Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_scale_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_scale_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Multiplies a floating-point vector by a scalar.
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 scale Vector Scale
emilmont 1:fdd22bb7aa52 44 *
emilmont 1:fdd22bb7aa52 45 * Multiply a vector by a scalar value. For floating-point data, the algorithm used is:
emilmont 1:fdd22bb7aa52 46 *
emilmont 1:fdd22bb7aa52 47 * <pre>
emilmont 1:fdd22bb7aa52 48 * pDst[n] = pSrc[n] * scale, 0 <= n < blockSize.
emilmont 1:fdd22bb7aa52 49 * </pre>
emilmont 1:fdd22bb7aa52 50 *
emilmont 1:fdd22bb7aa52 51 * In the fixed-point Q7, Q15, and Q31 functions, <code>scale</code> is represented by
emilmont 1:fdd22bb7aa52 52 * a fractional multiplication <code>scaleFract</code> and an arithmetic shift <code>shift</code>.
emilmont 1:fdd22bb7aa52 53 * The shift allows the gain of the scaling operation to exceed 1.0.
emilmont 1:fdd22bb7aa52 54 * The algorithm used with fixed-point data is:
emilmont 1:fdd22bb7aa52 55 *
emilmont 1:fdd22bb7aa52 56 * <pre>
emilmont 1:fdd22bb7aa52 57 * pDst[n] = (pSrc[n] * scaleFract) << shift, 0 <= n < blockSize.
emilmont 1:fdd22bb7aa52 58 * </pre>
emilmont 1:fdd22bb7aa52 59 *
emilmont 1:fdd22bb7aa52 60 * The overall scale factor applied to the fixed-point data is
emilmont 1:fdd22bb7aa52 61 * <pre>
emilmont 1:fdd22bb7aa52 62 * scale = scaleFract * 2^shift.
emilmont 1:fdd22bb7aa52 63 * </pre>
emilmont 1:fdd22bb7aa52 64 */
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66 /**
emilmont 1:fdd22bb7aa52 67 * @addtogroup scale
emilmont 1:fdd22bb7aa52 68 * @{
emilmont 1:fdd22bb7aa52 69 */
emilmont 1:fdd22bb7aa52 70
emilmont 1:fdd22bb7aa52 71 /**
emilmont 1:fdd22bb7aa52 72 * @brief Multiplies a floating-point vector by a scalar.
emilmont 1:fdd22bb7aa52 73 * @param[in] *pSrc points to the input vector
emilmont 1:fdd22bb7aa52 74 * @param[in] scale scale factor to be applied
emilmont 1:fdd22bb7aa52 75 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 76 * @param[in] blockSize number of samples in the vector
emilmont 1:fdd22bb7aa52 77 * @return none.
emilmont 1:fdd22bb7aa52 78 */
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 void arm_scale_f32(
emilmont 1:fdd22bb7aa52 82 float32_t * pSrc,
emilmont 1:fdd22bb7aa52 83 float32_t scale,
emilmont 1:fdd22bb7aa52 84 float32_t * pDst,
emilmont 1:fdd22bb7aa52 85 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 86 {
emilmont 1:fdd22bb7aa52 87 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 88 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 89
emilmont 1:fdd22bb7aa52 90 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 91 float32_t in1, in2, in3, in4; /* temporary variabels */
emilmont 1:fdd22bb7aa52 92
emilmont 1:fdd22bb7aa52 93 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 94 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 95
emilmont 1:fdd22bb7aa52 96 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 97 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 98 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 99 {
emilmont 1:fdd22bb7aa52 100 /* C = A * scale */
emilmont 1:fdd22bb7aa52 101 /* Scale the input and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 102 /* read input samples from source */
emilmont 1:fdd22bb7aa52 103 in1 = *pSrc;
emilmont 1:fdd22bb7aa52 104 in2 = *(pSrc + 1);
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* multiply with scaling factor */
emilmont 1:fdd22bb7aa52 107 in1 = in1 * scale;
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 /* read input sample from source */
emilmont 1:fdd22bb7aa52 110 in3 = *(pSrc + 2);
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* multiply with scaling factor */
emilmont 1:fdd22bb7aa52 113 in2 = in2 * scale;
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* read input sample from source */
emilmont 1:fdd22bb7aa52 116 in4 = *(pSrc + 3);
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* multiply with scaling factor */
emilmont 1:fdd22bb7aa52 119 in3 = in3 * scale;
emilmont 1:fdd22bb7aa52 120 in4 = in4 * scale;
emilmont 1:fdd22bb7aa52 121 /* store the result to destination */
emilmont 1:fdd22bb7aa52 122 *pDst = in1;
emilmont 1:fdd22bb7aa52 123 *(pDst + 1) = in2;
emilmont 1:fdd22bb7aa52 124 *(pDst + 2) = in3;
emilmont 1:fdd22bb7aa52 125 *(pDst + 3) = in4;
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 /* update pointers to process next samples */
emilmont 1:fdd22bb7aa52 128 pSrc += 4u;
emilmont 1:fdd22bb7aa52 129 pDst += 4u;
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 132 blkCnt--;
emilmont 1:fdd22bb7aa52 133 }
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 136 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 137 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 #else
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 144 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 149 {
emilmont 1:fdd22bb7aa52 150 /* C = A * scale */
emilmont 1:fdd22bb7aa52 151 /* Scale the input and then store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 152 *pDst++ = (*pSrc++) * scale;
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 155 blkCnt--;
emilmont 1:fdd22bb7aa52 156 }
emilmont 1:fdd22bb7aa52 157 }
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 /**
emilmont 1:fdd22bb7aa52 160 * @} end of scale group
emilmont 1:fdd22bb7aa52 161 */