V4.0.1 of the ARM CMSIS DSP libraries. Note that arm_bitreversal2.s, arm_cfft_f32.c and arm_rfft_fast_f32.c had to be removed. arm_bitreversal2.s will not assemble with the online tools. So, the fast f32 FFT functions are not yet available. All the other FFT functions are available.
Dependents: MPU9150_Example fir_f32 fir_f32 MPU9150_nucleo_noni2cdev ... more
ComplexMathFunctions/arm_cmplx_mult_cmplx_q31.c@0:3d9c67d97d6f, 2014-07-28 (annotated)
- Committer:
- emh203
- Date:
- Mon Jul 28 15:03:15 2014 +0000
- Revision:
- 0:3d9c67d97d6f
1st working commit. Had to remove arm_bitreversal2.s arm_cfft_f32.c and arm_rfft_fast_f32.c. The .s will not assemble. For now I removed these functions so we could at least have a library for the other functions.
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
emh203 | 0:3d9c67d97d6f | 1 | /* ---------------------------------------------------------------------- |
emh203 | 0:3d9c67d97d6f | 2 | * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
emh203 | 0:3d9c67d97d6f | 3 | * |
emh203 | 0:3d9c67d97d6f | 4 | * $Date: 12. March 2014 |
emh203 | 0:3d9c67d97d6f | 5 | * $Revision: V1.4.3 |
emh203 | 0:3d9c67d97d6f | 6 | * |
emh203 | 0:3d9c67d97d6f | 7 | * Project: CMSIS DSP Library |
emh203 | 0:3d9c67d97d6f | 8 | * Title: arm_cmplx_mult_cmplx_q31.c |
emh203 | 0:3d9c67d97d6f | 9 | * |
emh203 | 0:3d9c67d97d6f | 10 | * Description: Q31 complex-by-complex multiplication |
emh203 | 0:3d9c67d97d6f | 11 | * |
emh203 | 0:3d9c67d97d6f | 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
emh203 | 0:3d9c67d97d6f | 13 | * |
emh203 | 0:3d9c67d97d6f | 14 | * Redistribution and use in source and binary forms, with or without |
emh203 | 0:3d9c67d97d6f | 15 | * modification, are permitted provided that the following conditions |
emh203 | 0:3d9c67d97d6f | 16 | * are met: |
emh203 | 0:3d9c67d97d6f | 17 | * - Redistributions of source code must retain the above copyright |
emh203 | 0:3d9c67d97d6f | 18 | * notice, this list of conditions and the following disclaimer. |
emh203 | 0:3d9c67d97d6f | 19 | * - Redistributions in binary form must reproduce the above copyright |
emh203 | 0:3d9c67d97d6f | 20 | * notice, this list of conditions and the following disclaimer in |
emh203 | 0:3d9c67d97d6f | 21 | * the documentation and/or other materials provided with the |
emh203 | 0:3d9c67d97d6f | 22 | * distribution. |
emh203 | 0:3d9c67d97d6f | 23 | * - Neither the name of ARM LIMITED nor the names of its contributors |
emh203 | 0:3d9c67d97d6f | 24 | * may be used to endorse or promote products derived from this |
emh203 | 0:3d9c67d97d6f | 25 | * software without specific prior written permission. |
emh203 | 0:3d9c67d97d6f | 26 | * |
emh203 | 0:3d9c67d97d6f | 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
emh203 | 0:3d9c67d97d6f | 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
emh203 | 0:3d9c67d97d6f | 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
emh203 | 0:3d9c67d97d6f | 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
emh203 | 0:3d9c67d97d6f | 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
emh203 | 0:3d9c67d97d6f | 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
emh203 | 0:3d9c67d97d6f | 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
emh203 | 0:3d9c67d97d6f | 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
emh203 | 0:3d9c67d97d6f | 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
emh203 | 0:3d9c67d97d6f | 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
emh203 | 0:3d9c67d97d6f | 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
emh203 | 0:3d9c67d97d6f | 38 | * POSSIBILITY OF SUCH DAMAGE. |
emh203 | 0:3d9c67d97d6f | 39 | * -------------------------------------------------------------------- */ |
emh203 | 0:3d9c67d97d6f | 40 | |
emh203 | 0:3d9c67d97d6f | 41 | #include "arm_math.h" |
emh203 | 0:3d9c67d97d6f | 42 | |
emh203 | 0:3d9c67d97d6f | 43 | /** |
emh203 | 0:3d9c67d97d6f | 44 | * @ingroup groupCmplxMath |
emh203 | 0:3d9c67d97d6f | 45 | */ |
emh203 | 0:3d9c67d97d6f | 46 | |
emh203 | 0:3d9c67d97d6f | 47 | /** |
emh203 | 0:3d9c67d97d6f | 48 | * @addtogroup CmplxByCmplxMult |
emh203 | 0:3d9c67d97d6f | 49 | * @{ |
emh203 | 0:3d9c67d97d6f | 50 | */ |
emh203 | 0:3d9c67d97d6f | 51 | |
emh203 | 0:3d9c67d97d6f | 52 | |
emh203 | 0:3d9c67d97d6f | 53 | /** |
emh203 | 0:3d9c67d97d6f | 54 | * @brief Q31 complex-by-complex multiplication |
emh203 | 0:3d9c67d97d6f | 55 | * @param[in] *pSrcA points to the first input vector |
emh203 | 0:3d9c67d97d6f | 56 | * @param[in] *pSrcB points to the second input vector |
emh203 | 0:3d9c67d97d6f | 57 | * @param[out] *pDst points to the output vector |
emh203 | 0:3d9c67d97d6f | 58 | * @param[in] numSamples number of complex samples in each vector |
emh203 | 0:3d9c67d97d6f | 59 | * @return none. |
emh203 | 0:3d9c67d97d6f | 60 | * |
emh203 | 0:3d9c67d97d6f | 61 | * <b>Scaling and Overflow Behavior:</b> |
emh203 | 0:3d9c67d97d6f | 62 | * \par |
emh203 | 0:3d9c67d97d6f | 63 | * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format. |
emh203 | 0:3d9c67d97d6f | 64 | * Input down scaling is not required. |
emh203 | 0:3d9c67d97d6f | 65 | */ |
emh203 | 0:3d9c67d97d6f | 66 | |
emh203 | 0:3d9c67d97d6f | 67 | void arm_cmplx_mult_cmplx_q31( |
emh203 | 0:3d9c67d97d6f | 68 | q31_t * pSrcA, |
emh203 | 0:3d9c67d97d6f | 69 | q31_t * pSrcB, |
emh203 | 0:3d9c67d97d6f | 70 | q31_t * pDst, |
emh203 | 0:3d9c67d97d6f | 71 | uint32_t numSamples) |
emh203 | 0:3d9c67d97d6f | 72 | { |
emh203 | 0:3d9c67d97d6f | 73 | q31_t a, b, c, d; /* Temporary variables to store real and imaginary values */ |
emh203 | 0:3d9c67d97d6f | 74 | uint32_t blkCnt; /* loop counters */ |
emh203 | 0:3d9c67d97d6f | 75 | q31_t mul1, mul2, mul3, mul4; |
emh203 | 0:3d9c67d97d6f | 76 | q31_t out1, out2; |
emh203 | 0:3d9c67d97d6f | 77 | |
emh203 | 0:3d9c67d97d6f | 78 | #ifndef ARM_MATH_CM0_FAMILY |
emh203 | 0:3d9c67d97d6f | 79 | |
emh203 | 0:3d9c67d97d6f | 80 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emh203 | 0:3d9c67d97d6f | 81 | |
emh203 | 0:3d9c67d97d6f | 82 | /* loop Unrolling */ |
emh203 | 0:3d9c67d97d6f | 83 | blkCnt = numSamples >> 2u; |
emh203 | 0:3d9c67d97d6f | 84 | |
emh203 | 0:3d9c67d97d6f | 85 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emh203 | 0:3d9c67d97d6f | 86 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emh203 | 0:3d9c67d97d6f | 87 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 88 | { |
emh203 | 0:3d9c67d97d6f | 89 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emh203 | 0:3d9c67d97d6f | 90 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emh203 | 0:3d9c67d97d6f | 91 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 92 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 93 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 94 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 95 | |
emh203 | 0:3d9c67d97d6f | 96 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 97 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 98 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 99 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 100 | |
emh203 | 0:3d9c67d97d6f | 101 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 102 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 103 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 104 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 105 | |
emh203 | 0:3d9c67d97d6f | 106 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 107 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 108 | |
emh203 | 0:3d9c67d97d6f | 109 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 110 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 111 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 112 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 113 | |
emh203 | 0:3d9c67d97d6f | 114 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 115 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 116 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 117 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 118 | |
emh203 | 0:3d9c67d97d6f | 119 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 120 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 121 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 122 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 123 | |
emh203 | 0:3d9c67d97d6f | 124 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 125 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 126 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 127 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 128 | |
emh203 | 0:3d9c67d97d6f | 129 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 130 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 131 | |
emh203 | 0:3d9c67d97d6f | 132 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 133 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 134 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 135 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 136 | |
emh203 | 0:3d9c67d97d6f | 137 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 138 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 139 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 140 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 141 | |
emh203 | 0:3d9c67d97d6f | 142 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 143 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 144 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 145 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 146 | |
emh203 | 0:3d9c67d97d6f | 147 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 148 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 149 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 150 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 151 | |
emh203 | 0:3d9c67d97d6f | 152 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 153 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 154 | |
emh203 | 0:3d9c67d97d6f | 155 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 156 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 157 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 158 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 159 | |
emh203 | 0:3d9c67d97d6f | 160 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 161 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 162 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 163 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 164 | |
emh203 | 0:3d9c67d97d6f | 165 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 166 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 167 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 168 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 169 | |
emh203 | 0:3d9c67d97d6f | 170 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 171 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 172 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 173 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 174 | |
emh203 | 0:3d9c67d97d6f | 175 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 176 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 177 | |
emh203 | 0:3d9c67d97d6f | 178 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 179 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 180 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 181 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 182 | |
emh203 | 0:3d9c67d97d6f | 183 | /* Decrement the blockSize loop counter */ |
emh203 | 0:3d9c67d97d6f | 184 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 185 | } |
emh203 | 0:3d9c67d97d6f | 186 | |
emh203 | 0:3d9c67d97d6f | 187 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emh203 | 0:3d9c67d97d6f | 188 | ** No loop unrolling is used. */ |
emh203 | 0:3d9c67d97d6f | 189 | blkCnt = numSamples % 0x4u; |
emh203 | 0:3d9c67d97d6f | 190 | |
emh203 | 0:3d9c67d97d6f | 191 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 192 | { |
emh203 | 0:3d9c67d97d6f | 193 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emh203 | 0:3d9c67d97d6f | 194 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emh203 | 0:3d9c67d97d6f | 195 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 196 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 197 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 198 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 199 | |
emh203 | 0:3d9c67d97d6f | 200 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 201 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 202 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 203 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 204 | |
emh203 | 0:3d9c67d97d6f | 205 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 206 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 207 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 208 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 209 | |
emh203 | 0:3d9c67d97d6f | 210 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 211 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 212 | |
emh203 | 0:3d9c67d97d6f | 213 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 214 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 215 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 216 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 217 | |
emh203 | 0:3d9c67d97d6f | 218 | /* Decrement the blockSize loop counter */ |
emh203 | 0:3d9c67d97d6f | 219 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 220 | } |
emh203 | 0:3d9c67d97d6f | 221 | |
emh203 | 0:3d9c67d97d6f | 222 | #else |
emh203 | 0:3d9c67d97d6f | 223 | |
emh203 | 0:3d9c67d97d6f | 224 | /* Run the below code for Cortex-M0 */ |
emh203 | 0:3d9c67d97d6f | 225 | |
emh203 | 0:3d9c67d97d6f | 226 | /* loop Unrolling */ |
emh203 | 0:3d9c67d97d6f | 227 | blkCnt = numSamples >> 1u; |
emh203 | 0:3d9c67d97d6f | 228 | |
emh203 | 0:3d9c67d97d6f | 229 | /* First part of the processing with loop unrolling. Compute 2 outputs at a time. |
emh203 | 0:3d9c67d97d6f | 230 | ** a second loop below computes the remaining 1 sample. */ |
emh203 | 0:3d9c67d97d6f | 231 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 232 | { |
emh203 | 0:3d9c67d97d6f | 233 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emh203 | 0:3d9c67d97d6f | 234 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emh203 | 0:3d9c67d97d6f | 235 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 236 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 237 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 238 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 239 | |
emh203 | 0:3d9c67d97d6f | 240 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 241 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 242 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 243 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 244 | |
emh203 | 0:3d9c67d97d6f | 245 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 246 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 247 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 248 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 249 | |
emh203 | 0:3d9c67d97d6f | 250 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 251 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 252 | |
emh203 | 0:3d9c67d97d6f | 253 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 254 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 255 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 256 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 257 | |
emh203 | 0:3d9c67d97d6f | 258 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 259 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 260 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 261 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 262 | |
emh203 | 0:3d9c67d97d6f | 263 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 264 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 265 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 266 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 267 | |
emh203 | 0:3d9c67d97d6f | 268 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 269 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 270 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 271 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 272 | |
emh203 | 0:3d9c67d97d6f | 273 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 274 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 275 | |
emh203 | 0:3d9c67d97d6f | 276 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 277 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 278 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 279 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 280 | |
emh203 | 0:3d9c67d97d6f | 281 | /* Decrement the blockSize loop counter */ |
emh203 | 0:3d9c67d97d6f | 282 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 283 | } |
emh203 | 0:3d9c67d97d6f | 284 | |
emh203 | 0:3d9c67d97d6f | 285 | /* If the blockSize is not a multiple of 2, compute any remaining output samples here. |
emh203 | 0:3d9c67d97d6f | 286 | ** No loop unrolling is used. */ |
emh203 | 0:3d9c67d97d6f | 287 | blkCnt = numSamples % 0x2u; |
emh203 | 0:3d9c67d97d6f | 288 | |
emh203 | 0:3d9c67d97d6f | 289 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 290 | { |
emh203 | 0:3d9c67d97d6f | 291 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emh203 | 0:3d9c67d97d6f | 292 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emh203 | 0:3d9c67d97d6f | 293 | a = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 294 | b = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 295 | c = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 296 | d = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 297 | |
emh203 | 0:3d9c67d97d6f | 298 | mul1 = (q31_t) (((q63_t) a * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 299 | mul2 = (q31_t) (((q63_t) b * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 300 | mul3 = (q31_t) (((q63_t) a * d) >> 32); |
emh203 | 0:3d9c67d97d6f | 301 | mul4 = (q31_t) (((q63_t) b * c) >> 32); |
emh203 | 0:3d9c67d97d6f | 302 | |
emh203 | 0:3d9c67d97d6f | 303 | mul1 = (mul1 >> 1); |
emh203 | 0:3d9c67d97d6f | 304 | mul2 = (mul2 >> 1); |
emh203 | 0:3d9c67d97d6f | 305 | mul3 = (mul3 >> 1); |
emh203 | 0:3d9c67d97d6f | 306 | mul4 = (mul4 >> 1); |
emh203 | 0:3d9c67d97d6f | 307 | |
emh203 | 0:3d9c67d97d6f | 308 | out1 = mul1 - mul2; |
emh203 | 0:3d9c67d97d6f | 309 | out2 = mul3 + mul4; |
emh203 | 0:3d9c67d97d6f | 310 | |
emh203 | 0:3d9c67d97d6f | 311 | /* store the real result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 312 | *pDst++ = out1; |
emh203 | 0:3d9c67d97d6f | 313 | /* store the imag result in 3.29 format in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 314 | *pDst++ = out2; |
emh203 | 0:3d9c67d97d6f | 315 | |
emh203 | 0:3d9c67d97d6f | 316 | /* Decrement the blockSize loop counter */ |
emh203 | 0:3d9c67d97d6f | 317 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 318 | } |
emh203 | 0:3d9c67d97d6f | 319 | |
emh203 | 0:3d9c67d97d6f | 320 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
emh203 | 0:3d9c67d97d6f | 321 | |
emh203 | 0:3d9c67d97d6f | 322 | } |
emh203 | 0:3d9c67d97d6f | 323 | |
emh203 | 0:3d9c67d97d6f | 324 | /** |
emh203 | 0:3d9c67d97d6f | 325 | * @} end of CmplxByCmplxMult group |
emh203 | 0:3d9c67d97d6f | 326 | */ |