| 提交 | 用户 | age | ||
| bfc108 | 1 | /* ---------------------------------------------------------------------- |
| Q | 2 | * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
| 3 | * | |
| 4 | * $Date: 19. March 2015 | |
| 5 | * $Revision: V.1.4.5 | |
| 6 | * | |
| 7 | * Project: CMSIS DSP Library | |
| 8 | * Title: arm_scale_q31.c | |
| 9 | * | |
| 10 | * Description: Multiplies a Q31 vector by a scalar. | |
| 11 | * | |
| 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 | |
| 13 | * | |
| 14 | * Redistribution and use in source and binary forms, with or without | |
| 15 | * modification, are permitted provided that the following conditions | |
| 16 | * are met: | |
| 17 | * - Redistributions of source code must retain the above copyright | |
| 18 | * notice, this list of conditions and the following disclaimer. | |
| 19 | * - Redistributions in binary form must reproduce the above copyright | |
| 20 | * notice, this list of conditions and the following disclaimer in | |
| 21 | * the documentation and/or other materials provided with the | |
| 22 | * distribution. | |
| 23 | * - Neither the name of ARM LIMITED nor the names of its contributors | |
| 24 | * may be used to endorse or promote products derived from this | |
| 25 | * software without specific prior written permission. | |
| 26 | * | |
| 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
| 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
| 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS | |
| 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE | |
| 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, | |
| 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, | |
| 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | |
| 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER | |
| 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT | |
| 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN | |
| 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE | |
| 38 | * POSSIBILITY OF SUCH DAMAGE. | |
| 39 | * -------------------------------------------------------------------- */ | |
| 40 | ||
| 41 | #include "arm_math.h" | |
| 42 | ||
| 43 | /** | |
| 44 | * @ingroup groupMath | |
| 45 | */ | |
| 46 | ||
| 47 | /** | |
| 48 | * @addtogroup scale | |
| 49 | * @{ | |
| 50 | */ | |
| 51 | ||
| 52 | /** | |
| 53 | * @brief Multiplies a Q31 vector by a scalar. | |
| 54 | * @param[in] *pSrc points to the input vector | |
| 55 | * @param[in] scaleFract fractional portion of the scale value | |
| 56 | * @param[in] shift number of bits to shift the result by | |
| 57 | * @param[out] *pDst points to the output vector | |
| 58 | * @param[in] blockSize number of samples in the vector | |
| 59 | * @return none. | |
| 60 | * | |
| 61 | * <b>Scaling and Overflow Behavior:</b> | |
| 62 | * \par | |
| 63 | * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format. | |
| 64 | * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format. | |
| 65 | */ | |
| 66 | ||
| 67 | void arm_scale_q31( | |
| 68 | q31_t * pSrc, | |
| 69 | q31_t scaleFract, | |
| 70 | int8_t shift, | |
| 71 | q31_t * pDst, | |
| 72 | uint32_t blockSize) | |
| 73 | { | |
| 74 | int8_t kShift = shift + 1; /* Shift to apply after scaling */ | |
| 75 | int8_t sign = (kShift & 0x80); | |
| 76 | uint32_t blkCnt; /* loop counter */ | |
| 77 | q31_t in, out; | |
| 78 | ||
| 79 | #ifndef ARM_MATH_CM0_FAMILY | |
| 80 | ||
| 81 | /* Run the below code for Cortex-M4 and Cortex-M3 */ | |
| 82 | ||
| 83 | q31_t in1, in2, in3, in4; /* temporary input variables */ | |
| 84 | q31_t out1, out2, out3, out4; /* temporary output variabels */ | |
| 85 | ||
| 86 | ||
| 87 | /*loop Unrolling */ | |
| 88 | blkCnt = blockSize >> 2u; | |
| 89 | ||
| 90 | if(sign == 0u) | |
| 91 | { | |
| 92 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. | |
| 93 | ** a second loop below computes the remaining 1 to 3 samples. */ | |
| 94 | while(blkCnt > 0u) | |
| 95 | { | |
| 96 | /* read four inputs from source */ | |
| 97 | in1 = *pSrc; | |
| 98 | in2 = *(pSrc + 1); | |
| 99 | in3 = *(pSrc + 2); | |
| 100 | in4 = *(pSrc + 3); | |
| 101 | ||
| 102 | /* multiply input with scaler value */ | |
| 103 | in1 = ((q63_t) in1 * scaleFract) >> 32; | |
| 104 | in2 = ((q63_t) in2 * scaleFract) >> 32; | |
| 105 | in3 = ((q63_t) in3 * scaleFract) >> 32; | |
| 106 | in4 = ((q63_t) in4 * scaleFract) >> 32; | |
| 107 | ||
| 108 | /* apply shifting */ | |
| 109 | out1 = in1 << kShift; | |
| 110 | out2 = in2 << kShift; | |
| 111 | ||
| 112 | /* saturate the results. */ | |
| 113 | if(in1 != (out1 >> kShift)) | |
| 114 | out1 = 0x7FFFFFFF ^ (in1 >> 31); | |
| 115 | ||
| 116 | if(in2 != (out2 >> kShift)) | |
| 117 | out2 = 0x7FFFFFFF ^ (in2 >> 31); | |
| 118 | ||
| 119 | out3 = in3 << kShift; | |
| 120 | out4 = in4 << kShift; | |
| 121 | ||
| 122 | *pDst = out1; | |
| 123 | *(pDst + 1) = out2; | |
| 124 | ||
| 125 | if(in3 != (out3 >> kShift)) | |
| 126 | out3 = 0x7FFFFFFF ^ (in3 >> 31); | |
| 127 | ||
| 128 | if(in4 != (out4 >> kShift)) | |
| 129 | out4 = 0x7FFFFFFF ^ (in4 >> 31); | |
| 130 | ||
| 131 | /* Store result destination */ | |
| 132 | *(pDst + 2) = out3; | |
| 133 | *(pDst + 3) = out4; | |
| 134 | ||
| 135 | /* Update pointers to process next sampels */ | |
| 136 | pSrc += 4u; | |
| 137 | pDst += 4u; | |
| 138 | ||
| 139 | /* Decrement the loop counter */ | |
| 140 | blkCnt--; | |
| 141 | } | |
| 142 | ||
| 143 | } | |
| 144 | else | |
| 145 | { | |
| 146 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. | |
| 147 | ** a second loop below computes the remaining 1 to 3 samples. */ | |
| 148 | while(blkCnt > 0u) | |
| 149 | { | |
| 150 | /* read four inputs from source */ | |
| 151 | in1 = *pSrc; | |
| 152 | in2 = *(pSrc + 1); | |
| 153 | in3 = *(pSrc + 2); | |
| 154 | in4 = *(pSrc + 3); | |
| 155 | ||
| 156 | /* multiply input with scaler value */ | |
| 157 | in1 = ((q63_t) in1 * scaleFract) >> 32; | |
| 158 | in2 = ((q63_t) in2 * scaleFract) >> 32; | |
| 159 | in3 = ((q63_t) in3 * scaleFract) >> 32; | |
| 160 | in4 = ((q63_t) in4 * scaleFract) >> 32; | |
| 161 | ||
| 162 | /* apply shifting */ | |
| 163 | out1 = in1 >> -kShift; | |
| 164 | out2 = in2 >> -kShift; | |
| 165 | ||
| 166 | out3 = in3 >> -kShift; | |
| 167 | out4 = in4 >> -kShift; | |
| 168 | ||
| 169 | /* Store result destination */ | |
| 170 | *pDst = out1; | |
| 171 | *(pDst + 1) = out2; | |
| 172 | ||
| 173 | *(pDst + 2) = out3; | |
| 174 | *(pDst + 3) = out4; | |
| 175 | ||
| 176 | /* Update pointers to process next sampels */ | |
| 177 | pSrc += 4u; | |
| 178 | pDst += 4u; | |
| 179 | ||
| 180 | /* Decrement the loop counter */ | |
| 181 | blkCnt--; | |
| 182 | } | |
| 183 | } | |
| 184 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. | |
| 185 | ** No loop unrolling is used. */ | |
| 186 | blkCnt = blockSize % 0x4u; | |
| 187 | ||
| 188 | #else | |
| 189 | ||
| 190 | /* Run the below code for Cortex-M0 */ | |
| 191 | ||
| 192 | /* Initialize blkCnt with number of samples */ | |
| 193 | blkCnt = blockSize; | |
| 194 | ||
| 195 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ | |
| 196 | ||
| 197 | if(sign == 0) | |
| 198 | { | |
| 199 | while(blkCnt > 0u) | |
| 200 | { | |
| 201 | /* C = A * scale */ | |
| 202 | /* Scale the input and then store the result in the destination buffer. */ | |
| 203 | in = *pSrc++; | |
| 204 | in = ((q63_t) in * scaleFract) >> 32; | |
| 205 | ||
| 206 | out = in << kShift; | |
| 207 | ||
| 208 | if(in != (out >> kShift)) | |
| 209 | out = 0x7FFFFFFF ^ (in >> 31); | |
| 210 | ||
| 211 | *pDst++ = out; | |
| 212 | ||
| 213 | /* Decrement the loop counter */ | |
| 214 | blkCnt--; | |
| 215 | } | |
| 216 | } | |
| 217 | else | |
| 218 | { | |
| 219 | while(blkCnt > 0u) | |
| 220 | { | |
| 221 | /* C = A * scale */ | |
| 222 | /* Scale the input and then store the result in the destination buffer. */ | |
| 223 | in = *pSrc++; | |
| 224 | in = ((q63_t) in * scaleFract) >> 32; | |
| 225 | ||
| 226 | out = in >> -kShift; | |
| 227 | ||
| 228 | *pDst++ = out; | |
| 229 | ||
| 230 | /* Decrement the loop counter */ | |
| 231 | blkCnt--; | |
| 232 | } | |
| 233 | ||
| 234 | } | |
| 235 | } | |
| 236 | ||
| 237 | /** | |
| 238 | * @} end of scale group | |
| 239 | */ | |
