Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_abs_f32.c@2:da51fb522205, 2013-05-30 (annotated)

Committer:
emilmont
Date:
Thu May 30 17:10:11 2013 +0100
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source

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 2:da51fb522205 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_abs_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Vector absolute value.
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 #include <math.h>
emilmont 1:fdd22bb7aa52 38
emilmont 1:fdd22bb7aa52 39 /**
emilmont 1:fdd22bb7aa52 40 * @ingroup groupMath
emilmont 1:fdd22bb7aa52 41 */
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @defgroup BasicAbs Vector Absolute Value
emilmont 1:fdd22bb7aa52 45 *
emilmont 1:fdd22bb7aa52 46 * Computes the absolute value of a vector on an element-by-element basis.
emilmont 1:fdd22bb7aa52 47 *
emilmont 1:fdd22bb7aa52 48 * <pre>
emilmont 1:fdd22bb7aa52 49 * pDst[n] = abs(pSrcA[n]), 0 <= n < blockSize.
emilmont 1:fdd22bb7aa52 50 * </pre>
emilmont 1:fdd22bb7aa52 51 *
emilmont 1:fdd22bb7aa52 52 * The operation can be done in-place by setting the input and output pointers to the same buffer.
emilmont 1:fdd22bb7aa52 53 * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
emilmont 1:fdd22bb7aa52 54 */
emilmont 1:fdd22bb7aa52 55
emilmont 1:fdd22bb7aa52 56 /**
emilmont 1:fdd22bb7aa52 57 * @addtogroup BasicAbs
emilmont 1:fdd22bb7aa52 58 * @{
emilmont 1:fdd22bb7aa52 59 */
emilmont 1:fdd22bb7aa52 60
emilmont 1:fdd22bb7aa52 61 /**
emilmont 1:fdd22bb7aa52 62 * @brief Floating-point vector absolute value.
emilmont 1:fdd22bb7aa52 63 * @param[in] *pSrc points to the input buffer
emilmont 1:fdd22bb7aa52 64 * @param[out] *pDst points to the output buffer
emilmont 1:fdd22bb7aa52 65 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 66 * @return none.
emilmont 1:fdd22bb7aa52 67 */
emilmont 1:fdd22bb7aa52 68
emilmont 1:fdd22bb7aa52 69 void arm_abs_f32(
emilmont 1:fdd22bb7aa52 70 float32_t * pSrc,
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 in1, in2, in3, in4; /* temporary variables */
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 82 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 85 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 86 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 87 {
emilmont 1:fdd22bb7aa52 88 /* C = |A| */
emilmont 1:fdd22bb7aa52 89 /* Calculate absolute and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 90 /* read sample from source */
emilmont 1:fdd22bb7aa52 91 in1 = *pSrc;
emilmont 1:fdd22bb7aa52 92 in2 = *(pSrc + 1);
emilmont 1:fdd22bb7aa52 93 in3 = *(pSrc + 2);
emilmont 1:fdd22bb7aa52 94
emilmont 1:fdd22bb7aa52 95 /* find absolute value */
emilmont 1:fdd22bb7aa52 96 in1 = fabsf(in1);
emilmont 1:fdd22bb7aa52 97
emilmont 1:fdd22bb7aa52 98 /* read sample from source */
emilmont 1:fdd22bb7aa52 99 in4 = *(pSrc + 3);
emilmont 1:fdd22bb7aa52 100
emilmont 1:fdd22bb7aa52 101 /* find absolute value */
emilmont 1:fdd22bb7aa52 102 in2 = fabsf(in2);
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* read sample from source */
emilmont 1:fdd22bb7aa52 105 *pDst = in1;
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 /* find absolute value */
emilmont 1:fdd22bb7aa52 108 in3 = fabsf(in3);
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110 /* find absolute value */
emilmont 1:fdd22bb7aa52 111 in4 = fabsf(in4);
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 /* store result to destination */
emilmont 1:fdd22bb7aa52 114 *(pDst + 1) = in2;
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 /* store result to destination */
emilmont 1:fdd22bb7aa52 117 *(pDst + 2) = in3;
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119 /* store result to destination */
emilmont 1:fdd22bb7aa52 120 *(pDst + 3) = in4;
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* Update source pointer to process next sampels */
emilmont 1:fdd22bb7aa52 124 pSrc += 4u;
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* Update destination pointer to process next sampels */
emilmont 1:fdd22bb7aa52 127 pDst += 4u;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 130 blkCnt--;
emilmont 1:fdd22bb7aa52 131 }
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 134 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 135 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 136
emilmont 1:fdd22bb7aa52 137 #else
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 142 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 147 {
emilmont 1:fdd22bb7aa52 148 /* C = |A| */
emilmont 1:fdd22bb7aa52 149 /* Calculate absolute and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 150 *pDst++ = fabsf(*pSrc++);
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 153 blkCnt--;
emilmont 1:fdd22bb7aa52 154 }
emilmont 1:fdd22bb7aa52 155 }
emilmont 1:fdd22bb7aa52 156
emilmont 1:fdd22bb7aa52 157 /**
emilmont 1:fdd22bb7aa52 158 * @} end of BasicAbs group
emilmont 1:fdd22bb7aa52 159 */