mbed-os 6.10 versione
cmsis_dsp/BasicMathFunctions/arm_scale_q31.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?
User | Revision | Line number | New contents of line |
---|---|---|---|
mbed_official | 3:7a284390b0ce | 1 | /* ---------------------------------------------------------------------- |
mbed_official | 3:7a284390b0ce | 2 | * Copyright (C) 2010-2013 ARM Limited. All rights reserved. |
mbed_official | 3:7a284390b0ce | 3 | * |
mbed_official | 3:7a284390b0ce | 4 | * $Date: 17. January 2013 |
mbed_official | 3:7a284390b0ce | 5 | * $Revision: V1.4.1 |
mbed_official | 3:7a284390b0ce | 6 | * |
mbed_official | 3:7a284390b0ce | 7 | * Project: CMSIS DSP Library |
mbed_official | 3:7a284390b0ce | 8 | * Title: arm_scale_q31.c |
mbed_official | 3:7a284390b0ce | 9 | * |
mbed_official | 3:7a284390b0ce | 10 | * Description: Multiplies a Q31 vector by a scalar. |
mbed_official | 3:7a284390b0ce | 11 | * |
emilmont | 1:fdd22bb7aa52 | 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
mbed_official | 3:7a284390b0ce | 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. |
emilmont | 1:fdd22bb7aa52 | 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 | |
mbed_official | 3:7a284390b0ce | 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 | * @addtogroup scale |
mbed_official | 3:7a284390b0ce | 49 | * @{ |
emilmont | 1:fdd22bb7aa52 | 50 | */ |
emilmont | 1:fdd22bb7aa52 | 51 | |
mbed_official | 3:7a284390b0ce | 52 | /** |
mbed_official | 3:7a284390b0ce | 53 | * @brief Multiplies a Q31 vector by a scalar. |
mbed_official | 3:7a284390b0ce | 54 | * @param[in] *pSrc points to the input vector |
mbed_official | 3:7a284390b0ce | 55 | * @param[in] scaleFract fractional portion of the scale value |
mbed_official | 3:7a284390b0ce | 56 | * @param[in] shift number of bits to shift the result by |
mbed_official | 3:7a284390b0ce | 57 | * @param[out] *pDst points to the output vector |
mbed_official | 3:7a284390b0ce | 58 | * @param[in] blockSize number of samples in the vector |
mbed_official | 3:7a284390b0ce | 59 | * @return none. |
mbed_official | 3:7a284390b0ce | 60 | * |
mbed_official | 3:7a284390b0ce | 61 | * <b>Scaling and Overflow Behavior:</b> |
mbed_official | 3:7a284390b0ce | 62 | * \par |
mbed_official | 3:7a284390b0ce | 63 | * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format. |
mbed_official | 3:7a284390b0ce | 64 | * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format. |
emilmont | 1:fdd22bb7aa52 | 65 | */ |
emilmont | 1:fdd22bb7aa52 | 66 | |
emilmont | 1:fdd22bb7aa52 | 67 | void arm_scale_q31( |
emilmont | 1:fdd22bb7aa52 | 68 | q31_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 69 | q31_t scaleFract, |
emilmont | 1:fdd22bb7aa52 | 70 | int8_t shift, |
emilmont | 1:fdd22bb7aa52 | 71 | q31_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 72 | uint32_t blockSize) |
emilmont | 1:fdd22bb7aa52 | 73 | { |
emilmont | 1:fdd22bb7aa52 | 74 | int8_t kShift = shift + 1; /* Shift to apply after scaling */ |
emilmont | 1:fdd22bb7aa52 | 75 | int8_t sign = (kShift & 0x80); |
emilmont | 1:fdd22bb7aa52 | 76 | uint32_t blkCnt; /* loop counter */ |
emilmont | 1:fdd22bb7aa52 | 77 | q31_t in, out; |
emilmont | 1:fdd22bb7aa52 | 78 | |
mbed_official | 3:7a284390b0ce | 79 | #ifndef ARM_MATH_CM0_FAMILY |
emilmont | 1:fdd22bb7aa52 | 80 | |
emilmont | 1:fdd22bb7aa52 | 81 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 82 | |
emilmont | 1:fdd22bb7aa52 | 83 | q31_t in1, in2, in3, in4; /* temporary input variables */ |
emilmont | 1:fdd22bb7aa52 | 84 | q31_t out1, out2, out3, out4; /* temporary output variabels */ |
emilmont | 1:fdd22bb7aa52 | 85 | |
emilmont | 1:fdd22bb7aa52 | 86 | |
emilmont | 1:fdd22bb7aa52 | 87 | /*loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 88 | blkCnt = blockSize >> 2u; |
emilmont | 1:fdd22bb7aa52 | 89 | |
emilmont | 1:fdd22bb7aa52 | 90 | if(sign == 0u) |
emilmont | 1:fdd22bb7aa52 | 91 | { |
mbed_official | 3:7a284390b0ce | 92 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 93 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 94 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 95 | { |
emilmont | 1:fdd22bb7aa52 | 96 | /* read four inputs from source */ |
emilmont | 1:fdd22bb7aa52 | 97 | in1 = *pSrc; |
emilmont | 1:fdd22bb7aa52 | 98 | in2 = *(pSrc + 1); |
emilmont | 1:fdd22bb7aa52 | 99 | in3 = *(pSrc + 2); |
emilmont | 1:fdd22bb7aa52 | 100 | in4 = *(pSrc + 3); |
emilmont | 1:fdd22bb7aa52 | 101 | |
emilmont | 1:fdd22bb7aa52 | 102 | /* multiply input with scaler value */ |
emilmont | 1:fdd22bb7aa52 | 103 | in1 = ((q63_t) in1 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 104 | in2 = ((q63_t) in2 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 105 | in3 = ((q63_t) in3 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 106 | in4 = ((q63_t) in4 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 107 | |
emilmont | 1:fdd22bb7aa52 | 108 | /* apply shifting */ |
emilmont | 1:fdd22bb7aa52 | 109 | out1 = in1 << kShift; |
emilmont | 1:fdd22bb7aa52 | 110 | out2 = in2 << kShift; |
emilmont | 1:fdd22bb7aa52 | 111 | |
emilmont | 1:fdd22bb7aa52 | 112 | /* saturate the results. */ |
emilmont | 1:fdd22bb7aa52 | 113 | if(in1 != (out1 >> kShift)) |
emilmont | 1:fdd22bb7aa52 | 114 | out1 = 0x7FFFFFFF ^ (in1 >> 31); |
emilmont | 1:fdd22bb7aa52 | 115 | |
emilmont | 1:fdd22bb7aa52 | 116 | if(in2 != (out2 >> kShift)) |
emilmont | 1:fdd22bb7aa52 | 117 | out2 = 0x7FFFFFFF ^ (in2 >> 31); |
emilmont | 1:fdd22bb7aa52 | 118 | |
emilmont | 1:fdd22bb7aa52 | 119 | out3 = in3 << kShift; |
emilmont | 1:fdd22bb7aa52 | 120 | out4 = in4 << kShift; |
emilmont | 1:fdd22bb7aa52 | 121 | |
emilmont | 1:fdd22bb7aa52 | 122 | *pDst = out1; |
emilmont | 1:fdd22bb7aa52 | 123 | *(pDst + 1) = out2; |
emilmont | 1:fdd22bb7aa52 | 124 | |
emilmont | 1:fdd22bb7aa52 | 125 | if(in3 != (out3 >> kShift)) |
emilmont | 1:fdd22bb7aa52 | 126 | out3 = 0x7FFFFFFF ^ (in3 >> 31); |
emilmont | 1:fdd22bb7aa52 | 127 | |
emilmont | 1:fdd22bb7aa52 | 128 | if(in4 != (out4 >> kShift)) |
emilmont | 1:fdd22bb7aa52 | 129 | out4 = 0x7FFFFFFF ^ (in4 >> 31); |
emilmont | 1:fdd22bb7aa52 | 130 | |
emilmont | 1:fdd22bb7aa52 | 131 | /* Store result destination */ |
emilmont | 1:fdd22bb7aa52 | 132 | *(pDst + 2) = out3; |
emilmont | 1:fdd22bb7aa52 | 133 | *(pDst + 3) = out4; |
emilmont | 1:fdd22bb7aa52 | 134 | |
emilmont | 1:fdd22bb7aa52 | 135 | /* Update pointers to process next sampels */ |
emilmont | 1:fdd22bb7aa52 | 136 | pSrc += 4u; |
emilmont | 1:fdd22bb7aa52 | 137 | pDst += 4u; |
emilmont | 1:fdd22bb7aa52 | 138 | |
emilmont | 1:fdd22bb7aa52 | 139 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 140 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 141 | } |
emilmont | 1:fdd22bb7aa52 | 142 | |
emilmont | 1:fdd22bb7aa52 | 143 | } |
emilmont | 1:fdd22bb7aa52 | 144 | else |
emilmont | 1:fdd22bb7aa52 | 145 | { |
mbed_official | 3:7a284390b0ce | 146 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 147 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 148 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 149 | { |
emilmont | 1:fdd22bb7aa52 | 150 | /* read four inputs from source */ |
emilmont | 1:fdd22bb7aa52 | 151 | in1 = *pSrc; |
emilmont | 1:fdd22bb7aa52 | 152 | in2 = *(pSrc + 1); |
emilmont | 1:fdd22bb7aa52 | 153 | in3 = *(pSrc + 2); |
emilmont | 1:fdd22bb7aa52 | 154 | in4 = *(pSrc + 3); |
emilmont | 1:fdd22bb7aa52 | 155 | |
emilmont | 1:fdd22bb7aa52 | 156 | /* multiply input with scaler value */ |
emilmont | 1:fdd22bb7aa52 | 157 | in1 = ((q63_t) in1 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 158 | in2 = ((q63_t) in2 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 159 | in3 = ((q63_t) in3 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 160 | in4 = ((q63_t) in4 * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 161 | |
emilmont | 1:fdd22bb7aa52 | 162 | /* apply shifting */ |
mbed_official | 3:7a284390b0ce | 163 | out1 = in1 >> -kShift; |
mbed_official | 3:7a284390b0ce | 164 | out2 = in2 >> -kShift; |
emilmont | 1:fdd22bb7aa52 | 165 | |
mbed_official | 3:7a284390b0ce | 166 | out3 = in3 >> -kShift; |
mbed_official | 3:7a284390b0ce | 167 | out4 = in4 >> -kShift; |
emilmont | 1:fdd22bb7aa52 | 168 | |
emilmont | 1:fdd22bb7aa52 | 169 | /* Store result destination */ |
emilmont | 1:fdd22bb7aa52 | 170 | *pDst = out1; |
emilmont | 1:fdd22bb7aa52 | 171 | *(pDst + 1) = out2; |
emilmont | 1:fdd22bb7aa52 | 172 | |
emilmont | 1:fdd22bb7aa52 | 173 | *(pDst + 2) = out3; |
emilmont | 1:fdd22bb7aa52 | 174 | *(pDst + 3) = out4; |
emilmont | 1:fdd22bb7aa52 | 175 | |
emilmont | 1:fdd22bb7aa52 | 176 | /* Update pointers to process next sampels */ |
emilmont | 1:fdd22bb7aa52 | 177 | pSrc += 4u; |
emilmont | 1:fdd22bb7aa52 | 178 | pDst += 4u; |
emilmont | 1:fdd22bb7aa52 | 179 | |
emilmont | 1:fdd22bb7aa52 | 180 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 181 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 182 | } |
emilmont | 1:fdd22bb7aa52 | 183 | } |
mbed_official | 3:7a284390b0ce | 184 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 185 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 186 | blkCnt = blockSize % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 187 | |
emilmont | 1:fdd22bb7aa52 | 188 | #else |
emilmont | 1:fdd22bb7aa52 | 189 | |
emilmont | 1:fdd22bb7aa52 | 190 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 191 | |
emilmont | 1:fdd22bb7aa52 | 192 | /* Initialize blkCnt with number of samples */ |
emilmont | 1:fdd22bb7aa52 | 193 | blkCnt = blockSize; |
emilmont | 1:fdd22bb7aa52 | 194 | |
mbed_official | 3:7a284390b0ce | 195 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
emilmont | 1:fdd22bb7aa52 | 196 | |
mbed_official | 3:7a284390b0ce | 197 | if(sign == 0) |
emilmont | 1:fdd22bb7aa52 | 198 | { |
mbed_official | 3:7a284390b0ce | 199 | while(blkCnt > 0u) |
mbed_official | 3:7a284390b0ce | 200 | { |
mbed_official | 3:7a284390b0ce | 201 | /* C = A * scale */ |
mbed_official | 3:7a284390b0ce | 202 | /* Scale the input and then store the result in the destination buffer. */ |
mbed_official | 3:7a284390b0ce | 203 | in = *pSrc++; |
mbed_official | 3:7a284390b0ce | 204 | in = ((q63_t) in * scaleFract) >> 32; |
mbed_official | 3:7a284390b0ce | 205 | |
mbed_official | 3:7a284390b0ce | 206 | out = in << kShift; |
mbed_official | 3:7a284390b0ce | 207 | |
mbed_official | 3:7a284390b0ce | 208 | if(in != (out >> kShift)) |
mbed_official | 3:7a284390b0ce | 209 | out = 0x7FFFFFFF ^ (in >> 31); |
mbed_official | 3:7a284390b0ce | 210 | |
mbed_official | 3:7a284390b0ce | 211 | *pDst++ = out; |
emilmont | 1:fdd22bb7aa52 | 212 | |
mbed_official | 3:7a284390b0ce | 213 | /* Decrement the loop counter */ |
mbed_official | 3:7a284390b0ce | 214 | blkCnt--; |
mbed_official | 3:7a284390b0ce | 215 | } |
mbed_official | 3:7a284390b0ce | 216 | } |
mbed_official | 3:7a284390b0ce | 217 | else |
mbed_official | 3:7a284390b0ce | 218 | { |
mbed_official | 3:7a284390b0ce | 219 | while(blkCnt > 0u) |
mbed_official | 3:7a284390b0ce | 220 | { |
mbed_official | 3:7a284390b0ce | 221 | /* C = A * scale */ |
mbed_official | 3:7a284390b0ce | 222 | /* Scale the input and then store the result in the destination buffer. */ |
mbed_official | 3:7a284390b0ce | 223 | in = *pSrc++; |
mbed_official | 3:7a284390b0ce | 224 | in = ((q63_t) in * scaleFract) >> 32; |
emilmont | 1:fdd22bb7aa52 | 225 | |
mbed_official | 3:7a284390b0ce | 226 | out = in >> -kShift; |
mbed_official | 3:7a284390b0ce | 227 | |
mbed_official | 3:7a284390b0ce | 228 | *pDst++ = out; |
emilmont | 1:fdd22bb7aa52 | 229 | |
mbed_official | 3:7a284390b0ce | 230 | /* Decrement the loop counter */ |
mbed_official | 3:7a284390b0ce | 231 | blkCnt--; |
mbed_official | 3:7a284390b0ce | 232 | } |
mbed_official | 3:7a284390b0ce | 233 | |
emilmont | 1:fdd22bb7aa52 | 234 | } |
emilmont | 1:fdd22bb7aa52 | 235 | } |
emilmont | 1:fdd22bb7aa52 | 236 | |
mbed_official | 3:7a284390b0ce | 237 | /** |
mbed_official | 3:7a284390b0ce | 238 | * @} end of scale group |
emilmont | 1:fdd22bb7aa52 | 239 | */ |