col = numColsB >> 2;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* The pointer px is set to starting address of the column being processed */
emilmont 1:fdd22bb7aa52 130 px = pSrcBT + i;
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 133 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 134 while(col > 0u)
emilmont 1:fdd22bb7aa52 135 {
emilmont 1:fdd22bb7aa52 136 #ifndef UNALIGNED_SUPPORT_DISABLE
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 /* Read two elements from the row */
emilmont 1:fdd22bb7aa52 139 in = *__SIMD32(pInB)++;
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /* Unpack and store one element in the destination */
emilmont 1:fdd22bb7aa52 142 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 *px = (q15_t) in;
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 #else
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 *px = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 153 px += numRowsB;
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* Unpack and store the second element in the destination */
emilmont 1:fdd22bb7aa52 156 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 157
emilmont 1:fdd22bb7aa52 158 *px = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 159
emilmont 1:fdd22bb7aa52 160 #else
emilmont 1:fdd22bb7aa52 161
emilmont 1:fdd22bb7aa52 162 *px = (q15_t) in;
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 167 px += numRowsB;
emilmont 1:fdd22bb7aa52 168
emilmont 1:fdd22bb7aa52 169 /* Read two elements from the row */
emilmont 1:fdd22bb7aa52 170 in = *__SIMD32(pInB)++;
emilmont 1:fdd22bb7aa52 171
emilmont 1:fdd22bb7aa52 172 /* Unpack and store one element in the destination */
emilmont 1:fdd22bb7aa52 173 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 174
emilmont 1:fdd22bb7aa52 175 *px = (q15_t) in;
emilmont 1:fdd22bb7aa52 176
emilmont 1:fdd22bb7aa52 177 #else
emilmont 1:fdd22bb7aa52 178
emilmont 1:fdd22bb7aa52 179 *px = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 180
emilmont 1:fdd22bb7aa52 181 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 182
emilmont 1:fdd22bb7aa52 183 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 184 px += numRowsB;
emilmont 1:fdd22bb7aa52 185
emilmont 1:fdd22bb7aa52 186 /* Unpack and store the second element in the destination */
emilmont 1:fdd22bb7aa52 187
emilmont 1:fdd22bb7aa52 188 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 189
emilmont 1:fdd22bb7aa52 190 *px = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
emilmont 1:fdd22bb7aa52 191
emilmont 1:fdd22bb7aa52 192 #else
emilmont 1:fdd22bb7aa52 193
emilmont 1:fdd22bb7aa52 194 *px = (q15_t) in;
emilmont 1:fdd22bb7aa52 195
emilmont 1:fdd22bb7aa52 196 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 197
emilmont 1:fdd22bb7aa52 198 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 199 px += numRowsB;
emilmont 1:fdd22bb7aa52 200
emilmont 1:fdd22bb7aa52 201 #else
emilmont 1:fdd22bb7aa52 202
emilmont 1:fdd22bb7aa52 203 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 204 in = *pInB++;
emilmont 1:fdd22bb7aa52 205
emilmont 1:fdd22bb7aa52 206 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 207 *px = in;
emilmont 1:fdd22bb7aa52 208
emilmont 1:fdd22bb7aa52 209 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 210 px += numRowsB;
emilmont 1:fdd22bb7aa52 211
emilmont 1:fdd22bb7aa52 212 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 213 in = *pInB++;
emilmont 1:fdd22bb7aa52 214
emilmont 1:fdd22bb7aa52 215 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 216 *px = in;
emilmont 1:fdd22bb7aa52 217
emilmont 1:fdd22bb7aa52 218 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 219 px += numRowsB;
emilmont 1:fdd22bb7aa52 220
emilmont 1:fdd22bb7aa52 221 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 222 in = *pInB++;
emilmont 1:fdd22bb7aa52 223
emilmont 1:fdd22bb7aa52 224 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 225 *px = in;
emilmont 1:fdd22bb7aa52 226
emilmont 1:fdd22bb7aa52 227 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 228 px += numRowsB;
emilmont 1:fdd22bb7aa52 229
emilmont 1:fdd22bb7aa52 230 /* Read one element from the row */
emilmont 1:fdd22bb7aa52 231 in = *pInB++;
emilmont 1:fdd22bb7aa52 232
emilmont 1:fdd22bb7aa52 233 /* Store one element in the destination */
emilmont 1:fdd22bb7aa52 234 *px = in;
emilmont 1:fdd22bb7aa52 235
emilmont 1:fdd22bb7aa52 236 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 237 px += numRowsB;
emilmont 1:fdd22bb7aa52 238
emilmont 1:fdd22bb7aa52 239 #endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */
emilmont 1:fdd22bb7aa52 240
emilmont 1:fdd22bb7aa52 241 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 242 col--;
emilmont 1:fdd22bb7aa52 243 }
emilmont 1:fdd22bb7aa52 244
emilmont 1:fdd22bb7aa52 245 /* If the columns of pSrcB is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 246 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 247 col = numColsB % 0x4u;
emilmont 1:fdd22bb7aa52 248
emilmont 1:fdd22bb7aa52 249 while(col > 0u)
emilmont 1:fdd22bb7aa52 250 {
emilmont 1:fdd22bb7aa52 251 /* Read and store the input element in the destination */
emilmont 1:fdd22bb7aa52 252 *px = *pInB++;
emilmont 1:fdd22bb7aa52 253
emilmont 1:fdd22bb7aa52 254 /* Update the pointer px to point to the next row of the transposed matrix */
emilmont 1:fdd22bb7aa52 255 px += numRowsB;
emilmont 1:fdd22bb7aa52 256
emilmont 1:fdd22bb7aa52 257 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 258 col--;
emilmont 1:fdd22bb7aa52 259 }
emilmont 1:fdd22bb7aa52 260
emilmont 1:fdd22bb7aa52 261 i++;
emilmont 1:fdd22bb7aa52 262
emilmont 1:fdd22bb7aa52 263 /* Decrement the row loop counter */
emilmont 1:fdd22bb7aa52 264 row--;
emilmont 1:fdd22bb7aa52 265
emilmont 1:fdd22bb7aa52 266 } while(row > 0u);
emilmont 1:fdd22bb7aa52 267
emilmont 1:fdd22bb7aa52 268 /* Reset the variables for the usage in the following multiplication process */
emilmont 1:fdd22bb7aa52 269 row = numRowsA;
emilmont 1:fdd22bb7aa52 270 i = 0u;
emilmont 1:fdd22bb7aa52 271 px = pDst->pData;
emilmont 1:fdd22bb7aa52 272
emilmont 1:fdd22bb7aa52 273 /* The following loop performs the dot-product of each row in pSrcA with each column in pSrcB */
emilmont 1:fdd22bb7aa52 274 /* row loop */
emilmont 1:fdd22bb7aa52 275 do
emilmont 1:fdd22bb7aa52 276 {
emilmont 1:fdd22bb7aa52 277 /* For every row wise process, the column loop counter is to be initiated */
emilmont 1:fdd22bb7aa52 278 col = numColsB;
emilmont 1:fdd22bb7aa52 279
emilmont 1:fdd22bb7aa52 280 /* For every row wise process, the pIn2 pointer is set
emilmont 1:fdd22bb7aa52 281 ** to the starting address of the transposed pSrcB data */
emilmont 1:fdd22bb7aa52 282 pInB = pSrcBT;
emilmont 1:fdd22bb7aa52 283
emilmont 1:fdd22bb7aa52 284 /* column loop */
emilmont 1:fdd22bb7aa52 285 do
emilmont 1:fdd22bb7aa52 286 {
emilmont 1:fdd22bb7aa52 287 /* Set the variable sum, that acts as accumulator, to zero */
emilmont 1:fdd22bb7aa52 288 sum = 0;
emilmont 1:fdd22bb7aa52 289
emilmont 1:fdd22bb7aa52 290 /* Apply loop unrolling and compute 2 MACs simultaneously. */
emilmont 1:fdd22bb7aa52 291 colCnt = numColsA >> 2;
emilmont 1:fdd22bb7aa52 292
emilmont 1:fdd22bb7aa52 293 /* Initiate the pointer pIn1 to point to the starting address of the column being processed */
emilmont 1:fdd22bb7aa52 294 pInA = pSrcA->pData + i;
emilmont 1:fdd22bb7aa52 295
emilmont 1:fdd22bb7aa52 296
emilmont 1:fdd22bb7aa52 297 /* matrix multiplication */
emilmont 1:fdd22bb7aa52 298 while(colCnt > 0u)
emilmont 1:fdd22bb7aa52 299 {
emilmont 1:fdd22bb7aa52 300 /* c(m,n) = a(1,1)*b(1,1) + a(1,2) * b(2,1) + .... + a(m,p)*b(p,n) */
emilmont 1:fdd22bb7aa52 301 #ifndef UNALIGNED_SUPPORT_DISABLE
emilmont 1:fdd22bb7aa52 302
emilmont 1:fdd22bb7aa52 303 /* read real and imag values from pSrcA and pSrcB buffer */
emilmont 1:fdd22bb7aa52 304 pSourceA1 = *__SIMD32(pInA)++;
emilmont 1:fdd22bb7aa52 305 pSourceB1 = *__SIMD32(pInB)++;
emilmont 1:fdd22bb7aa52 306
emilmont 1:fdd22bb7aa52 307 pSourceA2 = *__SIMD32(pInA)++;
emilmont 1:fdd22bb7aa52 308 pSourceB2 = *__SIMD32(pInB)++;
emilmont 1:fdd22bb7aa52 309
emilmont 1:fdd22bb7aa52 310 /* Multiply and Accumlates */
emilmont 1:fdd22bb7aa52 311 sum = __SMLALD(pSourceA1, pSourceB1, sum);
emilmont 1:fdd22bb7aa52 312 sum = __SMLALD(pSourceA2, pSourceB2, sum);
emilmont 1:fdd22bb7aa52 313
emilmont 1:fdd22bb7aa52 314 #else
emilmont 1:fdd22bb7aa52 315 /* read real and imag values from pSrcA and pSrcB buffer */
emilmont 1:fdd22bb7aa52 316 inA1 = *pInA++;
emilmont 1:fdd22bb7aa52 317 inB1 = *pInB++;
emilmont 1:fdd22bb7aa52 318 inA2 = *pInA++;
emilmont 1:fdd22bb7aa52 319 /* Multiply and Accumlates */
emilmont 1:fdd22bb7aa52 320 sum += inA1 * inB1;
emilmont 1:fdd22bb7aa52 321 inB2 = *pInB++;
emilmont 1:fdd22bb7aa52 322
emilmont 1:fdd22bb7aa52 323 inA1 = *pInA++;
emilmont 1:fdd22bb7aa52 324 inB1 = *pInB++;
emilmont 1:fdd22bb7aa52 325 /* Multiply and Accumlates */
emilmont 1:fdd22bb7aa52 326 sum += inA2 * inB2;
emilmont 1:fdd22bb7aa52 327 inA2 = *pInA++;
emilmont 1:fdd22bb7aa52 328 inB2 = *pInB++;
emilmont 1:fdd22bb7aa52 329
emilmont 1:fdd22bb7aa52 330 /* Multiply and Accumlates */
emilmont 1:fdd22bb7aa52 331 sum += inA1 * inB1;
emilmont 1:fdd22bb7aa52 332 sum += inA2 * inB2;
emilmont 1:fdd22bb7aa52 333
emilmont 1:fdd22bb7aa52 334 #endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */
emilmont 1:fdd22bb7aa52 335
emilmont 1:fdd22bb7aa52 336 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 337 colCnt--;
emilmont 1:fdd22bb7aa52 338 }
emilmont 1:fdd22bb7aa52 339
emilmont 1:fdd22bb7aa52 340 /* process remaining column samples */
emilmont 1:fdd22bb7aa52 341 colCnt = numColsA & 3u;
emilmont 1:fdd22bb7aa52 342
emilmont 1:fdd22bb7aa52 343 while(colCnt > 0u)
emilmont 1:fdd22bb7aa52 344 {
emilmont 1:fdd22bb7aa52 345 /* c(m,n) = a(1,1)*b(1,1) + a(1,2) * b(2,1) + .... + a(m,p)*b(p,n) */
emilmont 1:fdd22bb7aa52 346 sum += *pInA++ * *pInB++;
emilmont 1:fdd22bb7aa52 347
emilmont 1:fdd22bb7aa52 348 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 349 colCnt--;
emilmont 1:fdd22bb7aa52 350 }
emilmont 1:fdd22bb7aa52 351
emilmont 1:fdd22bb7aa52 352 /* Saturate and store the result in the destination buffer */
emilmont 1:fdd22bb7aa52 353 *px = (q15_t) (__SSAT((sum >> 15), 16));
emilmont 1:fdd22bb7aa52 354 px++;
emilmont 1:fdd22bb7aa52 355
emilmont 1:fdd22bb7aa52 356 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 357 col--;
emilmont 1:fdd22bb7aa52 358
emilmont 1:fdd22bb7aa52 359 } while(col > 0u);
emilmont 1:fdd22bb7aa52 360
emilmont 1:fdd22bb7aa52 361 i = i + numColsA;
emilmont 1:fdd22bb7aa52 362
emilmont 1:fdd22bb7aa52 363 /* Decrement the row loop counter */
emilmont 1:fdd22bb7aa52 364 row--;
emilmont 1:fdd22bb7aa52 365
emilmont 1:fdd22bb7aa52 366 } while(row > 0u);
emilmont 1:fdd22bb7aa52 367
emilmont 1:fdd22bb7aa52 368 #else
emilmont 1:fdd22bb7aa52 369
emilmont 1:fdd22bb7aa52 370 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 371
emilmont 1:fdd22bb7aa52 372 q15_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */
emilmont 1:fdd22bb7aa52 373 q15_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */
emilmont 1:fdd22bb7aa52 374 q15_t *pInA = pSrcA->pData; /* input data matrix pointer A of Q15 type */
emilmont 1:fdd22bb7aa52 375 q15_t *pInB = pSrcB->pData; /* input data matrix pointer B of Q15 type */
emilmont 1:fdd22bb7aa52 376 q15_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 377 q15_t *px; /* Temporary output data matrix pointer */
emilmont 1:fdd22bb7aa52 378 uint16_t numColsB = pSrcB->numCols; /* number of columns of input matrix B */
emilmont 1:fdd22bb7aa52 379 uint16_t numColsA = pSrcA->numCols; /* number of columns of input matrix A */
emilmont 1:fdd22bb7aa52 380 uint16_t numRowsA = pSrcA->numRows; /* number of rows of input matrix A */
emilmont 1:fdd22bb7aa52 381 uint16_t col, i = 0u, row = numRowsA, colCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 382 arm_status status; /* status of matrix multiplication */
emilmont 1:fdd22bb7aa52 383
emilmont 1:fdd22bb7aa52 384 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 385
emilmont 1:fdd22bb7aa52 386 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 387 if((pSrcA->numCols != pSrcB->numRows) ||
emilmont 1:fdd22bb7aa52 388 (pSrcA->numRows != pDst->numRows) || (pSrcB->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 389 {
emilmont 1:fdd22bb7aa52 390 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 391 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 392 }
emilmont 1:fdd22bb7aa52 393 else
emilmont 1:fdd22bb7aa52 394 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 395
emilmont 1:fdd22bb7aa52 396 {
emilmont 1:fdd22bb7aa52 397 /* The following loop performs the dot-product of each row in pSrcA with each column in pSrcB */
emilmont 1:fdd22bb7aa52 398 /* row loop */
emilmont 1:fdd22bb7aa52 399 do
emilmont 1:fdd22bb7aa52 400 {
emilmont 1:fdd22bb7aa52 401 /* Output pointer is set to starting address of the row being processed */
emilmont 1:fdd22bb7aa52 402 px = pOut + i;
emilmont 1:fdd22bb7aa52 403
emilmont 1:fdd22bb7aa52 404 /* For every row wise process, the column loop counter is to be initiated */
emilmont 1:fdd22bb7aa52 405 col = numColsB;
emilmont 1:fdd22bb7aa52 406
emilmont 1:fdd22bb7aa52 407 /* For every row wise process, the pIn2 pointer is set
emilmont 1:fdd22bb7aa52 408 ** to the starting address of the pSrcB data */
emilmont 1:fdd22bb7aa52 409 pIn2 = pSrcB->pData;
emilmont 1:fdd22bb7aa52 410
emilmont 1:fdd22bb7aa52 411 /* column loop */
emilmont 1:fdd22bb7aa52 412 do
emilmont 1:fdd22bb7aa52 413 {
emilmont 1:fdd22bb7aa52 414 /* Set the variable sum, that acts as accumulator, to zero */
emilmont 1:fdd22bb7aa52 415 sum = 0;
emilmont 1:fdd22bb7aa52 416
emilmont 1:fdd22bb7aa52 417 /* Initiate the pointer pIn1 to point to the starting address of pSrcA */
emilmont 1:fdd22bb7aa52 418 pIn1 = pInA;
emilmont 1:fdd22bb7aa52 419
emilmont 1:fdd22bb7aa52 420 /* Matrix A columns number of MAC operations are to be performed */
emilmont 1:fdd22bb7aa52 421 colCnt = numColsA;
emilmont 1:fdd22bb7aa52 422
emilmont 1:fdd22bb7aa52 423 /* matrix multiplication */
emilmont 1:fdd22bb7aa52 424 while(colCnt > 0u)
emilmont 1:fdd22bb7aa52 425 {
emilmont 1:fdd22bb7aa52 426 /* c(m,n) = a(1,1)*b(1,1) + a(1,2) * b(2,1) + .... + a(m,p)*b(p,n) */
emilmont 1:fdd22bb7aa52 427 /* Perform the multiply-accumulates */
emilmont 1:fdd22bb7aa52 428 sum += (q31_t) * pIn1++ * *pIn2;
emilmont 1:fdd22bb7aa52 429 pIn2 += numColsB;
emilmont 1:fdd22bb7aa52 430
emilmont 1:fdd22bb7aa52 431 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 432 colCnt--;
emilmont 1:fdd22bb7aa52 433 }
emilmont 1:fdd22bb7aa52 434
emilmont 1:fdd22bb7aa52 435 /* Convert the result from 34.30 to 1.15 format and store the saturated value in destination buffer */
emilmont 1:fdd22bb7aa52 436 /* Saturate and store the result in the destination buffer */
emilmont 1:fdd22bb7aa52 437 *px++ = (q15_t) __SSAT((sum >> 15), 16);
emilmont 1:fdd22bb7aa52 438
emilmont 1:fdd22bb7aa52 439 /* Decrement the column loop counter */
emilmont 1:fdd22bb7aa52 440 col--;
emilmont 1:fdd22bb7aa52 441
emilmont 1:fdd22bb7aa52 442 /* Update the pointer pIn2 to point to the starting address of the next column */
emilmont 1:fdd22bb7aa52 443 pIn2 = pInB + (numColsB - col);
emilmont 1:fdd22bb7aa52 444
emilmont 1:fdd22bb7aa52 445 } while(col > 0u);
emilmont 1:fdd22bb7aa52 446
emilmont 1:fdd22bb7aa52 447 /* Update the pointer pSrcA to point to the starting address of the next row */
emilmont 1:fdd22bb7aa52 448 i = i + numColsB;
emilmont 1:fdd22bb7aa52 449 pInA = pInA + numColsA;
emilmont 1:fdd22bb7aa52 450
emilmont 1:fdd22bb7aa52 451 /* Decrement the row loop counter */
emilmont 1:fdd22bb7aa52 452 row--;
emilmont 1:fdd22bb7aa52 453
emilmont 1:fdd22bb7aa52 454 } while(row > 0u);
emilmont 1:fdd22bb7aa52 455
emilmont 1:fdd22bb7aa52 456 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 457 /* set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 458 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 459 }
emilmont 1:fdd22bb7aa52 460
emilmont 1:fdd22bb7aa52 461 /* Return to application */
emilmont 1:fdd22bb7aa52 462 return (status);
emilmont 1:fdd22bb7aa52 463 }
emilmont 1:fdd22bb7aa52 464
emilmont 1:fdd22bb7aa52 465 /**
emilmont 1:fdd22bb7aa52 466 * @} end of MatrixMult group
emilmont 1:fdd22bb7aa52 467 */