Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_scale_q31.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. May 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_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Multiplies a Q31 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 * @addtogroup scale
emilmont 1:fdd22bb7aa52 44 * @{
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @brief Multiplies a Q31 vector by a scalar.
emilmont 1:fdd22bb7aa52 49 * @param[in] *pSrc points to the input vector
emilmont 1:fdd22bb7aa52 50 * @param[in] scaleFract fractional portion of the scale value
emilmont 1:fdd22bb7aa52 51 * @param[in] shift number of bits to shift the result by
emilmont 1:fdd22bb7aa52 52 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 53 * @param[in] blockSize number of samples in the vector
emilmont 1:fdd22bb7aa52 54 * @return none.
emilmont 1:fdd22bb7aa52 55 *
emilmont 1:fdd22bb7aa52 56 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 57 * \par
emilmont 1:fdd22bb7aa52 58 * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.
emilmont 1:fdd22bb7aa52 59 * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.
emilmont 1:fdd22bb7aa52 60 */
emilmont 1:fdd22bb7aa52 61
emilmont 1:fdd22bb7aa52 62 void arm_scale_q31(
emilmont 1:fdd22bb7aa52 63 q31_t * pSrc,
emilmont 1:fdd22bb7aa52 64 q31_t scaleFract,
emilmont 1:fdd22bb7aa52 65 int8_t shift,
emilmont 1:fdd22bb7aa52 66 q31_t * pDst,
emilmont 1:fdd22bb7aa52 67 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 68 {
emilmont 1:fdd22bb7aa52 69 int8_t kShift = shift + 1; /* Shift to apply after scaling */
emilmont 1:fdd22bb7aa52 70 int8_t sign = (kShift & 0x80);
emilmont 1:fdd22bb7aa52 71 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 72 q31_t in, out;
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 75
emilmont 1:fdd22bb7aa52 76 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 q31_t in1, in2, in3, in4; /* temporary input variables */
emilmont 1:fdd22bb7aa52 79 q31_t out1, out2, out3, out4; /* temporary output variabels */
emilmont 1:fdd22bb7aa52 80
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 if(sign == 0u)
emilmont 1:fdd22bb7aa52 86 {
emilmont 1:fdd22bb7aa52 87 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 88 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 89 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 90 {
emilmont 1:fdd22bb7aa52 91 /* read four inputs from source */
emilmont 1:fdd22bb7aa52 92 in1 = *pSrc;
emilmont 1:fdd22bb7aa52 93 in2 = *(pSrc + 1);
emilmont 1:fdd22bb7aa52 94 in3 = *(pSrc + 2);
emilmont 1:fdd22bb7aa52 95 in4 = *(pSrc + 3);
emilmont 1:fdd22bb7aa52 96
emilmont 1:fdd22bb7aa52 97 /* multiply input with scaler value */
emilmont 1:fdd22bb7aa52 98 in1 = ((q63_t) in1 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 99 in2 = ((q63_t) in2 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 100 in3 = ((q63_t) in3 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 101 in4 = ((q63_t) in4 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 /* apply shifting */
emilmont 1:fdd22bb7aa52 104 out1 = in1 << kShift;
emilmont 1:fdd22bb7aa52 105 out2 = in2 << kShift;
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 /* saturate the results. */
emilmont 1:fdd22bb7aa52 108 if(in1 != (out1 >> kShift))
emilmont 1:fdd22bb7aa52 109 out1 = 0x7FFFFFFF ^ (in1 >> 31);
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 if(in2 != (out2 >> kShift))
emilmont 1:fdd22bb7aa52 112 out2 = 0x7FFFFFFF ^ (in2 >> 31);
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 out3 = in3 << kShift;
emilmont 1:fdd22bb7aa52 115 out4 = in4 << kShift;
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 *pDst = out1;
emilmont 1:fdd22bb7aa52 118 *(pDst + 1) = out2;
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 if(in3 != (out3 >> kShift))
emilmont 1:fdd22bb7aa52 121 out3 = 0x7FFFFFFF ^ (in3 >> 31);
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 if(in4 != (out4 >> kShift))
emilmont 1:fdd22bb7aa52 124 out4 = 0x7FFFFFFF ^ (in4 >> 31);
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* Store result destination */
emilmont 1:fdd22bb7aa52 127 *(pDst + 2) = out3;
emilmont 1:fdd22bb7aa52 128 *(pDst + 3) = out4;
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130 /* Update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 131 pSrc += 4u;
emilmont 1:fdd22bb7aa52 132 pDst += 4u;
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 135 blkCnt--;
emilmont 1:fdd22bb7aa52 136 }
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 }
emilmont 1:fdd22bb7aa52 139 else
emilmont 1:fdd22bb7aa52 140 {
emilmont 1:fdd22bb7aa52 141 kShift = -kShift;
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 144 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 145 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 146 {
emilmont 1:fdd22bb7aa52 147 /* read four inputs from source */
emilmont 1:fdd22bb7aa52 148 in1 = *pSrc;
emilmont 1:fdd22bb7aa52 149 in2 = *(pSrc + 1);
emilmont 1:fdd22bb7aa52 150 in3 = *(pSrc + 2);
emilmont 1:fdd22bb7aa52 151 in4 = *(pSrc + 3);
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 /* multiply input with scaler value */
emilmont 1:fdd22bb7aa52 154 in1 = ((q63_t) in1 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 155 in2 = ((q63_t) in2 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 156 in3 = ((q63_t) in3 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 157 in4 = ((q63_t) in4 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 /* apply shifting */
emilmont 1:fdd22bb7aa52 160 out1 = in1 >> kShift;
emilmont 1:fdd22bb7aa52 161 out2 = in2 >> kShift;
emilmont 1:fdd22bb7aa52 162
emilmont 1:fdd22bb7aa52 163 out3 = in3 >> kShift;
emilmont 1:fdd22bb7aa52 164 out4 = in4 >> kShift;
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 /* Store result destination */
emilmont 1:fdd22bb7aa52 167 *pDst = out1;
emilmont 1:fdd22bb7aa52 168 *(pDst + 1) = out2;
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 *(pDst + 2) = out3;
emilmont 1:fdd22bb7aa52 171 *(pDst + 3) = out4;
emilmont 1:fdd22bb7aa52 172
emilmont 1:fdd22bb7aa52 173 /* Update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 174 pSrc += 4u;
emilmont 1:fdd22bb7aa52 175 pDst += 4u;
emilmont 1:fdd22bb7aa52 176
emilmont 1:fdd22bb7aa52 177 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 178 blkCnt--;
emilmont 1:fdd22bb7aa52 179 }
emilmont 1:fdd22bb7aa52 180 }
emilmont 1:fdd22bb7aa52 181 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 182 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 183 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 184
emilmont 1:fdd22bb7aa52 185 #else
emilmont 1:fdd22bb7aa52 186
emilmont 1:fdd22bb7aa52 187 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 188 if(sign != 0u)
emilmont 1:fdd22bb7aa52 189 kShift = -kShift;
emilmont 1:fdd22bb7aa52 190
emilmont 1:fdd22bb7aa52 191 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 192 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 193
emilmont 1:fdd22bb7aa52 194 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 195
emilmont 1:fdd22bb7aa52 196 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 197 {
emilmont 1:fdd22bb7aa52 198 /* C = A * scale */
emilmont 1:fdd22bb7aa52 199 /* Scale the input and then store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 200 in = *pSrc++;
emilmont 1:fdd22bb7aa52 201 in = ((q63_t) in * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 202
emilmont 1:fdd22bb7aa52 203 if(sign == 0)
emilmont 1:fdd22bb7aa52 204 {
emilmont 1:fdd22bb7aa52 205 out = in << kShift;
emilmont 1:fdd22bb7aa52 206 if(in != (out >> kShift))
emilmont 1:fdd22bb7aa52 207 out = 0x7FFFFFFF ^ (in >> 31);
emilmont 1:fdd22bb7aa52 208 }
emilmont 1:fdd22bb7aa52 209 else
emilmont 1:fdd22bb7aa52 210 {
emilmont 1:fdd22bb7aa52 211 out = in >> kShift;
emilmont 1:fdd22bb7aa52 212 }
emilmont 1:fdd22bb7aa52 213
emilmont 1:fdd22bb7aa52 214 *pDst++ = out;
emilmont 1:fdd22bb7aa52 215
emilmont 1:fdd22bb7aa52 216 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 217 blkCnt--;
emilmont 1:fdd22bb7aa52 218 }
emilmont 1:fdd22bb7aa52 219 }
emilmont 1:fdd22bb7aa52 220
emilmont 1:fdd22bb7aa52 221 /**
emilmont 1:fdd22bb7aa52 222 * @} end of scale group
emilmont 1:fdd22bb7aa52 223 */