| 提交 | 用户 | age | ||
| 8b51c7 | 1 | /* ---------------------------------------------------------------------- |
| Q | 2 | * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
| 3 | * | |
| 4 | * $Date: 19. October 2015 | |
| 5 | * $Revision: V.1.4.5 a | |
| 6 | * | |
| 7 | * Project: CMSIS DSP Library | |
| 8 | * Title: arm_cmplx_mult_real_q15.c | |
| 9 | * | |
| 10 | * Description: Q15 complex by real multiplication | |
| 11 | * | |
| 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 | |
| 13 | * | |
| 14 | * Redistribution and use in source and binary forms, with or without | |
| 15 | * modification, are permitted provided that the following conditions | |
| 16 | * are met: | |
| 17 | * - Redistributions of source code must retain the above copyright | |
| 18 | * notice, this list of conditions and the following disclaimer. | |
| 19 | * - Redistributions in binary form must reproduce the above copyright | |
| 20 | * notice, this list of conditions and the following disclaimer in | |
| 21 | * the documentation and/or other materials provided with the | |
| 22 | * distribution. | |
| 23 | * - Neither the name of ARM LIMITED nor the names of its contributors | |
| 24 | * may be used to endorse or promote products derived from this | |
| 25 | * software without specific prior written permission. | |
| 26 | * | |
| 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
| 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
| 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS | |
| 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE | |
| 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, | |
| 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, | |
| 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | |
| 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER | |
| 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT | |
| 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN | |
| 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE | |
| 38 | * POSSIBILITY OF SUCH DAMAGE. | |
| 39 | * -------------------------------------------------------------------- */ | |
| 40 | ||
| 41 | #include "arm_math.h" | |
| 42 | ||
| 43 | /** | |
| 44 | * @ingroup groupCmplxMath | |
| 45 | */ | |
| 46 | ||
| 47 | /** | |
| 48 | * @addtogroup CmplxByRealMult | |
| 49 | * @{ | |
| 50 | */ | |
| 51 | ||
| 52 | ||
| 53 | /** | |
| 54 | * @brief Q15 complex-by-real multiplication | |
| 55 | * @param[in] *pSrcCmplx points to the complex input vector | |
| 56 | * @param[in] *pSrcReal points to the real input vector | |
| 57 | * @param[out] *pCmplxDst points to the complex output vector | |
| 58 | * @param[in] numSamples number of samples in each vector | |
| 59 | * @return none. | |
| 60 | * | |
| 61 | * <b>Scaling and Overflow Behavior:</b> | |
| 62 | * \par | |
| 63 | * The function uses saturating arithmetic. | |
| 64 | * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated. | |
| 65 | */ | |
| 66 | ||
| 67 | void arm_cmplx_mult_real_q15( | |
| 68 | q15_t * pSrcCmplx, | |
| 69 | q15_t * pSrcReal, | |
| 70 | q15_t * pCmplxDst, | |
| 71 | uint32_t numSamples) | |
| 72 | { | |
| 73 | q15_t in; /* Temporary variable to store input value */ | |
| 74 | ||
| 75 | #ifndef ARM_MATH_CM0_FAMILY | |
| 76 | ||
| 77 | /* Run the below code for Cortex-M4 and Cortex-M3 */ | |
| 78 | uint32_t blkCnt; /* loop counters */ | |
| 79 | q31_t inA1, inA2; /* Temporary variables to hold input data */ | |
| 80 | q31_t inB1; /* Temporary variables to hold input data */ | |
| 81 | q15_t out1, out2, out3, out4; /* Temporary variables to hold output data */ | |
| 82 | q31_t mul1, mul2, mul3, mul4; /* Temporary variables to hold intermediate data */ | |
| 83 | ||
| 84 | /* loop Unrolling */ | |
| 85 | blkCnt = numSamples >> 2u; | |
| 86 | ||
| 87 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. | |
| 88 | ** a second loop below computes the remaining 1 to 3 samples. */ | |
| 89 | while(blkCnt > 0u) | |
| 90 | { | |
| 91 | /* C[2 * i] = A[2 * i] * B[i]. */ | |
| 92 | /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */ | |
| 93 | /* read complex number both real and imaginary from complex input buffer */ | |
| 94 | inA1 = *__SIMD32(pSrcCmplx)++; | |
| 95 | /* read two real values at a time from real input buffer */ | |
| 96 | inB1 = *__SIMD32(pSrcReal)++; | |
| 97 | /* read complex number both real and imaginary from complex input buffer */ | |
| 98 | inA2 = *__SIMD32(pSrcCmplx)++; | |
| 99 | ||
| 100 | /* multiply complex number with real numbers */ | |
| 101 | #ifndef ARM_MATH_BIG_ENDIAN | |
| 102 | ||
| 103 | mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1)); | |
| 104 | mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1)); | |
| 105 | mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16)); | |
| 106 | mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16)); | |
| 107 | ||
| 108 | #else | |
| 109 | ||
| 110 | mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16)); | |
| 111 | mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16)); | |
| 112 | mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1); | |
| 113 | mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1); | |
| 114 | ||
| 115 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ | |
| 116 | ||
| 117 | /* saturate the result */ | |
| 118 | out1 = (q15_t) __SSAT(mul1 >> 15u, 16); | |
| 119 | out2 = (q15_t) __SSAT(mul2 >> 15u, 16); | |
| 120 | out3 = (q15_t) __SSAT(mul3 >> 15u, 16); | |
| 121 | out4 = (q15_t) __SSAT(mul4 >> 15u, 16); | |
| 122 | ||
| 123 | /* pack real and imaginary outputs and store them to destination */ | |
| 124 | *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16); | |
| 125 | *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16); | |
| 126 | ||
| 127 | inA1 = *__SIMD32(pSrcCmplx)++; | |
| 128 | inB1 = *__SIMD32(pSrcReal)++; | |
| 129 | inA2 = *__SIMD32(pSrcCmplx)++; | |
| 130 | ||
| 131 | #ifndef ARM_MATH_BIG_ENDIAN | |
| 132 | ||
| 133 | mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1)); | |
| 134 | mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1)); | |
| 135 | mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16)); | |
| 136 | mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16)); | |
| 137 | ||
| 138 | #else | |
| 139 | ||
| 140 | mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16)); | |
| 141 | mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16)); | |
| 142 | mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1); | |
| 143 | mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1); | |
| 144 | ||
| 145 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ | |
| 146 | ||
| 147 | out1 = (q15_t) __SSAT(mul1 >> 15u, 16); | |
| 148 | out2 = (q15_t) __SSAT(mul2 >> 15u, 16); | |
| 149 | out3 = (q15_t) __SSAT(mul3 >> 15u, 16); | |
| 150 | out4 = (q15_t) __SSAT(mul4 >> 15u, 16); | |
| 151 | ||
| 152 | *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16); | |
| 153 | *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16); | |
| 154 | ||
| 155 | /* Decrement the numSamples loop counter */ | |
| 156 | blkCnt--; | |
| 157 | } | |
| 158 | ||
| 159 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. | |
| 160 | ** No loop unrolling is used. */ | |
| 161 | blkCnt = numSamples % 0x4u; | |
| 162 | ||
| 163 | while(blkCnt > 0u) | |
| 164 | { | |
| 165 | /* C[2 * i] = A[2 * i] * B[i]. */ | |
| 166 | /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */ | |
| 167 | in = *pSrcReal++; | |
| 168 | /* store the result in the destination buffer. */ | |
| 169 | *pCmplxDst++ = | |
| 170 | (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16); | |
| 171 | *pCmplxDst++ = | |
| 172 | (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16); | |
| 173 | ||
| 174 | /* Decrement the numSamples loop counter */ | |
| 175 | blkCnt--; | |
| 176 | } | |
| 177 | ||
| 178 | #else | |
| 179 | ||
| 180 | /* Run the below code for Cortex-M0 */ | |
| 181 | ||
| 182 | while(numSamples > 0u) | |
| 183 | { | |
| 184 | /* realOut = realA * realB. */ | |
| 185 | /* imagOut = imagA * realB. */ | |
| 186 | in = *pSrcReal++; | |
| 187 | /* store the result in the destination buffer. */ | |
| 188 | *pCmplxDst++ = | |
| 189 | (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16); | |
| 190 | *pCmplxDst++ = | |
| 191 | (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16); | |
| 192 | ||
| 193 | /* Decrement the numSamples loop counter */ | |
| 194 | numSamples--; | |
| 195 | } | |
| 196 | ||
| 197 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ | |
| 198 | ||
| 199 | } | |
| 200 | ||
| 201 | /** | |
| 202 | * @} end of CmplxByRealMult group | |
| 203 | */ | |
