Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_dot_prod_f32.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?

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_dot_prod_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Floating-point dot product.
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 /**
mbed_official 3:7a284390b0ce 44 * @ingroup groupMath
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
mbed_official 3:7a284390b0ce 47 /**
mbed_official 3:7a284390b0ce 48 * @defgroup dot_prod Vector Dot Product
mbed_official 3:7a284390b0ce 49 *
mbed_official 3:7a284390b0ce 50 * Computes the dot product of two vectors.
mbed_official 3:7a284390b0ce 51 * The vectors are multiplied element-by-element and then summed.
mbed_official 3:7a284390b0ce 52 *
mbed_official 3:7a284390b0ce 53 * <pre>
mbed_official 3:7a284390b0ce 54 * sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
mbed_official 3:7a284390b0ce 55 * </pre>
mbed_official 3:7a284390b0ce 56 *
emilmont 1:fdd22bb7aa52 57 * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
emilmont 1:fdd22bb7aa52 58 */
emilmont 1:fdd22bb7aa52 59
emilmont 1:fdd22bb7aa52 60 /**
emilmont 1:fdd22bb7aa52 61 * @addtogroup dot_prod
emilmont 1:fdd22bb7aa52 62 * @{
emilmont 1:fdd22bb7aa52 63 */
emilmont 1:fdd22bb7aa52 64
emilmont 1:fdd22bb7aa52 65 /**
emilmont 1:fdd22bb7aa52 66 * @brief Dot product of floating-point vectors.
emilmont 1:fdd22bb7aa52 67 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 68 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 69 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 70 * @param[out] *result output result returned here
emilmont 1:fdd22bb7aa52 71 * @return none.
emilmont 1:fdd22bb7aa52 72 */
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 void arm_dot_prod_f32(
emilmont 1:fdd22bb7aa52 76 float32_t * pSrcA,
emilmont 1:fdd22bb7aa52 77 float32_t * pSrcB,
emilmont 1:fdd22bb7aa52 78 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 79 float32_t * result)
emilmont 1:fdd22bb7aa52 80 {
emilmont 1:fdd22bb7aa52 81 float32_t sum = 0.0f; /* Temporary result storage */
emilmont 1:fdd22bb7aa52 82 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84
mbed_official 3:7a284390b0ce 85 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 88 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 89 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 90
emilmont 1:fdd22bb7aa52 91 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 92 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 93 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 94 {
emilmont 1:fdd22bb7aa52 95 /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
emilmont 1:fdd22bb7aa52 96 /* Calculate dot product and then store the result in a temporary buffer */
emilmont 1:fdd22bb7aa52 97 sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 98 sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 99 sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 100 sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 103 blkCnt--;
emilmont 1:fdd22bb7aa52 104 }
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 107 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 108 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110 #else
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 115 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 116
mbed_official 3:7a284390b0ce 117 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 121 {
emilmont 1:fdd22bb7aa52 122 /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
emilmont 1:fdd22bb7aa52 123 /* Calculate dot product and then store the result in a temporary buffer. */
emilmont 1:fdd22bb7aa52 124 sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 127 blkCnt--;
emilmont 1:fdd22bb7aa52 128 }
emilmont 1:fdd22bb7aa52 129 /* Store the result back in the destination buffer */
emilmont 1:fdd22bb7aa52 130 *result = sum;
emilmont 1:fdd22bb7aa52 131 }
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 /**
emilmont 1:fdd22bb7aa52 134 * @} end of dot_prod group
emilmont 1:fdd22bb7aa52 135 */