CMSIS DSP library

Dependents:   KL25Z_FFT_Demo Hat_Board_v5_1 KL25Z_FFT_Demo_tony KL25Z_FFT_Demo_tony ... more

Fork of mbed-dsp by mbed official

Committer:
mbed_official
Date:
Fri Nov 08 13:45:10 2013 +0000
Revision:
3:7a284390b0ce
Parent:
2:da51fb522205
Synchronized with git revision e69956aba2f68a2a26ac26b051f8d349deaa1ce8

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
mbed_official 3:7a284390b0ce 2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 3:7a284390b0ce 4 * $Date: 17. January 2013
mbed_official 3:7a284390b0ce 5 * $Revision: V1.4.1
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_cmplx_mult_real_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q31 complex by real 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 CmplxByRealMult
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-real multiplication
emilmont 1:fdd22bb7aa52 55 * @param[in] *pSrcCmplx points to the complex input vector
emilmont 1:fdd22bb7aa52 56 * @param[in] *pSrcReal points to the real input vector
emilmont 1:fdd22bb7aa52 57 * @param[out] *pCmplxDst points to the complex output vector
emilmont 1:fdd22bb7aa52 58 * @param[in] numSamples number of 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 uses saturating arithmetic.
emilmont 1:fdd22bb7aa52 64 * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.
emilmont 1:fdd22bb7aa52 65 */
emilmont 1:fdd22bb7aa52 66
emilmont 1:fdd22bb7aa52 67 void arm_cmplx_mult_real_q31(
emilmont 1:fdd22bb7aa52 68 q31_t * pSrcCmplx,
emilmont 1:fdd22bb7aa52 69 q31_t * pSrcReal,
emilmont 1:fdd22bb7aa52 70 q31_t * pCmplxDst,
emilmont 1:fdd22bb7aa52 71 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 72 {
emilmont 1:fdd22bb7aa52 73 q31_t inA1; /* Temporary variable to store input value */
emilmont 1:fdd22bb7aa52 74
mbed_official 3:7a284390b0ce 75 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 78 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 79 q31_t inA2, inA3, inA4; /* Temporary variables to hold input data */
emilmont 1:fdd22bb7aa52 80 q31_t inB1, inB2; /* Temporary variabels to hold input data */
emilmont 1:fdd22bb7aa52 81 q31_t out1, out2, out3, out4; /* Temporary variables to hold output data */
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 84 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 85
emilmont 1:fdd22bb7aa52 86 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 87 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 88 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 89 {
emilmont 1:fdd22bb7aa52 90 /* C[2 * i] = A[2 * i] * B[i]. */
emilmont 1:fdd22bb7aa52 91 /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */
emilmont 1:fdd22bb7aa52 92 /* read real input from complex input buffer */
emilmont 1:fdd22bb7aa52 93 inA1 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 94 inA2 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 95 /* read input from real input bufer */
emilmont 1:fdd22bb7aa52 96 inB1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 97 inB2 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 98 /* read imaginary input from complex input buffer */
emilmont 1:fdd22bb7aa52 99 inA3 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 100 inA4 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* multiply complex input with real input */
emilmont 1:fdd22bb7aa52 103 out1 = ((q63_t) inA1 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 104 out2 = ((q63_t) inA2 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 105 out3 = ((q63_t) inA3 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 106 out4 = ((q63_t) inA4 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* sature the result */
emilmont 1:fdd22bb7aa52 109 out1 = __SSAT(out1, 31);
emilmont 1:fdd22bb7aa52 110 out2 = __SSAT(out2, 31);
emilmont 1:fdd22bb7aa52 111 out3 = __SSAT(out3, 31);
emilmont 1:fdd22bb7aa52 112 out4 = __SSAT(out4, 31);
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 /* get result in 1.31 format */
emilmont 1:fdd22bb7aa52 115 out1 = out1 << 1;
emilmont 1:fdd22bb7aa52 116 out2 = out2 << 1;
emilmont 1:fdd22bb7aa52 117 out3 = out3 << 1;
emilmont 1:fdd22bb7aa52 118 out4 = out4 << 1;
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 /* store the result to destination buffer */
emilmont 1:fdd22bb7aa52 121 *pCmplxDst++ = out1;
emilmont 1:fdd22bb7aa52 122 *pCmplxDst++ = out2;
emilmont 1:fdd22bb7aa52 123 *pCmplxDst++ = out3;
emilmont 1:fdd22bb7aa52 124 *pCmplxDst++ = out4;
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* read real input from complex input buffer */
emilmont 1:fdd22bb7aa52 127 inA1 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 128 inA2 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 129 /* read input from real input bufer */
emilmont 1:fdd22bb7aa52 130 inB1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 131 inB2 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 132 /* read imaginary input from complex input buffer */
emilmont 1:fdd22bb7aa52 133 inA3 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 134 inA4 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 /* multiply complex input with real input */
emilmont 1:fdd22bb7aa52 137 out1 = ((q63_t) inA1 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 138 out2 = ((q63_t) inA2 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 139 out3 = ((q63_t) inA3 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 140 out4 = ((q63_t) inA4 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /* sature the result */
emilmont 1:fdd22bb7aa52 143 out1 = __SSAT(out1, 31);
emilmont 1:fdd22bb7aa52 144 out2 = __SSAT(out2, 31);
emilmont 1:fdd22bb7aa52 145 out3 = __SSAT(out3, 31);
emilmont 1:fdd22bb7aa52 146 out4 = __SSAT(out4, 31);
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 /* get result in 1.31 format */
emilmont 1:fdd22bb7aa52 149 out1 = out1 << 1;
emilmont 1:fdd22bb7aa52 150 out2 = out2 << 1;
emilmont 1:fdd22bb7aa52 151 out3 = out3 << 1;
emilmont 1:fdd22bb7aa52 152 out4 = out4 << 1;
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 /* store the result to destination buffer */
emilmont 1:fdd22bb7aa52 155 *pCmplxDst++ = out1;
emilmont 1:fdd22bb7aa52 156 *pCmplxDst++ = out2;
emilmont 1:fdd22bb7aa52 157 *pCmplxDst++ = out3;
emilmont 1:fdd22bb7aa52 158 *pCmplxDst++ = out4;
emilmont 1:fdd22bb7aa52 159
emilmont 1:fdd22bb7aa52 160 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 161 blkCnt--;
emilmont 1:fdd22bb7aa52 162 }
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 165 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 166 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 167
emilmont 1:fdd22bb7aa52 168 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 169 {
emilmont 1:fdd22bb7aa52 170 /* C[2 * i] = A[2 * i] * B[i]. */
emilmont 1:fdd22bb7aa52 171 /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */
emilmont 1:fdd22bb7aa52 172 /* read real input from complex input buffer */
emilmont 1:fdd22bb7aa52 173 inA1 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 174 inA2 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 175 /* read input from real input bufer */
emilmont 1:fdd22bb7aa52 176 inB1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 /* multiply complex input with real input */
emilmont 1:fdd22bb7aa52 179 out1 = ((q63_t) inA1 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 180 out2 = ((q63_t) inA2 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 181
emilmont 1:fdd22bb7aa52 182 /* sature the result */
emilmont 1:fdd22bb7aa52 183 out1 = __SSAT(out1, 31);
emilmont 1:fdd22bb7aa52 184 out2 = __SSAT(out2, 31);
emilmont 1:fdd22bb7aa52 185
emilmont 1:fdd22bb7aa52 186 /* get result in 1.31 format */
emilmont 1:fdd22bb7aa52 187 out1 = out1 << 1;
emilmont 1:fdd22bb7aa52 188 out2 = out2 << 1;
emilmont 1:fdd22bb7aa52 189
emilmont 1:fdd22bb7aa52 190 /* store the result to destination buffer */
emilmont 1:fdd22bb7aa52 191 *pCmplxDst++ = out1;
emilmont 1:fdd22bb7aa52 192 *pCmplxDst++ = out2;
emilmont 1:fdd22bb7aa52 193
emilmont 1:fdd22bb7aa52 194 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 195 blkCnt--;
emilmont 1:fdd22bb7aa52 196 }
emilmont 1:fdd22bb7aa52 197
emilmont 1:fdd22bb7aa52 198 #else
emilmont 1:fdd22bb7aa52 199
emilmont 1:fdd22bb7aa52 200 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 201
emilmont 1:fdd22bb7aa52 202 while(numSamples > 0u)
emilmont 1:fdd22bb7aa52 203 {
emilmont 1:fdd22bb7aa52 204 /* realOut = realA * realB. */
emilmont 1:fdd22bb7aa52 205 /* imagReal = imagA * realB. */
emilmont 1:fdd22bb7aa52 206 inA1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 207 /* store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 208 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 209 (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
emilmont 1:fdd22bb7aa52 210 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 211 (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
emilmont 1:fdd22bb7aa52 212
emilmont 1:fdd22bb7aa52 213 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 214 numSamples--;
emilmont 1:fdd22bb7aa52 215 }
emilmont 1:fdd22bb7aa52 216
mbed_official 3:7a284390b0ce 217 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 218
emilmont 1:fdd22bb7aa52 219 }
emilmont 1:fdd22bb7aa52 220
emilmont 1:fdd22bb7aa52 221 /**
emilmont 1:fdd22bb7aa52 222 * @} end of CmplxByRealMult group
emilmont 1:fdd22bb7aa52 223 */