mbed official / mbed-dsp

CMSIS DSP library

Dependents:   performance_timer Surfboard_ gps2rtty Capstone ... more

Legacy Warning

This is an mbed 2 library. To learn more about mbed OS 5, visit the docs.

cmsis_dsp/ComplexMathFunctions/arm_cmplx_mult_cmplx_q31.c@5:3762170b6d4d, 2015-11-20 (annotated)

Committer:
mbed_official
Date:
Fri Nov 20 08:45:18 2015 +0000
Revision:
5:3762170b6d4d
Parent:
3:7a284390b0ce 
Synchronized with git revision 2eb940b9a73af188d3004a2575fdfbb05febe62b



Full URL: https://github.com/mbedmicro/mbed/commit/2eb940b9a73af188d3004a2575fdfbb05febe62b/



Added option to build rpc library. closes #1426

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
mbed_official 5:3762170b6d4d 2 * Copyright (C) 2010-2014 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 5:3762170b6d4d 4 * $Date: 19. March 2015
mbed_official 5:3762170b6d4d 5 * $Revision: V.1.4.5
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_cmplx_mult_cmplx_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q31 complex-by-complex multiplication
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 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.
mbed_official 3:7a284390b0ce 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
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @ingroup groupCmplxMath
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @addtogroup CmplxByCmplxMult
emilmont 1:fdd22bb7aa52 49 * @{
emilmont 1:fdd22bb7aa52 50 */
emilmont 1:fdd22bb7aa52 51
emilmont 1:fdd22bb7aa52 52
emilmont 1:fdd22bb7aa52 53 /**
emilmont 1:fdd22bb7aa52 54 * @brief Q31 complex-by-complex multiplication
emilmont 1:fdd22bb7aa52 55 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 56 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 57 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 58 * @param[in] numSamples number of complex samples in each vector
emilmont 1:fdd22bb7aa52 59 * @return none.
emilmont 1:fdd22bb7aa52 60 *
emilmont 1:fdd22bb7aa52 61 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 62 * \par
emilmont 1:fdd22bb7aa52 63 * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.
emilmont 1:fdd22bb7aa52 64 * Input down scaling is not required.
emilmont 1:fdd22bb7aa52 65 */
emilmont 1:fdd22bb7aa52 66
emilmont 1:fdd22bb7aa52 67 void arm_cmplx_mult_cmplx_q31(
emilmont 1:fdd22bb7aa52 68 q31_t * pSrcA,
emilmont 1:fdd22bb7aa52 69 q31_t * pSrcB,
emilmont 1:fdd22bb7aa52 70 q31_t * pDst,
emilmont 1:fdd22bb7aa52 71 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 72 {
emilmont 1:fdd22bb7aa52 73 q31_t a, b, c, d; /* Temporary variables to store real and imaginary values */
emilmont 1:fdd22bb7aa52 74 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 75 q31_t mul1, mul2, mul3, mul4;
emilmont 1:fdd22bb7aa52 76 q31_t out1, out2;
emilmont 1:fdd22bb7aa52 77
mbed_official 3:7a284390b0ce 78 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 83 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 86 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 87 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 88 {
emilmont 1:fdd22bb7aa52 89 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
emilmont 1:fdd22bb7aa52 90 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
emilmont 1:fdd22bb7aa52 91 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 92 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 93 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 94 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 95
emilmont 1:fdd22bb7aa52 96 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 97 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 98 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 99 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 100
emilmont 1:fdd22bb7aa52 101 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 102 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 103 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 104 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 107 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 110 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 111 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 112 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 115 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 116 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 117 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 120 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 121 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 122 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 123
emilmont 1:fdd22bb7aa52 124 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 125 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 126 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 127 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 130 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 133 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 134 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 135 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 136
emilmont 1:fdd22bb7aa52 137 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 138 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 139 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 140 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 143 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 144 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 145 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 148 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 149 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 150 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 153 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 156 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 157 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 158 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 159
emilmont 1:fdd22bb7aa52 160 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 161 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 162 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 163 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 166 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 167 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 168 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 171 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 172 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 173 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 174
emilmont 1:fdd22bb7aa52 175 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 176 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 179 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 180 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 181 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 182
emilmont 1:fdd22bb7aa52 183 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 184 blkCnt--;
emilmont 1:fdd22bb7aa52 185 }
emilmont 1:fdd22bb7aa52 186
emilmont 1:fdd22bb7aa52 187 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 188 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 189 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 190
emilmont 1:fdd22bb7aa52 191 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 192 {
emilmont 1:fdd22bb7aa52 193 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
emilmont 1:fdd22bb7aa52 194 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
emilmont 1:fdd22bb7aa52 195 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 196 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 197 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 198 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 199
emilmont 1:fdd22bb7aa52 200 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 201 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 202 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 203 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 204
emilmont 1:fdd22bb7aa52 205 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 206 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 207 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 208 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 209
emilmont 1:fdd22bb7aa52 210 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 211 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 212
emilmont 1:fdd22bb7aa52 213 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 214 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 215 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 216 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 217
emilmont 1:fdd22bb7aa52 218 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 219 blkCnt--;
emilmont 1:fdd22bb7aa52 220 }
emilmont 1:fdd22bb7aa52 221
emilmont 1:fdd22bb7aa52 222 #else
emilmont 1:fdd22bb7aa52 223
emilmont 1:fdd22bb7aa52 224 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 225
emilmont 1:fdd22bb7aa52 226 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 227 blkCnt = numSamples >> 1u;
emilmont 1:fdd22bb7aa52 228
emilmont 1:fdd22bb7aa52 229 /* First part of the processing with loop unrolling. Compute 2 outputs at a time.
emilmont 1:fdd22bb7aa52 230 ** a second loop below computes the remaining 1 sample. */
emilmont 1:fdd22bb7aa52 231 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 232 {
emilmont 1:fdd22bb7aa52 233 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
emilmont 1:fdd22bb7aa52 234 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
emilmont 1:fdd22bb7aa52 235 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 236 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 237 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 238 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 239
emilmont 1:fdd22bb7aa52 240 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 241 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 242 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 243 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 244
emilmont 1:fdd22bb7aa52 245 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 246 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 247 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 248 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 249
emilmont 1:fdd22bb7aa52 250 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 251 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 252
emilmont 1:fdd22bb7aa52 253 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 254 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 255 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 256 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 257
emilmont 1:fdd22bb7aa52 258 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 259 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 260 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 261 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 262
emilmont 1:fdd22bb7aa52 263 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 264 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 265 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 266 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 267
emilmont 1:fdd22bb7aa52 268 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 269 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 270 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 271 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 272
emilmont 1:fdd22bb7aa52 273 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 274 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 275
emilmont 1:fdd22bb7aa52 276 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 277 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 278 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 279 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 280
emilmont 1:fdd22bb7aa52 281 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 282 blkCnt--;
emilmont 1:fdd22bb7aa52 283 }
emilmont 1:fdd22bb7aa52 284
emilmont 1:fdd22bb7aa52 285 /* If the blockSize is not a multiple of 2, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 286 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 287 blkCnt = numSamples % 0x2u;
emilmont 1:fdd22bb7aa52 288
emilmont 1:fdd22bb7aa52 289 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 290 {
emilmont 1:fdd22bb7aa52 291 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
emilmont 1:fdd22bb7aa52 292 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
emilmont 1:fdd22bb7aa52 293 a = *pSrcA++;
emilmont 1:fdd22bb7aa52 294 b = *pSrcA++;
emilmont 1:fdd22bb7aa52 295 c = *pSrcB++;
emilmont 1:fdd22bb7aa52 296 d = *pSrcB++;
emilmont 1:fdd22bb7aa52 297
emilmont 1:fdd22bb7aa52 298 mul1 = (q31_t) (((q63_t) a * c) >> 32);
emilmont 1:fdd22bb7aa52 299 mul2 = (q31_t) (((q63_t) b * d) >> 32);
emilmont 1:fdd22bb7aa52 300 mul3 = (q31_t) (((q63_t) a * d) >> 32);
emilmont 1:fdd22bb7aa52 301 mul4 = (q31_t) (((q63_t) b * c) >> 32);
emilmont 1:fdd22bb7aa52 302
emilmont 1:fdd22bb7aa52 303 mul1 = (mul1 >> 1);
emilmont 1:fdd22bb7aa52 304 mul2 = (mul2 >> 1);
emilmont 1:fdd22bb7aa52 305 mul3 = (mul3 >> 1);
emilmont 1:fdd22bb7aa52 306 mul4 = (mul4 >> 1);
emilmont 1:fdd22bb7aa52 307
emilmont 1:fdd22bb7aa52 308 out1 = mul1 - mul2;
emilmont 1:fdd22bb7aa52 309 out2 = mul3 + mul4;
emilmont 1:fdd22bb7aa52 310
emilmont 1:fdd22bb7aa52 311 /* store the real result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 312 *pDst++ = out1;
emilmont 1:fdd22bb7aa52 313 /* store the imag result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 314 *pDst++ = out2;
emilmont 1:fdd22bb7aa52 315
emilmont 1:fdd22bb7aa52 316 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 317 blkCnt--;
emilmont 1:fdd22bb7aa52 318 }
emilmont 1:fdd22bb7aa52 319
mbed_official 3:7a284390b0ce 320 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 321
emilmont 1:fdd22bb7aa52 322 }
emilmont 1:fdd22bb7aa52 323
emilmont 1:fdd22bb7aa52 324 /**
emilmont 1:fdd22bb7aa52 325 * @} end of CmplxByCmplxMult group
emilmont 1:fdd22bb7aa52 326 */