Laxmi Kant Tiwari / mbed-dsp

Important changes to repositories hosted on mbed.com

Mbed hosted mercurial repositories are deprecated and are due to be permanently deleted in July 2026.

To keep a copy of this software download the repository Zip archive or clone locally using Mercurial.

It is also possible to export all your personal repositories from the account settings page.

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_add_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_add_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Floating-point vector 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 0.0.7 2010/06/10
emilmont 1:fdd22bb7aa52 33 * Misra-C changes done
emilmont 1:fdd22bb7aa52 34 * ---------------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 35
emilmont 1:fdd22bb7aa52 36 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 37
emilmont 1:fdd22bb7aa52 38 /**
emilmont 1:fdd22bb7aa52 39 * @ingroup groupMath
emilmont 1:fdd22bb7aa52 40 */
emilmont 1:fdd22bb7aa52 41
emilmont 1:fdd22bb7aa52 42 /**
emilmont 1:fdd22bb7aa52 43 * @defgroup BasicAdd Vector Addition
emilmont 1:fdd22bb7aa52 44 *
emilmont 1:fdd22bb7aa52 45 * Element-by-element addition of two vectors.
emilmont 1:fdd22bb7aa52 46 *
emilmont 1:fdd22bb7aa52 47 * <pre>
emilmont 1:fdd22bb7aa52 48 * pDst[n] = pSrcA[n] + pSrcB[n], 0 <= n < blockSize.
emilmont 1:fdd22bb7aa52 49 * </pre>
emilmont 1:fdd22bb7aa52 50 *
emilmont 1:fdd22bb7aa52 51 * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
emilmont 1:fdd22bb7aa52 52 */
emilmont 1:fdd22bb7aa52 53
emilmont 1:fdd22bb7aa52 54 /**
emilmont 1:fdd22bb7aa52 55 * @addtogroup BasicAdd
emilmont 1:fdd22bb7aa52 56 * @{
emilmont 1:fdd22bb7aa52 57 */
emilmont 1:fdd22bb7aa52 58
emilmont 1:fdd22bb7aa52 59 /**
emilmont 1:fdd22bb7aa52 60 * @brief Floating-point vector addition.
emilmont 1:fdd22bb7aa52 61 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 62 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 63 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 64 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 65 * @return none.
emilmont 1:fdd22bb7aa52 66 */
emilmont 1:fdd22bb7aa52 67
emilmont 1:fdd22bb7aa52 68 void arm_add_f32(
emilmont 1:fdd22bb7aa52 69 float32_t * pSrcA,
emilmont 1:fdd22bb7aa52 70 float32_t * pSrcB,
emilmont 1:fdd22bb7aa52 71 float32_t * pDst,
emilmont 1:fdd22bb7aa52 72 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 73 {
emilmont 1:fdd22bb7aa52 74 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 75
emilmont 1:fdd22bb7aa52 76 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 79 float32_t inA1, inA2, inA3, inA4; /* temporary input variabels */
emilmont 1:fdd22bb7aa52 80 float32_t inB1, inB2, inB3, inB4; /* temporary input variables */
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 83 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 86 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 87 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 88 {
emilmont 1:fdd22bb7aa52 89 /* C = A + B */
emilmont 1:fdd22bb7aa52 90 /* Add and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 91
emilmont 1:fdd22bb7aa52 92 /* read four inputs from sourceA and four inputs from sourceB */
emilmont 1:fdd22bb7aa52 93 inA1 = *pSrcA;
emilmont 1:fdd22bb7aa52 94 inB1 = *pSrcB;
emilmont 1:fdd22bb7aa52 95 inA2 = *(pSrcA + 1);
emilmont 1:fdd22bb7aa52 96 inB2 = *(pSrcB + 1);
emilmont 1:fdd22bb7aa52 97 inA3 = *(pSrcA + 2);
emilmont 1:fdd22bb7aa52 98 inB3 = *(pSrcB + 2);
emilmont 1:fdd22bb7aa52 99 inA4 = *(pSrcA + 3);
emilmont 1:fdd22bb7aa52 100 inB4 = *(pSrcB + 3);
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* C = A + B */
emilmont 1:fdd22bb7aa52 103 /* add and store result to destination */
emilmont 1:fdd22bb7aa52 104 *pDst = inA1 + inB1;
emilmont 1:fdd22bb7aa52 105 *(pDst + 1) = inA2 + inB2;
emilmont 1:fdd22bb7aa52 106 *(pDst + 2) = inA3 + inB3;
emilmont 1:fdd22bb7aa52 107 *(pDst + 3) = inA4 + inB4;
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 /* update pointers to process next samples */
emilmont 1:fdd22bb7aa52 110 pSrcA += 4u;
emilmont 1:fdd22bb7aa52 111 pSrcB += 4u;
emilmont 1:fdd22bb7aa52 112 pDst += 4u;
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 116 blkCnt--;
emilmont 1:fdd22bb7aa52 117 }
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 120 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 121 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 #else
emilmont 1:fdd22bb7aa52 124
emilmont 1:fdd22bb7aa52 125 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 128 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 133 {
emilmont 1:fdd22bb7aa52 134 /* C = A + B */
emilmont 1:fdd22bb7aa52 135 /* Add and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 136 *pDst++ = (*pSrcA++) + (*pSrcB++);
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 139 blkCnt--;
emilmont 1:fdd22bb7aa52 140 }
emilmont 1:fdd22bb7aa52 141 }
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /**
emilmont 1:fdd22bb7aa52 144 * @} end of BasicAdd group
emilmont 1:fdd22bb7aa52 145 */