Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_mult_f32.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_mult_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Floating-point vector 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 groupMath
emilmont 1:fdd22bb7aa52 43 */
emilmont 1:fdd22bb7aa52 44
emilmont 1:fdd22bb7aa52 45 /**
emilmont 1:fdd22bb7aa52 46 * @defgroup BasicMult Vector Multiplication
emilmont 1:fdd22bb7aa52 47 *
emilmont 1:fdd22bb7aa52 48 * Element-by-element multiplication of two vectors.
emilmont 1:fdd22bb7aa52 49 *
emilmont 1:fdd22bb7aa52 50 * <pre>
emilmont 1:fdd22bb7aa52 51 * pDst[n] = pSrcA[n] * pSrcB[n], 0 <= n < blockSize.
emilmont 1:fdd22bb7aa52 52 * </pre>
emilmont 1:fdd22bb7aa52 53 *
emilmont 1:fdd22bb7aa52 54 * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
emilmont 1:fdd22bb7aa52 55 */
emilmont 1:fdd22bb7aa52 56
emilmont 1:fdd22bb7aa52 57 /**
emilmont 1:fdd22bb7aa52 58 * @addtogroup BasicMult
emilmont 1:fdd22bb7aa52 59 * @{
emilmont 1:fdd22bb7aa52 60 */
emilmont 1:fdd22bb7aa52 61
emilmont 1:fdd22bb7aa52 62 /**
emilmont 1:fdd22bb7aa52 63 * @brief Floating-point vector multiplication.
emilmont 1:fdd22bb7aa52 64 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 65 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 66 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 67 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 68 * @return none.
emilmont 1:fdd22bb7aa52 69 */
emilmont 1:fdd22bb7aa52 70
emilmont 1:fdd22bb7aa52 71 void arm_mult_f32(
emilmont 1:fdd22bb7aa52 72 float32_t * pSrcA,
emilmont 1:fdd22bb7aa52 73 float32_t * pSrcB,
emilmont 1:fdd22bb7aa52 74 float32_t * pDst,
emilmont 1:fdd22bb7aa52 75 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 76 {
emilmont 1:fdd22bb7aa52 77 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 78 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 81 float32_t inA1, inA2, inA3, inA4; /* temporary input variables */
emilmont 1:fdd22bb7aa52 82 float32_t inB1, inB2, inB3, inB4; /* temporary input variables */
emilmont 1:fdd22bb7aa52 83 float32_t out1, out2, out3, out4; /* temporary output variables */
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 86 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 87
emilmont 1:fdd22bb7aa52 88 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 89 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 90 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 91 {
emilmont 1:fdd22bb7aa52 92 /* C = A * B */
emilmont 1:fdd22bb7aa52 93 /* Multiply the inputs and store the results in output buffer */
emilmont 1:fdd22bb7aa52 94 /* read sample from sourceA */
emilmont 1:fdd22bb7aa52 95 inA1 = *pSrcA;
emilmont 1:fdd22bb7aa52 96 /* read sample from sourceB */
emilmont 1:fdd22bb7aa52 97 inB1 = *pSrcB;
emilmont 1:fdd22bb7aa52 98 /* read sample from sourceA */
emilmont 1:fdd22bb7aa52 99 inA2 = *(pSrcA + 1);
emilmont 1:fdd22bb7aa52 100 /* read sample from sourceB */
emilmont 1:fdd22bb7aa52 101 inB2 = *(pSrcB + 1);
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 /* out = sourceA * sourceB */
emilmont 1:fdd22bb7aa52 104 out1 = inA1 * inB1;
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* read sample from sourceA */
emilmont 1:fdd22bb7aa52 107 inA3 = *(pSrcA + 2);
emilmont 1:fdd22bb7aa52 108 /* read sample from sourceB */
emilmont 1:fdd22bb7aa52 109 inB3 = *(pSrcB + 2);
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* out = sourceA * sourceB */
emilmont 1:fdd22bb7aa52 112 out2 = inA2 * inB2;
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 /* read sample from sourceA */
emilmont 1:fdd22bb7aa52 115 inA4 = *(pSrcA + 3);
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* store result to destination buffer */
emilmont 1:fdd22bb7aa52 118 *pDst = out1;
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 /* read sample from sourceB */
emilmont 1:fdd22bb7aa52 121 inB4 = *(pSrcB + 3);
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* out = sourceA * sourceB */
emilmont 1:fdd22bb7aa52 124 out3 = inA3 * inB3;
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* store result to destination buffer */
emilmont 1:fdd22bb7aa52 127 *(pDst + 1) = out2;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* out = sourceA * sourceB */
emilmont 1:fdd22bb7aa52 130 out4 = inA4 * inB4;
emilmont 1:fdd22bb7aa52 131 /* store result to destination buffer */
emilmont 1:fdd22bb7aa52 132 *(pDst + 2) = out3;
emilmont 1:fdd22bb7aa52 133 /* store result to destination buffer */
emilmont 1:fdd22bb7aa52 134 *(pDst + 3) = out4;
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136
emilmont 1:fdd22bb7aa52 137 /* update pointers to process next samples */
emilmont 1:fdd22bb7aa52 138 pSrcA += 4u;
emilmont 1:fdd22bb7aa52 139 pSrcB += 4u;
emilmont 1:fdd22bb7aa52 140 pDst += 4u;
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 143 blkCnt--;
emilmont 1:fdd22bb7aa52 144 }
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 147 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 148 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 #else
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 155 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 156
emilmont 1:fdd22bb7aa52 157 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 160 {
emilmont 1:fdd22bb7aa52 161 /* C = A * B */
emilmont 1:fdd22bb7aa52 162 /* Multiply the inputs and store the results in output buffer */
emilmont 1:fdd22bb7aa52 163 *pDst++ = (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 166 blkCnt--;
emilmont 1:fdd22bb7aa52 167 }
emilmont 1:fdd22bb7aa52 168 }
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 /**
emilmont 1:fdd22bb7aa52 171 * @} end of BasicMult group
emilmont 1:fdd22bb7aa52 172 */