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_f32.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_f32.c |
emh203 | 0:3d9c67d97d6f | 9 | * |
emh203 | 0:3d9c67d97d6f | 10 | * Description: Floating-point 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 | #include "arm_math.h" |
emh203 | 0:3d9c67d97d6f | 41 | |
emh203 | 0:3d9c67d97d6f | 42 | /** |
emh203 | 0:3d9c67d97d6f | 43 | * @ingroup groupCmplxMath |
emh203 | 0:3d9c67d97d6f | 44 | */ |
emh203 | 0:3d9c67d97d6f | 45 | |
emh203 | 0:3d9c67d97d6f | 46 | /** |
emh203 | 0:3d9c67d97d6f | 47 | * @defgroup CmplxByCmplxMult Complex-by-Complex Multiplication |
emh203 | 0:3d9c67d97d6f | 48 | * |
emh203 | 0:3d9c67d97d6f | 49 | * Multiplies a complex vector by another complex vector and generates a complex result. |
emh203 | 0:3d9c67d97d6f | 50 | * The data in the complex arrays is stored in an interleaved fashion |
emh203 | 0:3d9c67d97d6f | 51 | * (real, imag, real, imag, ...). |
emh203 | 0:3d9c67d97d6f | 52 | * The parameter <code>numSamples</code> represents the number of complex |
emh203 | 0:3d9c67d97d6f | 53 | * samples processed. The complex arrays have a total of <code>2*numSamples</code> |
emh203 | 0:3d9c67d97d6f | 54 | * real values. |
emh203 | 0:3d9c67d97d6f | 55 | * |
emh203 | 0:3d9c67d97d6f | 56 | * The underlying algorithm is used: |
emh203 | 0:3d9c67d97d6f | 57 | * |
emh203 | 0:3d9c67d97d6f | 58 | * <pre> |
emh203 | 0:3d9c67d97d6f | 59 | * for(n=0; n<numSamples; n++) { |
emh203 | 0:3d9c67d97d6f | 60 | * pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1]; |
emh203 | 0:3d9c67d97d6f | 61 | * pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0]; |
emh203 | 0:3d9c67d97d6f | 62 | * } |
emh203 | 0:3d9c67d97d6f | 63 | * </pre> |
emh203 | 0:3d9c67d97d6f | 64 | * |
emh203 | 0:3d9c67d97d6f | 65 | * There are separate functions for floating-point, Q15, and Q31 data types. |
emh203 | 0:3d9c67d97d6f | 66 | */ |
emh203 | 0:3d9c67d97d6f | 67 | |
emh203 | 0:3d9c67d97d6f | 68 | /** |
emh203 | 0:3d9c67d97d6f | 69 | * @addtogroup CmplxByCmplxMult |
emh203 | 0:3d9c67d97d6f | 70 | * @{ |
emh203 | 0:3d9c67d97d6f | 71 | */ |
emh203 | 0:3d9c67d97d6f | 72 | |
emh203 | 0:3d9c67d97d6f | 73 | |
emh203 | 0:3d9c67d97d6f | 74 | /** |
emh203 | 0:3d9c67d97d6f | 75 | * @brief Floating-point complex-by-complex multiplication |
emh203 | 0:3d9c67d97d6f | 76 | * @param[in] *pSrcA points to the first input vector |
emh203 | 0:3d9c67d97d6f | 77 | * @param[in] *pSrcB points to the second input vector |
emh203 | 0:3d9c67d97d6f | 78 | * @param[out] *pDst points to the output vector |
emh203 | 0:3d9c67d97d6f | 79 | * @param[in] numSamples number of complex samples in each vector |
emh203 | 0:3d9c67d97d6f | 80 | * @return none. |
emh203 | 0:3d9c67d97d6f | 81 | */ |
emh203 | 0:3d9c67d97d6f | 82 | |
emh203 | 0:3d9c67d97d6f | 83 | void arm_cmplx_mult_cmplx_f32( |
emh203 | 0:3d9c67d97d6f | 84 | float32_t * pSrcA, |
emh203 | 0:3d9c67d97d6f | 85 | float32_t * pSrcB, |
emh203 | 0:3d9c67d97d6f | 86 | float32_t * pDst, |
emh203 | 0:3d9c67d97d6f | 87 | uint32_t numSamples) |
emh203 | 0:3d9c67d97d6f | 88 | { |
emh203 | 0:3d9c67d97d6f | 89 | float32_t a1, b1, c1, d1; /* Temporary variables to store real and imaginary values */ |
emh203 | 0:3d9c67d97d6f | 90 | uint32_t blkCnt; /* loop counters */ |
emh203 | 0:3d9c67d97d6f | 91 | |
emh203 | 0:3d9c67d97d6f | 92 | #ifndef ARM_MATH_CM0_FAMILY |
emh203 | 0:3d9c67d97d6f | 93 | |
emh203 | 0:3d9c67d97d6f | 94 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emh203 | 0:3d9c67d97d6f | 95 | float32_t a2, b2, c2, d2; /* Temporary variables to store real and imaginary values */ |
emh203 | 0:3d9c67d97d6f | 96 | float32_t acc1, acc2, acc3, acc4; |
emh203 | 0:3d9c67d97d6f | 97 | |
emh203 | 0:3d9c67d97d6f | 98 | |
emh203 | 0:3d9c67d97d6f | 99 | /* loop Unrolling */ |
emh203 | 0:3d9c67d97d6f | 100 | blkCnt = numSamples >> 2u; |
emh203 | 0:3d9c67d97d6f | 101 | |
emh203 | 0:3d9c67d97d6f | 102 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emh203 | 0:3d9c67d97d6f | 103 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emh203 | 0:3d9c67d97d6f | 104 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 105 | { |
emh203 | 0:3d9c67d97d6f | 106 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emh203 | 0:3d9c67d97d6f | 107 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emh203 | 0:3d9c67d97d6f | 108 | a1 = *pSrcA; /* A[2 * i] */ |
emh203 | 0:3d9c67d97d6f | 109 | c1 = *pSrcB; /* B[2 * i] */ |
emh203 | 0:3d9c67d97d6f | 110 | |
emh203 | 0:3d9c67d97d6f | 111 | b1 = *(pSrcA + 1); /* A[2 * i + 1] */ |
emh203 | 0:3d9c67d97d6f | 112 | acc1 = a1 * c1; /* acc1 = A[2 * i] * B[2 * i] */ |
emh203 | 0:3d9c67d97d6f | 113 | |
emh203 | 0:3d9c67d97d6f | 114 | a2 = *(pSrcA + 2); /* A[2 * i + 2] */ |
emh203 | 0:3d9c67d97d6f | 115 | acc2 = (b1 * c1); /* acc2 = A[2 * i + 1] * B[2 * i] */ |
emh203 | 0:3d9c67d97d6f | 116 | |
emh203 | 0:3d9c67d97d6f | 117 | d1 = *(pSrcB + 1); /* B[2 * i + 1] */ |
emh203 | 0:3d9c67d97d6f | 118 | c2 = *(pSrcB + 2); /* B[2 * i + 2] */ |
emh203 | 0:3d9c67d97d6f | 119 | acc1 -= b1 * d1; /* acc1 = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */ |
emh203 | 0:3d9c67d97d6f | 120 | |
emh203 | 0:3d9c67d97d6f | 121 | d2 = *(pSrcB + 3); /* B[2 * i + 3] */ |
emh203 | 0:3d9c67d97d6f | 122 | acc3 = a2 * c2; /* acc3 = A[2 * i + 2] * B[2 * i + 2] */ |
emh203 | 0:3d9c67d97d6f | 123 | |
emh203 | 0:3d9c67d97d6f | 124 | b2 = *(pSrcA + 3); /* A[2 * i + 3] */ |
emh203 | 0:3d9c67d97d6f | 125 | acc2 += (a1 * d1); /* acc2 = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */ |
emh203 | 0:3d9c67d97d6f | 126 | |
emh203 | 0:3d9c67d97d6f | 127 | a1 = *(pSrcA + 4); /* A[2 * i + 4] */ |
emh203 | 0:3d9c67d97d6f | 128 | acc4 = (a2 * d2); /* acc4 = A[2 * i + 2] * B[2 * i + 3] */ |
emh203 | 0:3d9c67d97d6f | 129 | |
emh203 | 0:3d9c67d97d6f | 130 | c1 = *(pSrcB + 4); /* B[2 * i + 4] */ |
emh203 | 0:3d9c67d97d6f | 131 | acc3 -= (b2 * d2); /* acc3 = A[2 * i + 2] * B[2 * i + 2] - A[2 * i + 3] * B[2 * i + 3] */ |
emh203 | 0:3d9c67d97d6f | 132 | *pDst = acc1; /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */ |
emh203 | 0:3d9c67d97d6f | 133 | |
emh203 | 0:3d9c67d97d6f | 134 | b1 = *(pSrcA + 5); /* A[2 * i + 5] */ |
emh203 | 0:3d9c67d97d6f | 135 | acc4 += b2 * c2; /* acc4 = A[2 * i + 2] * B[2 * i + 3] + A[2 * i + 3] * B[2 * i + 2] */ |
emh203 | 0:3d9c67d97d6f | 136 | |
emh203 | 0:3d9c67d97d6f | 137 | *(pDst + 1) = acc2; /* C[2 * i + 1] = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */ |
emh203 | 0:3d9c67d97d6f | 138 | acc1 = (a1 * c1); |
emh203 | 0:3d9c67d97d6f | 139 | |
emh203 | 0:3d9c67d97d6f | 140 | d1 = *(pSrcB + 5); |
emh203 | 0:3d9c67d97d6f | 141 | acc2 = (b1 * c1); |
emh203 | 0:3d9c67d97d6f | 142 | |
emh203 | 0:3d9c67d97d6f | 143 | *(pDst + 2) = acc3; |
emh203 | 0:3d9c67d97d6f | 144 | *(pDst + 3) = acc4; |
emh203 | 0:3d9c67d97d6f | 145 | |
emh203 | 0:3d9c67d97d6f | 146 | a2 = *(pSrcA + 6); |
emh203 | 0:3d9c67d97d6f | 147 | acc1 -= (b1 * d1); |
emh203 | 0:3d9c67d97d6f | 148 | |
emh203 | 0:3d9c67d97d6f | 149 | c2 = *(pSrcB + 6); |
emh203 | 0:3d9c67d97d6f | 150 | acc2 += (a1 * d1); |
emh203 | 0:3d9c67d97d6f | 151 | |
emh203 | 0:3d9c67d97d6f | 152 | b2 = *(pSrcA + 7); |
emh203 | 0:3d9c67d97d6f | 153 | acc3 = (a2 * c2); |
emh203 | 0:3d9c67d97d6f | 154 | |
emh203 | 0:3d9c67d97d6f | 155 | d2 = *(pSrcB + 7); |
emh203 | 0:3d9c67d97d6f | 156 | acc4 = (b2 * c2); |
emh203 | 0:3d9c67d97d6f | 157 | |
emh203 | 0:3d9c67d97d6f | 158 | *(pDst + 4) = acc1; |
emh203 | 0:3d9c67d97d6f | 159 | pSrcA += 8u; |
emh203 | 0:3d9c67d97d6f | 160 | |
emh203 | 0:3d9c67d97d6f | 161 | acc3 -= (b2 * d2); |
emh203 | 0:3d9c67d97d6f | 162 | acc4 += (a2 * d2); |
emh203 | 0:3d9c67d97d6f | 163 | |
emh203 | 0:3d9c67d97d6f | 164 | *(pDst + 5) = acc2; |
emh203 | 0:3d9c67d97d6f | 165 | pSrcB += 8u; |
emh203 | 0:3d9c67d97d6f | 166 | |
emh203 | 0:3d9c67d97d6f | 167 | *(pDst + 6) = acc3; |
emh203 | 0:3d9c67d97d6f | 168 | *(pDst + 7) = acc4; |
emh203 | 0:3d9c67d97d6f | 169 | |
emh203 | 0:3d9c67d97d6f | 170 | pDst += 8u; |
emh203 | 0:3d9c67d97d6f | 171 | |
emh203 | 0:3d9c67d97d6f | 172 | /* Decrement the numSamples loop counter */ |
emh203 | 0:3d9c67d97d6f | 173 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 174 | } |
emh203 | 0:3d9c67d97d6f | 175 | |
emh203 | 0:3d9c67d97d6f | 176 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. |
emh203 | 0:3d9c67d97d6f | 177 | ** No loop unrolling is used. */ |
emh203 | 0:3d9c67d97d6f | 178 | blkCnt = numSamples % 0x4u; |
emh203 | 0:3d9c67d97d6f | 179 | |
emh203 | 0:3d9c67d97d6f | 180 | #else |
emh203 | 0:3d9c67d97d6f | 181 | |
emh203 | 0:3d9c67d97d6f | 182 | /* Run the below code for Cortex-M0 */ |
emh203 | 0:3d9c67d97d6f | 183 | blkCnt = numSamples; |
emh203 | 0:3d9c67d97d6f | 184 | |
emh203 | 0:3d9c67d97d6f | 185 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
emh203 | 0:3d9c67d97d6f | 186 | |
emh203 | 0:3d9c67d97d6f | 187 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 188 | { |
emh203 | 0:3d9c67d97d6f | 189 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emh203 | 0:3d9c67d97d6f | 190 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emh203 | 0:3d9c67d97d6f | 191 | a1 = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 192 | b1 = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 193 | c1 = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 194 | d1 = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 195 | |
emh203 | 0:3d9c67d97d6f | 196 | /* store the result in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 197 | *pDst++ = (a1 * c1) - (b1 * d1); |
emh203 | 0:3d9c67d97d6f | 198 | *pDst++ = (a1 * d1) + (b1 * c1); |
emh203 | 0:3d9c67d97d6f | 199 | |
emh203 | 0:3d9c67d97d6f | 200 | /* Decrement the numSamples loop counter */ |
emh203 | 0:3d9c67d97d6f | 201 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 202 | } |
emh203 | 0:3d9c67d97d6f | 203 | } |
emh203 | 0:3d9c67d97d6f | 204 | |
emh203 | 0:3d9c67d97d6f | 205 | /** |
emh203 | 0:3d9c67d97d6f | 206 | * @} end of CmplxByCmplxMult group |
emh203 | 0:3d9c67d97d6f | 207 | */ |