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.

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. October 2015
mbed_official 5:3762170b6d4d 5 * $Revision: V.1.4.5 a
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_cmplx_mult_real_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q15 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 Q15 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 Q15 range [0x8000 0x7FFF] will be saturated.
emilmont 1:fdd22bb7aa52 65 */
emilmont 1:fdd22bb7aa52 66
emilmont 1:fdd22bb7aa52 67 void arm_cmplx_mult_real_q15(
emilmont 1:fdd22bb7aa52 68 q15_t * pSrcCmplx,
emilmont 1:fdd22bb7aa52 69 q15_t * pSrcReal,
emilmont 1:fdd22bb7aa52 70 q15_t * pCmplxDst,
emilmont 1:fdd22bb7aa52 71 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 72 {
emilmont 1:fdd22bb7aa52 73 q15_t in; /* 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 inA1, inA2; /* Temporary variables to hold input data */
emilmont 1:fdd22bb7aa52 80 q31_t inB1; /* Temporary variables to hold input data */
emilmont 1:fdd22bb7aa52 81 q15_t out1, out2, out3, out4; /* Temporary variables to hold output data */
emilmont 1:fdd22bb7aa52 82 q31_t mul1, mul2, mul3, mul4; /* Temporary variables to hold intermediate data */
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 85 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 88 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 89 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 90 {
emilmont 1:fdd22bb7aa52 91 /* C[2 * i] = A[2 * i] * B[i]. */
emilmont 1:fdd22bb7aa52 92 /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */
emilmont 1:fdd22bb7aa52 93 /* read complex number both real and imaginary from complex input buffer */
emilmont 1:fdd22bb7aa52 94 inA1 = *__SIMD32(pSrcCmplx)++;
emilmont 1:fdd22bb7aa52 95 /* read two real values at a time from real input buffer */
emilmont 1:fdd22bb7aa52 96 inB1 = *__SIMD32(pSrcReal)++;
emilmont 1:fdd22bb7aa52 97 /* read complex number both real and imaginary from complex input buffer */
emilmont 1:fdd22bb7aa52 98 inA2 = *__SIMD32(pSrcCmplx)++;
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 /* multiply complex number with real numbers */
emilmont 1:fdd22bb7aa52 101 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1));
emilmont 1:fdd22bb7aa52 104 mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1));
emilmont 1:fdd22bb7aa52 105 mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 106 mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 #else
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110 mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 111 mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 112 mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1);
emilmont 1:fdd22bb7aa52 113 mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1);
emilmont 1:fdd22bb7aa52 114
mbed_official 5:3762170b6d4d 115 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* saturate the result */
emilmont 1:fdd22bb7aa52 118 out1 = (q15_t) __SSAT(mul1 >> 15u, 16);
emilmont 1:fdd22bb7aa52 119 out2 = (q15_t) __SSAT(mul2 >> 15u, 16);
emilmont 1:fdd22bb7aa52 120 out3 = (q15_t) __SSAT(mul3 >> 15u, 16);
emilmont 1:fdd22bb7aa52 121 out4 = (q15_t) __SSAT(mul4 >> 15u, 16);
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* pack real and imaginary outputs and store them to destination */
emilmont 1:fdd22bb7aa52 124 *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16);
emilmont 1:fdd22bb7aa52 125 *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16);
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 inA1 = *__SIMD32(pSrcCmplx)++;
emilmont 1:fdd22bb7aa52 128 inB1 = *__SIMD32(pSrcReal)++;
emilmont 1:fdd22bb7aa52 129 inA2 = *__SIMD32(pSrcCmplx)++;
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1));
emilmont 1:fdd22bb7aa52 134 mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1));
emilmont 1:fdd22bb7aa52 135 mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 136 mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 #else
emilmont 1:fdd22bb7aa52 139
emilmont 1:fdd22bb7aa52 140 mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 141 mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 142 mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1);
emilmont 1:fdd22bb7aa52 143 mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1);
emilmont 1:fdd22bb7aa52 144
mbed_official 5:3762170b6d4d 145 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 out1 = (q15_t) __SSAT(mul1 >> 15u, 16);
emilmont 1:fdd22bb7aa52 148 out2 = (q15_t) __SSAT(mul2 >> 15u, 16);
emilmont 1:fdd22bb7aa52 149 out3 = (q15_t) __SSAT(mul3 >> 15u, 16);
emilmont 1:fdd22bb7aa52 150 out4 = (q15_t) __SSAT(mul4 >> 15u, 16);
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16);
emilmont 1:fdd22bb7aa52 153 *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16);
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 156 blkCnt--;
emilmont 1:fdd22bb7aa52 157 }
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 160 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 161 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 162
emilmont 1:fdd22bb7aa52 163 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 164 {
emilmont 1:fdd22bb7aa52 165 /* C[2 * i] = A[2 * i] * B[i]. */
emilmont 1:fdd22bb7aa52 166 /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */
emilmont 1:fdd22bb7aa52 167 in = *pSrcReal++;
emilmont 1:fdd22bb7aa52 168 /* store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 169 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 170 (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
emilmont 1:fdd22bb7aa52 171 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 172 (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 175 blkCnt--;
emilmont 1:fdd22bb7aa52 176 }
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 #else
emilmont 1:fdd22bb7aa52 179
emilmont 1:fdd22bb7aa52 180 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 181
emilmont 1:fdd22bb7aa52 182 while(numSamples > 0u)
emilmont 1:fdd22bb7aa52 183 {
emilmont 1:fdd22bb7aa52 184 /* realOut = realA * realB. */
emilmont 1:fdd22bb7aa52 185 /* imagOut = imagA * realB. */
emilmont 1:fdd22bb7aa52 186 in = *pSrcReal++;
emilmont 1:fdd22bb7aa52 187 /* store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 188 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 189 (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
emilmont 1:fdd22bb7aa52 190 *pCmplxDst++ =
emilmont 1:fdd22bb7aa52 191 (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
emilmont 1:fdd22bb7aa52 192
emilmont 1:fdd22bb7aa52 193 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 194 numSamples--;
emilmont 1:fdd22bb7aa52 195 }
emilmont 1:fdd22bb7aa52 196
mbed_official 3:7a284390b0ce 197 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 198
emilmont 1:fdd22bb7aa52 199 }
emilmont 1:fdd22bb7aa52 200
emilmont 1:fdd22bb7aa52 201 /**
emilmont 1:fdd22bb7aa52 202 * @} end of CmplxByRealMult group
emilmont 1:fdd22bb7aa52 203 */