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_real_q31.c@2:da51fb522205, 2013-05-30 (annotated)

Committer:
emilmont
Date:
Thu May 30 17:10:11 2013 +0100
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
emilmont 1:fdd22bb7aa52 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
emilmont 1:fdd22bb7aa52 4 * $Date: 15. February 2012
emilmont 2:da51fb522205 5 * $Revision: V1.1.0
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 *
emilmont 1:fdd22bb7aa52 14 * Version 1.1.0 2012/02/15
emilmont 1:fdd22bb7aa52 15 * Updated with more optimizations, bug fixes and minor API changes.
emilmont 1:fdd22bb7aa52 16 *
emilmont 1:fdd22bb7aa52 17 * Version 1.0.10 2011/7/15
emilmont 1:fdd22bb7aa52 18 * Big Endian support added and Merged M0 and M3/M4 Source code.
emilmont 1:fdd22bb7aa52 19 *
emilmont 1:fdd22bb7aa52 20 * Version 1.0.3 2010/11/29
emilmont 1:fdd22bb7aa52 21 * Re-organized the CMSIS folders and updated documentation.
emilmont 1:fdd22bb7aa52 22 *
emilmont 1:fdd22bb7aa52 23 * Version 1.0.2 2010/11/11
emilmont 1:fdd22bb7aa52 24 * Documentation updated.
emilmont 1:fdd22bb7aa52 25 *
emilmont 1:fdd22bb7aa52 26 * Version 1.0.1 2010/10/05
emilmont 1:fdd22bb7aa52 27 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 28 *
emilmont 1:fdd22bb7aa52 29 * Version 1.0.0 2010/09/20
emilmont 1:fdd22bb7aa52 30 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 31 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 32
emilmont 1:fdd22bb7aa52 33 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 34
emilmont 1:fdd22bb7aa52 35 /**
emilmont 1:fdd22bb7aa52 36 * @ingroup groupCmplxMath
emilmont 1:fdd22bb7aa52 37 */
emilmont 1:fdd22bb7aa52 38
emilmont 1:fdd22bb7aa52 39 /**
emilmont 1:fdd22bb7aa52 40 * @addtogroup CmplxByRealMult
emilmont 1:fdd22bb7aa52 41 * @{
emilmont 1:fdd22bb7aa52 42 */
emilmont 1:fdd22bb7aa52 43
emilmont 1:fdd22bb7aa52 44
emilmont 1:fdd22bb7aa52 45 /**
emilmont 1:fdd22bb7aa52 46 * @brief Q31 complex-by-real multiplication
emilmont 1:fdd22bb7aa52 47 * @param[in] *pSrcCmplx points to the complex input vector
emilmont 1:fdd22bb7aa52 48 * @param[in] *pSrcReal points to the real input vector
emilmont 1:fdd22bb7aa52 49 * @param[out] *pCmplxDst points to the complex output vector
emilmont 1:fdd22bb7aa52 50 * @param[in] numSamples number of samples in each vector
emilmont 1:fdd22bb7aa52 51 * @return none.
emilmont 1:fdd22bb7aa52 52 *
emilmont 1:fdd22bb7aa52 53 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 54 * \par
emilmont 1:fdd22bb7aa52 55 * The function uses saturating arithmetic.
emilmont 1:fdd22bb7aa52 56 * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.
emilmont 1:fdd22bb7aa52 57 */
emilmont 1:fdd22bb7aa52 58
emilmont 1:fdd22bb7aa52 59 void arm_cmplx_mult_real_q31(
emilmont 1:fdd22bb7aa52 60 q31_t * pSrcCmplx,
emilmont 1:fdd22bb7aa52 61 q31_t * pSrcReal,
emilmont 1:fdd22bb7aa52 62 q31_t * pCmplxDst,
emilmont 1:fdd22bb7aa52 63 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 64 {
emilmont 1:fdd22bb7aa52 65 q31_t inA1; /* Temporary variable to store input value */
emilmont 1:fdd22bb7aa52 66
emilmont 1:fdd22bb7aa52 67 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 68
emilmont 1:fdd22bb7aa52 69 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 70 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 71 q31_t inA2, inA3, inA4; /* Temporary variables to hold input data */
emilmont 1:fdd22bb7aa52 72 q31_t inB1, inB2; /* Temporary variabels to hold input data */
emilmont 1:fdd22bb7aa52 73 q31_t out1, out2, out3, out4; /* Temporary variables to hold output data */
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 76 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 79 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 80 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 81 {
emilmont 1:fdd22bb7aa52 82 /* C[2 * i] = A[2 * i] * B[i]. */
emilmont 1:fdd22bb7aa52 83 /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */
emilmont 1:fdd22bb7aa52 84 /* read real input from complex input buffer */
emilmont 1:fdd22bb7aa52 85 inA1 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 86 inA2 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 87 /* read input from real input bufer */
emilmont 1:fdd22bb7aa52 88 inB1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 89 inB2 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 90 /* read imaginary input from complex input buffer */
emilmont 1:fdd22bb7aa52 91 inA3 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 92 inA4 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 /* multiply complex input with real input */
emilmont 1:fdd22bb7aa52 95 out1 = ((q63_t) inA1 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 96 out2 = ((q63_t) inA2 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 97 out3 = ((q63_t) inA3 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 98 out4 = ((q63_t) inA4 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 /* sature the result */
emilmont 1:fdd22bb7aa52 101 out1 = __SSAT(out1, 31);
emilmont 1:fdd22bb7aa52 102 out2 = __SSAT(out2, 31);
emilmont 1:fdd22bb7aa52 103 out3 = __SSAT(out3, 31);
emilmont 1:fdd22bb7aa52 104 out4 = __SSAT(out4, 31);
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* get result in 1.31 format */
emilmont 1:fdd22bb7aa52 107 out1 = out1 << 1;
emilmont 1:fdd22bb7aa52 108 out2 = out2 << 1;
emilmont 1:fdd22bb7aa52 109 out3 = out3 << 1;
emilmont 1:fdd22bb7aa52 110 out4 = out4 << 1;
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* store the result to destination buffer */
emilmont 1:fdd22bb7aa52 113 *pCmplxDst++ = out1;
emilmont 1:fdd22bb7aa52 114 *pCmplxDst++ = out2;
emilmont 1:fdd22bb7aa52 115 *pCmplxDst++ = out3;
emilmont 1:fdd22bb7aa52 116 *pCmplxDst++ = out4;
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* read real input from complex input buffer */
emilmont 1:fdd22bb7aa52 119 inA1 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 120 inA2 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 121 /* read input from real input bufer */
emilmont 1:fdd22bb7aa52 122 inB1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 123 inB2 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 124 /* read imaginary input from complex input buffer */
emilmont 1:fdd22bb7aa52 125 inA3 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 126 inA4 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 /* multiply complex input with real input */
emilmont 1:fdd22bb7aa52 129 out1 = ((q63_t) inA1 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 130 out2 = ((q63_t) inA2 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 131 out3 = ((q63_t) inA3 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 132 out4 = ((q63_t) inA4 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 /* sature the result */
emilmont 1:fdd22bb7aa52 135 out1 = __SSAT(out1, 31);
emilmont 1:fdd22bb7aa52 136 out2 = __SSAT(out2, 31);
emilmont 1:fdd22bb7aa52 137 out3 = __SSAT(out3, 31);
emilmont 1:fdd22bb7aa52 138 out4 = __SSAT(out4, 31);
emilmont 1:fdd22bb7aa52 139
emilmont 1:fdd22bb7aa52 140 /* get result in 1.31 format */
emilmont 1:fdd22bb7aa52 141 out1 = out1 << 1;
emilmont 1:fdd22bb7aa52 142 out2 = out2 << 1;
emilmont 1:fdd22bb7aa52 143 out3 = out3 << 1;
emilmont 1:fdd22bb7aa52 144 out4 = out4 << 1;
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 /* store the result to destination buffer */
emilmont 1:fdd22bb7aa52 147 *pCmplxDst++ = out1;
emilmont 1:fdd22bb7aa52 148 *pCmplxDst++ = out2;
emilmont 1:fdd22bb7aa52 149 *pCmplxDst++ = out3;
emilmont 1:fdd22bb7aa52 150 *pCmplxDst++ = out4;
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 153 blkCnt--;
emilmont 1:fdd22bb7aa52 154 }
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 157 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 158 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 159
emilmont 1:fdd22bb7aa52 160 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 161 {
emilmont 1:fdd22bb7aa52 162 /* C[2 * i] = A[2 * i] * B[i]. */
emilmont 1:fdd22bb7aa52 163 /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */
emilmont 1:fdd22bb7aa52 164 /* read real input from complex input buffer */
emilmont 1:fdd22bb7aa52 165 inA1 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 166 inA2 = *pSrcCmplx++;
emilmont 1:fdd22bb7aa52 167 /* read input from real input bufer */
emilmont 1:fdd22bb7aa52 168 inB1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 /* multiply complex input with real input */
emilmont 1:fdd22bb7aa52 171 out1 = ((q63_t) inA1 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 172 out2 = ((q63_t) inA2 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 /* sature the result */
emilmont 1:fdd22bb7aa52 175 out1 = __SSAT(out1, 31);
emilmont 1:fdd22bb7aa52 176 out2 = __SSAT(out2, 31);
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 /* get result in 1.31 format */
emilmont 1:fdd22bb7aa52 179 out1 = out1 << 1;
emilmont 1:fdd22bb7aa52 180 out2 = out2 << 1;
emilmont 1:fdd22bb7aa52 181
emilmont 1:fdd22bb7aa52 182 /* store the result to destination buffer */
emilmont 1:fdd22bb7aa52 183 *pCmplxDst++ = out1;
emilmont 1:fdd22bb7aa52 184 *pCmplxDst++ = out2;
emilmont 1:fdd22bb7aa52 185
emilmont 1:fdd22bb7aa52 186 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 187 blkCnt--;
emilmont 1:fdd22bb7aa52 188 }
emilmont 1:fdd22bb7aa52 189
emilmont 1:fdd22bb7aa52 190 #else
emilmont 1:fdd22bb7aa52 191
emilmont 1:fdd22bb7aa52 192 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 193
emilmont 1:fdd22bb7aa52 194 while(numSamples > 0u)
emilmont 1:fdd22bb7aa52 195 {
emilmont 1:fdd22bb7aa52 196 /* realOut = realA * realB. */
emilmont 1:fdd22bb7aa52 197 /* imagReal = imagA * realB. */
emilmont 1:fdd22bb7aa52 198 inA1 = *pSrcReal++;
emilmont 1:fdd22bb7aa52 199 /* store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 200 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 201 (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
emilmont 1:fdd22bb7aa52 202 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 203 (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
emilmont 1:fdd22bb7aa52 204
emilmont 1:fdd22bb7aa52 205 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 206 numSamples--;
emilmont 1:fdd22bb7aa52 207 }
emilmont 1:fdd22bb7aa52 208
emilmont 1:fdd22bb7aa52 209 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 210
emilmont 1:fdd22bb7aa52 211 }
emilmont 1:fdd22bb7aa52 212
emilmont 1:fdd22bb7aa52 213 /**
emilmont 1:fdd22bb7aa52 214 * @} end of CmplxByRealMult group
emilmont 1:fdd22bb7aa52 215 */