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
cmsis_dsp/MatrixFunctions/arm_mat_mult_fast_q31.c@3:7a284390b0ce, 2013-11-08 (annotated)
- Committer:
- mbed_official
- Date:
- Fri Nov 08 13:45:10 2013 +0000
- Revision:
- 3:7a284390b0ce
- Parent:
- 2:da51fb522205
Synchronized with git revision e69956aba2f68a2a26ac26b051f8d349deaa1ce8
Who changed what in which revision?
User | Revision | Line number | New 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_mult_fast_q31.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 10 | * Description: Q31 matrix multiplication (fast variant). |
emilmont | 1:fdd22bb7aa52 | 11 | * |
emilmont | 1:fdd22bb7aa52 | 12 | * Target Processor: Cortex-M4/Cortex-M3 |
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 MatrixMult |
emilmont | 1:fdd22bb7aa52 | 49 | * @{ |
emilmont | 1:fdd22bb7aa52 | 50 | */ |
emilmont | 1:fdd22bb7aa52 | 51 | |
emilmont | 1:fdd22bb7aa52 | 52 | /** |
emilmont | 1:fdd22bb7aa52 | 53 | * @brief Q31 matrix multiplication (fast variant) for Cortex-M3 and Cortex-M4 |
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 | * @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 difference between the function arm_mat_mult_q31() and this fast variant is that |
emilmont | 1:fdd22bb7aa52 | 65 | * the fast variant use a 32-bit rather than a 64-bit accumulator. |
emilmont | 1:fdd22bb7aa52 | 66 | * The result of each 1.31 x 1.31 multiplication is truncated to |
emilmont | 1:fdd22bb7aa52 | 67 | * 2.30 format. These intermediate results are accumulated in a 32-bit register in 2.30 |
emilmont | 1:fdd22bb7aa52 | 68 | * format. Finally, the accumulator is saturated and converted to a 1.31 result. |
emilmont | 1:fdd22bb7aa52 | 69 | * |
emilmont | 1:fdd22bb7aa52 | 70 | * \par |
emilmont | 1:fdd22bb7aa52 | 71 | * The fast version has the same overflow behavior as the standard version but provides |
emilmont | 1:fdd22bb7aa52 | 72 | * less precision since it discards the low 32 bits of each multiplication result. |
emilmont | 1:fdd22bb7aa52 | 73 | * In order to avoid overflows completely the input signals must be scaled down. |
emilmont | 1:fdd22bb7aa52 | 74 | * Scale down one of the input matrices by log2(numColsA) bits to |
emilmont | 1:fdd22bb7aa52 | 75 | * avoid overflows, as a total of numColsA additions are computed internally for each |
emilmont | 1:fdd22bb7aa52 | 76 | * output element. |
emilmont | 1:fdd22bb7aa52 | 77 | * |
emilmont | 1:fdd22bb7aa52 | 78 | * \par |
emilmont | 1:fdd22bb7aa52 | 79 | * See <code>arm_mat_mult_q31()</code> for a slower implementation of this function |
emilmont | 1:fdd22bb7aa52 | 80 | * which uses 64-bit accumulation to provide higher precision. |
emilmont | 1:fdd22bb7aa52 | 81 | */ |
emilmont | 1:fdd22bb7aa52 | 82 | |
emilmont | 1:fdd22bb7aa52 | 83 | arm_status arm_mat_mult_fast_q31( |
emilmont | 1:fdd22bb7aa52 | 84 | const arm_matrix_instance_q31 * pSrcA, |
emilmont | 1:fdd22bb7aa52 | 85 | const arm_matrix_instance_q31 * pSrcB, |
emilmont | 1:fdd22bb7aa52 | 86 | arm_matrix_instance_q31 * pDst) |
emilmont | 1:fdd22bb7aa52 | 87 | { |
emilmont | 1:fdd22bb7aa52 | 88 | q31_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */ |
emilmont | 1:fdd22bb7aa52 | 89 | q31_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */ |
emilmont | 1:fdd22bb7aa52 | 90 | q31_t *pInA = pSrcA->pData; /* input data matrix pointer A */ |
emilmont | 1:fdd22bb7aa52 | 91 | // q31_t *pSrcB = pSrcB->pData; /* input data matrix pointer B */ |
emilmont | 1:fdd22bb7aa52 | 92 | q31_t *pOut = pDst->pData; /* output data matrix pointer */ |
emilmont | 1:fdd22bb7aa52 | 93 | q31_t *px; /* Temporary output data matrix pointer */ |
emilmont | 1:fdd22bb7aa52 | 94 | q31_t sum; /* Accumulator */ |
emilmont | 1:fdd22bb7aa52 | 95 | uint16_t numRowsA = pSrcA->numRows; /* number of rows of input matrix A */ |
emilmont | 1:fdd22bb7aa52 | 96 | uint16_t numColsB = pSrcB->numCols; /* number of columns of input matrix B */ |
emilmont | 1:fdd22bb7aa52 | 97 | uint16_t numColsA = pSrcA->numCols; /* number of columns of input matrix A */ |
emilmont | 1:fdd22bb7aa52 | 98 | uint16_t col, i = 0u, j, row = numRowsA, colCnt; /* loop counters */ |
emilmont | 1:fdd22bb7aa52 | 99 | arm_status status; /* status of matrix multiplication */ |
emilmont | 1:fdd22bb7aa52 | 100 | q31_t inA1, inA2, inA3, inA4, inB1, inB2, inB3, inB4; |
emilmont | 1:fdd22bb7aa52 | 101 | |
emilmont | 1:fdd22bb7aa52 | 102 | #ifdef ARM_MATH_MATRIX_CHECK |
emilmont | 1:fdd22bb7aa52 | 103 | |
emilmont | 1:fdd22bb7aa52 | 104 | |
emilmont | 1:fdd22bb7aa52 | 105 | /* Check for matrix mismatch condition */ |
emilmont | 1:fdd22bb7aa52 | 106 | if((pSrcA->numCols != pSrcB->numRows) || |
emilmont | 1:fdd22bb7aa52 | 107 | (pSrcA->numRows != pDst->numRows) || (pSrcB->numCols != pDst->numCols)) |
emilmont | 1:fdd22bb7aa52 | 108 | { |
emilmont | 1:fdd22bb7aa52 | 109 | /* Set status as ARM_MATH_SIZE_MISMATCH */ |
emilmont | 1:fdd22bb7aa52 | 110 | status = ARM_MATH_SIZE_MISMATCH; |
emilmont | 1:fdd22bb7aa52 | 111 | } |
emilmont | 1:fdd22bb7aa52 | 112 | else |
emilmont | 1:fdd22bb7aa52 | 113 | #endif /* #ifdef ARM_MATH_MATRIX_CHECK */ |
emilmont | 1:fdd22bb7aa52 | 114 | |
emilmont | 1:fdd22bb7aa52 | 115 | { |
emilmont | 1:fdd22bb7aa52 | 116 | /* The following loop performs the dot-product of each row in pSrcA with each column in pSrcB */ |
emilmont | 1:fdd22bb7aa52 | 117 | /* row loop */ |
emilmont | 1:fdd22bb7aa52 | 118 | do |
emilmont | 1:fdd22bb7aa52 | 119 | { |
emilmont | 1:fdd22bb7aa52 | 120 | /* Output pointer is set to starting address of the row being processed */ |
emilmont | 1:fdd22bb7aa52 | 121 | px = pOut + i; |
emilmont | 1:fdd22bb7aa52 | 122 | |
emilmont | 1:fdd22bb7aa52 | 123 | /* For every row wise process, the column loop counter is to be initiated */ |
emilmont | 1:fdd22bb7aa52 | 124 | col = numColsB; |
emilmont | 1:fdd22bb7aa52 | 125 | |
emilmont | 1:fdd22bb7aa52 | 126 | /* For every row wise process, the pIn2 pointer is set |
emilmont | 1:fdd22bb7aa52 | 127 | ** to the starting address of the pSrcB data */ |
emilmont | 1:fdd22bb7aa52 | 128 | pIn2 = pSrcB->pData; |
emilmont | 1:fdd22bb7aa52 | 129 | |
emilmont | 1:fdd22bb7aa52 | 130 | j = 0u; |
emilmont | 1:fdd22bb7aa52 | 131 | |
emilmont | 1:fdd22bb7aa52 | 132 | /* column loop */ |
emilmont | 1:fdd22bb7aa52 | 133 | do |
emilmont | 1:fdd22bb7aa52 | 134 | { |
emilmont | 1:fdd22bb7aa52 | 135 | /* Set the variable sum, that acts as accumulator, to zero */ |
emilmont | 1:fdd22bb7aa52 | 136 | sum = 0; |
emilmont | 1:fdd22bb7aa52 | 137 | |
emilmont | 1:fdd22bb7aa52 | 138 | /* Initiate the pointer pIn1 to point to the starting address of pInA */ |
emilmont | 1:fdd22bb7aa52 | 139 | pIn1 = pInA; |
emilmont | 1:fdd22bb7aa52 | 140 | |
emilmont | 1:fdd22bb7aa52 | 141 | /* Apply loop unrolling and compute 4 MACs simultaneously. */ |
emilmont | 1:fdd22bb7aa52 | 142 | colCnt = numColsA >> 2; |
emilmont | 1:fdd22bb7aa52 | 143 | |
emilmont | 1:fdd22bb7aa52 | 144 | |
emilmont | 1:fdd22bb7aa52 | 145 | /* matrix multiplication */ |
emilmont | 1:fdd22bb7aa52 | 146 | while(colCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 147 | { |
emilmont | 1:fdd22bb7aa52 | 148 | /* c(m,n) = a(1,1)*b(1,1) + a(1,2) * b(2,1) + .... + a(m,p)*b(p,n) */ |
emilmont | 1:fdd22bb7aa52 | 149 | /* Perform the multiply-accumulates */ |
emilmont | 1:fdd22bb7aa52 | 150 | inB1 = *pIn2; |
emilmont | 1:fdd22bb7aa52 | 151 | pIn2 += numColsB; |
emilmont | 1:fdd22bb7aa52 | 152 | |
emilmont | 1:fdd22bb7aa52 | 153 | inA1 = pIn1[0]; |
emilmont | 1:fdd22bb7aa52 | 154 | inA2 = pIn1[1]; |
emilmont | 1:fdd22bb7aa52 | 155 | |
emilmont | 1:fdd22bb7aa52 | 156 | inB2 = *pIn2; |
emilmont | 1:fdd22bb7aa52 | 157 | pIn2 += numColsB; |
emilmont | 1:fdd22bb7aa52 | 158 | |
emilmont | 1:fdd22bb7aa52 | 159 | inB3 = *pIn2; |
emilmont | 1:fdd22bb7aa52 | 160 | pIn2 += numColsB; |
emilmont | 1:fdd22bb7aa52 | 161 | |
emilmont | 1:fdd22bb7aa52 | 162 | sum = (q31_t) ((((q63_t) sum << 32) + ((q63_t) inA1 * inB1)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 163 | sum = (q31_t) ((((q63_t) sum << 32) + ((q63_t) inA2 * inB2)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 164 | |
emilmont | 1:fdd22bb7aa52 | 165 | inA3 = pIn1[2]; |
emilmont | 1:fdd22bb7aa52 | 166 | inA4 = pIn1[3]; |
emilmont | 1:fdd22bb7aa52 | 167 | |
emilmont | 1:fdd22bb7aa52 | 168 | inB4 = *pIn2; |
emilmont | 1:fdd22bb7aa52 | 169 | pIn2 += numColsB; |
emilmont | 1:fdd22bb7aa52 | 170 | |
emilmont | 1:fdd22bb7aa52 | 171 | sum = (q31_t) ((((q63_t) sum << 32) + ((q63_t) inA3 * inB3)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 172 | sum = (q31_t) ((((q63_t) sum << 32) + ((q63_t) inA4 * inB4)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 173 | |
emilmont | 1:fdd22bb7aa52 | 174 | pIn1 += 4u; |
emilmont | 1:fdd22bb7aa52 | 175 | |
emilmont | 1:fdd22bb7aa52 | 176 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 177 | colCnt--; |
emilmont | 1:fdd22bb7aa52 | 178 | } |
emilmont | 1:fdd22bb7aa52 | 179 | |
emilmont | 1:fdd22bb7aa52 | 180 | /* If the columns of pSrcA is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 181 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 182 | colCnt = numColsA % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 183 | |
emilmont | 1:fdd22bb7aa52 | 184 | while(colCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 185 | { |
emilmont | 1:fdd22bb7aa52 | 186 | /* c(m,n) = a(1,1)*b(1,1) + a(1,2) * b(2,1) + .... + a(m,p)*b(p,n) */ |
emilmont | 1:fdd22bb7aa52 | 187 | /* Perform the multiply-accumulates */ |
emilmont | 1:fdd22bb7aa52 | 188 | sum = (q31_t) ((((q63_t) sum << 32) + |
emilmont | 1:fdd22bb7aa52 | 189 | ((q63_t) * pIn1++ * (*pIn2))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 190 | pIn2 += numColsB; |
emilmont | 1:fdd22bb7aa52 | 191 | |
emilmont | 1:fdd22bb7aa52 | 192 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 193 | colCnt--; |
emilmont | 1:fdd22bb7aa52 | 194 | } |
emilmont | 1:fdd22bb7aa52 | 195 | |
emilmont | 1:fdd22bb7aa52 | 196 | /* Convert the result from 2.30 to 1.31 format and store in destination buffer */ |
emilmont | 1:fdd22bb7aa52 | 197 | *px++ = sum << 1; |
emilmont | 1:fdd22bb7aa52 | 198 | |
emilmont | 1:fdd22bb7aa52 | 199 | /* Update the pointer pIn2 to point to the starting address of the next column */ |
emilmont | 1:fdd22bb7aa52 | 200 | j++; |
emilmont | 1:fdd22bb7aa52 | 201 | pIn2 = pSrcB->pData + j; |
emilmont | 1:fdd22bb7aa52 | 202 | |
emilmont | 1:fdd22bb7aa52 | 203 | /* Decrement the column loop counter */ |
emilmont | 1:fdd22bb7aa52 | 204 | col--; |
emilmont | 1:fdd22bb7aa52 | 205 | |
emilmont | 1:fdd22bb7aa52 | 206 | } while(col > 0u); |
emilmont | 1:fdd22bb7aa52 | 207 | |
emilmont | 1:fdd22bb7aa52 | 208 | /* Update the pointer pInA to point to the starting address of the next row */ |
emilmont | 1:fdd22bb7aa52 | 209 | i = i + numColsB; |
emilmont | 1:fdd22bb7aa52 | 210 | pInA = pInA + numColsA; |
emilmont | 1:fdd22bb7aa52 | 211 | |
emilmont | 1:fdd22bb7aa52 | 212 | /* Decrement the row loop counter */ |
emilmont | 1:fdd22bb7aa52 | 213 | row--; |
emilmont | 1:fdd22bb7aa52 | 214 | |
emilmont | 1:fdd22bb7aa52 | 215 | } while(row > 0u); |
emilmont | 1:fdd22bb7aa52 | 216 | |
emilmont | 1:fdd22bb7aa52 | 217 | /* set status as ARM_MATH_SUCCESS */ |
emilmont | 1:fdd22bb7aa52 | 218 | status = ARM_MATH_SUCCESS; |
emilmont | 1:fdd22bb7aa52 | 219 | } |
emilmont | 1:fdd22bb7aa52 | 220 | /* Return to application */ |
emilmont | 1:fdd22bb7aa52 | 221 | return (status); |
emilmont | 1:fdd22bb7aa52 | 222 | } |
emilmont | 1:fdd22bb7aa52 | 223 | |
emilmont | 1:fdd22bb7aa52 | 224 | /** |
emilmont | 1:fdd22bb7aa52 | 225 | * @} end of MatrixMult group |
emilmont | 1:fdd22bb7aa52 | 226 | */ |