Files
@ 7527bab9ca74
Branch filter:
Location: therm/drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_cmplx_q31.c
7527bab9ca74
9.7 KiB
text/plain
Tweaks to PID word length, commenting
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 | /* ----------------------------------------------------------------------
* Copyright (C) 2010-2013 ARM Limited. All rights reserved.
*
* $Date: 17. January 2013
* $Revision: V1.4.1
*
* Project: CMSIS DSP Library
* Title: arm_cmplx_mult_cmplx_q31.c
*
* Description: Q31 complex-by-complex multiplication
*
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* - Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* - Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
* - Neither the name of ARM LIMITED nor the names of its contributors
* may be used to endorse or promote products derived from this
* software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
* -------------------------------------------------------------------- */
#include "arm_math.h"
/**
* @ingroup groupCmplxMath
*/
/**
* @addtogroup CmplxByCmplxMult
* @{
*/
/**
* @brief Q31 complex-by-complex multiplication
* @param[in] *pSrcA points to the first input vector
* @param[in] *pSrcB points to the second input vector
* @param[out] *pDst points to the output vector
* @param[in] numSamples number of complex samples in each vector
* @return none.
*
* <b>Scaling and Overflow Behavior:</b>
* \par
* The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.
* Input down scaling is not required.
*/
void arm_cmplx_mult_cmplx_q31(
q31_t * pSrcA,
q31_t * pSrcB,
q31_t * pDst,
uint32_t numSamples)
{
q31_t a, b, c, d; /* Temporary variables to store real and imaginary values */
uint32_t blkCnt; /* loop counters */
q31_t mul1, mul2, mul3, mul4;
q31_t out1, out2;
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
/* loop Unrolling */
blkCnt = numSamples >> 2u;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
/* Decrement the blockSize loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = numSamples % 0x4u;
while(blkCnt > 0u)
{
/* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
/* Decrement the blockSize loop counter */
blkCnt--;
}
#else
/* Run the below code for Cortex-M0 */
/* loop Unrolling */
blkCnt = numSamples >> 1u;
/* First part of the processing with loop unrolling. Compute 2 outputs at a time.
** a second loop below computes the remaining 1 sample. */
while(blkCnt > 0u)
{
/* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
/* Decrement the blockSize loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 2, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = numSamples % 0x2u;
while(blkCnt > 0u)
{
/* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
mul1 = (q31_t) (((q63_t) a * c) >> 32);
mul2 = (q31_t) (((q63_t) b * d) >> 32);
mul3 = (q31_t) (((q63_t) a * d) >> 32);
mul4 = (q31_t) (((q63_t) b * c) >> 32);
mul1 = (mul1 >> 1);
mul2 = (mul2 >> 1);
mul3 = (mul3 >> 1);
mul4 = (mul4 >> 1);
out1 = mul1 - mul2;
out2 = mul3 + mul4;
/* store the real result in 3.29 format in the destination buffer. */
*pDst++ = out1;
/* store the imag result in 3.29 format in the destination buffer. */
*pDst++ = out2;
/* Decrement the blockSize loop counter */
blkCnt--;
}
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
}
/**
* @} end of CmplxByCmplxMult group
*/
|