Fork of mbed-dsp. CMSIS-DSP library of supporting NEON
Dependents: mbed-os-example-cmsis_dsp_neon
Fork of mbed-dsp by
Information
Japanese version is available in lower part of this page.
このページの後半に日本語版が用意されています.
CMSIS-DSP of supporting NEON
What is this ?
A library for CMSIS-DSP of supporting NEON.
We supported the NEON to CMSIS-DSP Ver1.4.3(CMSIS V4.1) that ARM supplied, has achieved the processing speed improvement.
If you use the mbed-dsp library, you can use to replace this library.
CMSIS-DSP of supporting NEON is provied as a library.
Library Creation environment
CMSIS-DSP library of supporting NEON was created by the following environment.
- Compiler
ARMCC Version 5.03 - Compile option switch[C Compiler]
-DARM_MATH_MATRIX_CHECK -DARM_MATH_ROUNDING -O3 -Otime --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp --vectorize --asm
- Compile option switch[Assembler]
--cpreproc --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp
Effects of NEON support
In the data which passes to each function, large size will be expected more effective than small size.
Also if the data is a multiple of 16, effect will be expected in every function in the CMSIS-DSP.
NEON対応CMSIS-DSP
概要
NEON対応したCMSIS-DSPのライブラリです。
ARM社提供のCMSIS-DSP Ver1.4.3(CMSIS V4.1)をターゲットにNEON対応を行ない、処理速度向上を実現しております。
mbed-dspライブラリを使用している場合は、本ライブラリに置き換えて使用することができます。
NEON対応したCMSIS-DSPはライブラリで提供します。
ライブラリ作成環境
NEON対応CMSIS-DSPライブラリは、以下の環境で作成しています。
- コンパイラ
ARMCC Version 5.03 - コンパイルオプションスイッチ[C Compiler]
-DARM_MATH_MATRIX_CHECK -DARM_MATH_ROUNDING -O3 -Otime --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp --vectorize --asm
- コンパイルオプションスイッチ[Assembler]
--cpreproc --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp
NEON対応による効果について
CMSIS-DSP内の各関数へ渡すデータは、小さいサイズよりも大きいサイズの方が効果が見込めます。
また、16の倍数のデータであれば、CMSIS-DSP内のどの関数でも効果が見込めます。
cmsis_dsp/TransformFunctions/arm_rfft_q31.c@3:7a284390b0ce, 2013-11-08 (annotated)
- 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?
User | Revision | Line number | New 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_rfft_q31.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 10 | * Description: RFFT & RIFFT Q31 process function |
emilmont | 1:fdd22bb7aa52 | 11 | * |
emilmont | 1:fdd22bb7aa52 | 12 | * |
emilmont | 1:fdd22bb7aa52 | 13 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
emilmont | 1:fdd22bb7aa52 | 14 | * |
mbed_official | 3:7a284390b0ce | 15 | * Redistribution and use in source and binary forms, with or without |
mbed_official | 3:7a284390b0ce | 16 | * modification, are permitted provided that the following conditions |
mbed_official | 3:7a284390b0ce | 17 | * are met: |
mbed_official | 3:7a284390b0ce | 18 | * - Redistributions of source code must retain the above copyright |
mbed_official | 3:7a284390b0ce | 19 | * notice, this list of conditions and the following disclaimer. |
mbed_official | 3:7a284390b0ce | 20 | * - Redistributions in binary form must reproduce the above copyright |
mbed_official | 3:7a284390b0ce | 21 | * notice, this list of conditions and the following disclaimer in |
mbed_official | 3:7a284390b0ce | 22 | * the documentation and/or other materials provided with the |
mbed_official | 3:7a284390b0ce | 23 | * distribution. |
mbed_official | 3:7a284390b0ce | 24 | * - Neither the name of ARM LIMITED nor the names of its contributors |
mbed_official | 3:7a284390b0ce | 25 | * may be used to endorse or promote products derived from this |
mbed_official | 3:7a284390b0ce | 26 | * software without specific prior written permission. |
mbed_official | 3:7a284390b0ce | 27 | * |
mbed_official | 3:7a284390b0ce | 28 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
mbed_official | 3:7a284390b0ce | 29 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
mbed_official | 3:7a284390b0ce | 30 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
mbed_official | 3:7a284390b0ce | 31 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
mbed_official | 3:7a284390b0ce | 32 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
mbed_official | 3:7a284390b0ce | 33 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
mbed_official | 3:7a284390b0ce | 34 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
mbed_official | 3:7a284390b0ce | 35 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
mbed_official | 3:7a284390b0ce | 36 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
mbed_official | 3:7a284390b0ce | 37 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
mbed_official | 3:7a284390b0ce | 38 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
mbed_official | 3:7a284390b0ce | 39 | * POSSIBILITY OF SUCH DAMAGE. |
emilmont | 1:fdd22bb7aa52 | 40 | * -------------------------------------------------------------------- */ |
emilmont | 1:fdd22bb7aa52 | 41 | |
emilmont | 1:fdd22bb7aa52 | 42 | #include "arm_math.h" |
emilmont | 1:fdd22bb7aa52 | 43 | |
mbed_official | 3:7a284390b0ce | 44 | void arm_radix4_butterfly_inverse_q31( |
mbed_official | 3:7a284390b0ce | 45 | q31_t * pSrc, |
mbed_official | 3:7a284390b0ce | 46 | uint32_t fftLen, |
mbed_official | 3:7a284390b0ce | 47 | q31_t * pCoef, |
mbed_official | 3:7a284390b0ce | 48 | uint32_t twidCoefModifier); |
mbed_official | 3:7a284390b0ce | 49 | |
mbed_official | 3:7a284390b0ce | 50 | void arm_radix4_butterfly_q31( |
mbed_official | 3:7a284390b0ce | 51 | q31_t * pSrc, |
mbed_official | 3:7a284390b0ce | 52 | uint32_t fftLen, |
mbed_official | 3:7a284390b0ce | 53 | q31_t * pCoef, |
mbed_official | 3:7a284390b0ce | 54 | uint32_t twidCoefModifier); |
mbed_official | 3:7a284390b0ce | 55 | |
mbed_official | 3:7a284390b0ce | 56 | void arm_bitreversal_q31( |
mbed_official | 3:7a284390b0ce | 57 | q31_t * pSrc, |
mbed_official | 3:7a284390b0ce | 58 | uint32_t fftLen, |
mbed_official | 3:7a284390b0ce | 59 | uint16_t bitRevFactor, |
mbed_official | 3:7a284390b0ce | 60 | uint16_t * pBitRevTab); |
mbed_official | 3:7a284390b0ce | 61 | |
emilmont | 1:fdd22bb7aa52 | 62 | /*-------------------------------------------------------------------- |
emilmont | 2:da51fb522205 | 63 | * Internal functions prototypes |
emilmont | 1:fdd22bb7aa52 | 64 | --------------------------------------------------------------------*/ |
emilmont | 1:fdd22bb7aa52 | 65 | |
emilmont | 1:fdd22bb7aa52 | 66 | void arm_split_rfft_q31( |
emilmont | 1:fdd22bb7aa52 | 67 | q31_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 68 | uint32_t fftLen, |
emilmont | 1:fdd22bb7aa52 | 69 | q31_t * pATable, |
emilmont | 1:fdd22bb7aa52 | 70 | q31_t * pBTable, |
emilmont | 1:fdd22bb7aa52 | 71 | q31_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 72 | uint32_t modifier); |
emilmont | 1:fdd22bb7aa52 | 73 | |
emilmont | 1:fdd22bb7aa52 | 74 | void arm_split_rifft_q31( |
emilmont | 1:fdd22bb7aa52 | 75 | q31_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 76 | uint32_t fftLen, |
emilmont | 1:fdd22bb7aa52 | 77 | q31_t * pATable, |
emilmont | 1:fdd22bb7aa52 | 78 | q31_t * pBTable, |
emilmont | 1:fdd22bb7aa52 | 79 | q31_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 80 | uint32_t modifier); |
emilmont | 1:fdd22bb7aa52 | 81 | |
emilmont | 1:fdd22bb7aa52 | 82 | /** |
mbed_official | 3:7a284390b0ce | 83 | * @addtogroup RealFFT |
emilmont | 1:fdd22bb7aa52 | 84 | * @{ |
emilmont | 1:fdd22bb7aa52 | 85 | */ |
emilmont | 1:fdd22bb7aa52 | 86 | |
emilmont | 1:fdd22bb7aa52 | 87 | /** |
emilmont | 1:fdd22bb7aa52 | 88 | * @brief Processing function for the Q31 RFFT/RIFFT. |
emilmont | 1:fdd22bb7aa52 | 89 | * @param[in] *S points to an instance of the Q31 RFFT/RIFFT structure. |
emilmont | 1:fdd22bb7aa52 | 90 | * @param[in] *pSrc points to the input buffer. |
emilmont | 1:fdd22bb7aa52 | 91 | * @param[out] *pDst points to the output buffer. |
emilmont | 1:fdd22bb7aa52 | 92 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 93 | * |
emilmont | 1:fdd22bb7aa52 | 94 | * \par Input an output formats: |
emilmont | 1:fdd22bb7aa52 | 95 | * \par |
emilmont | 1:fdd22bb7aa52 | 96 | * Internally input is downscaled by 2 for every stage to avoid saturations inside CFFT/CIFFT process. |
emilmont | 1:fdd22bb7aa52 | 97 | * Hence the output format is different for different RFFT sizes. |
emilmont | 1:fdd22bb7aa52 | 98 | * The input and output formats for different RFFT sizes and number of bits to upscale are mentioned in the tables below for RFFT and RIFFT: |
emilmont | 1:fdd22bb7aa52 | 99 | * \par |
emilmont | 1:fdd22bb7aa52 | 100 | * \image html RFFTQ31.gif "Input and Output Formats for Q31 RFFT" |
emilmont | 1:fdd22bb7aa52 | 101 | * |
emilmont | 1:fdd22bb7aa52 | 102 | * \par |
emilmont | 1:fdd22bb7aa52 | 103 | * \image html RIFFTQ31.gif "Input and Output Formats for Q31 RIFFT" |
emilmont | 1:fdd22bb7aa52 | 104 | */ |
emilmont | 1:fdd22bb7aa52 | 105 | |
emilmont | 1:fdd22bb7aa52 | 106 | void arm_rfft_q31( |
emilmont | 1:fdd22bb7aa52 | 107 | const arm_rfft_instance_q31 * S, |
emilmont | 1:fdd22bb7aa52 | 108 | q31_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 109 | q31_t * pDst) |
emilmont | 1:fdd22bb7aa52 | 110 | { |
emilmont | 1:fdd22bb7aa52 | 111 | const arm_cfft_radix4_instance_q31 *S_CFFT = S->pCfft; |
emilmont | 1:fdd22bb7aa52 | 112 | |
emilmont | 1:fdd22bb7aa52 | 113 | /* Calculation of RIFFT of input */ |
emilmont | 1:fdd22bb7aa52 | 114 | if(S->ifftFlagR == 1u) |
emilmont | 1:fdd22bb7aa52 | 115 | { |
emilmont | 1:fdd22bb7aa52 | 116 | /* Real IFFT core process */ |
emilmont | 1:fdd22bb7aa52 | 117 | arm_split_rifft_q31(pSrc, S->fftLenBy2, S->pTwiddleAReal, |
emilmont | 1:fdd22bb7aa52 | 118 | S->pTwiddleBReal, pDst, S->twidCoefRModifier); |
emilmont | 1:fdd22bb7aa52 | 119 | |
emilmont | 1:fdd22bb7aa52 | 120 | /* Complex readix-4 IFFT process */ |
emilmont | 1:fdd22bb7aa52 | 121 | arm_radix4_butterfly_inverse_q31(pDst, S_CFFT->fftLen, |
emilmont | 1:fdd22bb7aa52 | 122 | S_CFFT->pTwiddle, |
emilmont | 1:fdd22bb7aa52 | 123 | S_CFFT->twidCoefModifier); |
emilmont | 1:fdd22bb7aa52 | 124 | /* Bit reversal process */ |
emilmont | 1:fdd22bb7aa52 | 125 | if(S->bitReverseFlagR == 1u) |
emilmont | 1:fdd22bb7aa52 | 126 | { |
emilmont | 1:fdd22bb7aa52 | 127 | arm_bitreversal_q31(pDst, S_CFFT->fftLen, |
emilmont | 1:fdd22bb7aa52 | 128 | S_CFFT->bitRevFactor, S_CFFT->pBitRevTable); |
emilmont | 1:fdd22bb7aa52 | 129 | } |
emilmont | 1:fdd22bb7aa52 | 130 | } |
emilmont | 1:fdd22bb7aa52 | 131 | else |
emilmont | 1:fdd22bb7aa52 | 132 | { |
emilmont | 1:fdd22bb7aa52 | 133 | /* Calculation of RFFT of input */ |
emilmont | 1:fdd22bb7aa52 | 134 | |
emilmont | 1:fdd22bb7aa52 | 135 | /* Complex readix-4 FFT process */ |
emilmont | 1:fdd22bb7aa52 | 136 | arm_radix4_butterfly_q31(pSrc, S_CFFT->fftLen, |
emilmont | 1:fdd22bb7aa52 | 137 | S_CFFT->pTwiddle, S_CFFT->twidCoefModifier); |
emilmont | 1:fdd22bb7aa52 | 138 | |
emilmont | 1:fdd22bb7aa52 | 139 | /* Bit reversal process */ |
emilmont | 1:fdd22bb7aa52 | 140 | if(S->bitReverseFlagR == 1u) |
emilmont | 1:fdd22bb7aa52 | 141 | { |
emilmont | 1:fdd22bb7aa52 | 142 | arm_bitreversal_q31(pSrc, S_CFFT->fftLen, |
emilmont | 1:fdd22bb7aa52 | 143 | S_CFFT->bitRevFactor, S_CFFT->pBitRevTable); |
emilmont | 1:fdd22bb7aa52 | 144 | } |
emilmont | 1:fdd22bb7aa52 | 145 | |
emilmont | 1:fdd22bb7aa52 | 146 | /* Real FFT core process */ |
emilmont | 1:fdd22bb7aa52 | 147 | arm_split_rfft_q31(pSrc, S->fftLenBy2, S->pTwiddleAReal, |
emilmont | 1:fdd22bb7aa52 | 148 | S->pTwiddleBReal, pDst, S->twidCoefRModifier); |
emilmont | 1:fdd22bb7aa52 | 149 | } |
emilmont | 1:fdd22bb7aa52 | 150 | |
emilmont | 1:fdd22bb7aa52 | 151 | } |
emilmont | 1:fdd22bb7aa52 | 152 | |
emilmont | 1:fdd22bb7aa52 | 153 | |
emilmont | 1:fdd22bb7aa52 | 154 | /** |
mbed_official | 3:7a284390b0ce | 155 | * @} end of RealFFT group |
emilmont | 1:fdd22bb7aa52 | 156 | */ |
emilmont | 1:fdd22bb7aa52 | 157 | |
emilmont | 1:fdd22bb7aa52 | 158 | /** |
emilmont | 1:fdd22bb7aa52 | 159 | * @brief Core Real FFT process |
emilmont | 2:da51fb522205 | 160 | * @param[in] *pSrc points to the input buffer. |
emilmont | 2:da51fb522205 | 161 | * @param[in] fftLen length of FFT. |
emilmont | 2:da51fb522205 | 162 | * @param[in] *pATable points to the twiddle Coef A buffer. |
emilmont | 2:da51fb522205 | 163 | * @param[in] *pBTable points to the twiddle Coef B buffer. |
emilmont | 2:da51fb522205 | 164 | * @param[out] *pDst points to the output buffer. |
emilmont | 2:da51fb522205 | 165 | * @param[in] modifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. |
emilmont | 1:fdd22bb7aa52 | 166 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 167 | */ |
emilmont | 1:fdd22bb7aa52 | 168 | |
emilmont | 1:fdd22bb7aa52 | 169 | void arm_split_rfft_q31( |
emilmont | 1:fdd22bb7aa52 | 170 | q31_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 171 | uint32_t fftLen, |
emilmont | 1:fdd22bb7aa52 | 172 | q31_t * pATable, |
emilmont | 1:fdd22bb7aa52 | 173 | q31_t * pBTable, |
emilmont | 1:fdd22bb7aa52 | 174 | q31_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 175 | uint32_t modifier) |
emilmont | 1:fdd22bb7aa52 | 176 | { |
emilmont | 1:fdd22bb7aa52 | 177 | uint32_t i; /* Loop Counter */ |
emilmont | 1:fdd22bb7aa52 | 178 | q31_t outR, outI; /* Temporary variables for output */ |
emilmont | 1:fdd22bb7aa52 | 179 | q31_t *pCoefA, *pCoefB; /* Temporary pointers for twiddle factors */ |
emilmont | 1:fdd22bb7aa52 | 180 | q31_t CoefA1, CoefA2, CoefB1; /* Temporary variables for twiddle coefficients */ |
emilmont | 1:fdd22bb7aa52 | 181 | q31_t *pOut1 = &pDst[2], *pOut2 = &pDst[(4u * fftLen) - 1u]; |
emilmont | 1:fdd22bb7aa52 | 182 | q31_t *pIn1 = &pSrc[2], *pIn2 = &pSrc[(2u * fftLen) - 1u]; |
emilmont | 1:fdd22bb7aa52 | 183 | |
emilmont | 1:fdd22bb7aa52 | 184 | /* Init coefficient pointers */ |
emilmont | 1:fdd22bb7aa52 | 185 | pCoefA = &pATable[modifier * 2u]; |
emilmont | 1:fdd22bb7aa52 | 186 | pCoefB = &pBTable[modifier * 2u]; |
emilmont | 1:fdd22bb7aa52 | 187 | |
emilmont | 1:fdd22bb7aa52 | 188 | i = fftLen - 1u; |
emilmont | 1:fdd22bb7aa52 | 189 | |
emilmont | 1:fdd22bb7aa52 | 190 | while(i > 0u) |
emilmont | 1:fdd22bb7aa52 | 191 | { |
emilmont | 1:fdd22bb7aa52 | 192 | /* |
emilmont | 1:fdd22bb7aa52 | 193 | outR = (pSrc[2 * i] * pATable[2 * i] - pSrc[2 * i + 1] * pATable[2 * i + 1] |
emilmont | 1:fdd22bb7aa52 | 194 | + pSrc[2 * n - 2 * i] * pBTable[2 * i] + |
emilmont | 1:fdd22bb7aa52 | 195 | pSrc[2 * n - 2 * i + 1] * pBTable[2 * i + 1]); |
emilmont | 1:fdd22bb7aa52 | 196 | */ |
emilmont | 1:fdd22bb7aa52 | 197 | |
emilmont | 1:fdd22bb7aa52 | 198 | /* outI = (pIn[2 * i + 1] * pATable[2 * i] + pIn[2 * i] * pATable[2 * i + 1] + |
emilmont | 1:fdd22bb7aa52 | 199 | pIn[2 * n - 2 * i] * pBTable[2 * i + 1] - |
emilmont | 1:fdd22bb7aa52 | 200 | pIn[2 * n - 2 * i + 1] * pBTable[2 * i]); */ |
emilmont | 1:fdd22bb7aa52 | 201 | |
emilmont | 1:fdd22bb7aa52 | 202 | CoefA1 = *pCoefA++; |
emilmont | 1:fdd22bb7aa52 | 203 | CoefA2 = *pCoefA; |
emilmont | 1:fdd22bb7aa52 | 204 | |
emilmont | 1:fdd22bb7aa52 | 205 | /* outR = (pSrc[2 * i] * pATable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 206 | outR = ((int32_t) (((q63_t) * pIn1 * CoefA1) >> 32)); |
emilmont | 1:fdd22bb7aa52 | 207 | |
emilmont | 1:fdd22bb7aa52 | 208 | /* outI = pIn[2 * i] * pATable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 209 | outI = ((int32_t) (((q63_t) * pIn1++ * CoefA2) >> 32)); |
emilmont | 1:fdd22bb7aa52 | 210 | |
emilmont | 1:fdd22bb7aa52 | 211 | /* - pSrc[2 * i + 1] * pATable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 212 | outR = |
emilmont | 1:fdd22bb7aa52 | 213 | (q31_t) ((((q63_t) outR << 32) + ((q63_t) * pIn1 * (-CoefA2))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 214 | |
emilmont | 1:fdd22bb7aa52 | 215 | /* (pIn[2 * i + 1] * pATable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 216 | outI = |
emilmont | 1:fdd22bb7aa52 | 217 | (q31_t) ((((q63_t) outI << 32) + ((q63_t) * pIn1++ * (CoefA1))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 218 | |
emilmont | 1:fdd22bb7aa52 | 219 | /* pSrc[2 * n - 2 * i] * pBTable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 220 | outR = |
emilmont | 1:fdd22bb7aa52 | 221 | (q31_t) ((((q63_t) outR << 32) + ((q63_t) * pIn2 * (-CoefA2))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 222 | CoefB1 = *pCoefB; |
emilmont | 1:fdd22bb7aa52 | 223 | |
emilmont | 1:fdd22bb7aa52 | 224 | /* pIn[2 * n - 2 * i] * pBTable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 225 | outI = |
emilmont | 1:fdd22bb7aa52 | 226 | (q31_t) ((((q63_t) outI << 32) + ((q63_t) * pIn2-- * (-CoefB1))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 227 | |
emilmont | 1:fdd22bb7aa52 | 228 | /* pSrc[2 * n - 2 * i + 1] * pBTable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 229 | outR = |
emilmont | 1:fdd22bb7aa52 | 230 | (q31_t) ((((q63_t) outR << 32) + ((q63_t) * pIn2 * (CoefB1))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 231 | |
emilmont | 1:fdd22bb7aa52 | 232 | /* pIn[2 * n - 2 * i + 1] * pBTable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 233 | outI = |
emilmont | 1:fdd22bb7aa52 | 234 | (q31_t) ((((q63_t) outI << 32) + ((q63_t) * pIn2-- * (-CoefA2))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 235 | |
emilmont | 1:fdd22bb7aa52 | 236 | /* write output */ |
emilmont | 1:fdd22bb7aa52 | 237 | *pOut1++ = (outR << 1u); |
emilmont | 1:fdd22bb7aa52 | 238 | *pOut1++ = (outI << 1u); |
emilmont | 1:fdd22bb7aa52 | 239 | |
emilmont | 1:fdd22bb7aa52 | 240 | /* write complex conjugate output */ |
emilmont | 1:fdd22bb7aa52 | 241 | *pOut2-- = -(outI << 1u); |
emilmont | 1:fdd22bb7aa52 | 242 | *pOut2-- = (outR << 1u); |
emilmont | 1:fdd22bb7aa52 | 243 | |
emilmont | 1:fdd22bb7aa52 | 244 | /* update coefficient pointer */ |
emilmont | 1:fdd22bb7aa52 | 245 | pCoefB = pCoefB + (modifier * 2u); |
emilmont | 1:fdd22bb7aa52 | 246 | pCoefA = pCoefA + ((modifier * 2u) - 1u); |
emilmont | 1:fdd22bb7aa52 | 247 | |
emilmont | 1:fdd22bb7aa52 | 248 | i--; |
emilmont | 1:fdd22bb7aa52 | 249 | |
emilmont | 1:fdd22bb7aa52 | 250 | } |
emilmont | 1:fdd22bb7aa52 | 251 | |
emilmont | 1:fdd22bb7aa52 | 252 | pDst[2u * fftLen] = pSrc[0] - pSrc[1]; |
emilmont | 1:fdd22bb7aa52 | 253 | pDst[(2u * fftLen) + 1u] = 0; |
emilmont | 1:fdd22bb7aa52 | 254 | |
emilmont | 1:fdd22bb7aa52 | 255 | pDst[0] = pSrc[0] + pSrc[1]; |
emilmont | 1:fdd22bb7aa52 | 256 | pDst[1] = 0; |
emilmont | 1:fdd22bb7aa52 | 257 | |
emilmont | 1:fdd22bb7aa52 | 258 | } |
emilmont | 1:fdd22bb7aa52 | 259 | |
emilmont | 1:fdd22bb7aa52 | 260 | |
emilmont | 1:fdd22bb7aa52 | 261 | /** |
emilmont | 1:fdd22bb7aa52 | 262 | * @brief Core Real IFFT process |
emilmont | 2:da51fb522205 | 263 | * @param[in] *pSrc points to the input buffer. |
emilmont | 2:da51fb522205 | 264 | * @param[in] fftLen length of FFT. |
emilmont | 2:da51fb522205 | 265 | * @param[in] *pATable points to the twiddle Coef A buffer. |
emilmont | 2:da51fb522205 | 266 | * @param[in] *pBTable points to the twiddle Coef B buffer. |
emilmont | 2:da51fb522205 | 267 | * @param[out] *pDst points to the output buffer. |
emilmont | 2:da51fb522205 | 268 | * @param[in] modifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. |
emilmont | 1:fdd22bb7aa52 | 269 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 270 | */ |
emilmont | 1:fdd22bb7aa52 | 271 | |
emilmont | 1:fdd22bb7aa52 | 272 | void arm_split_rifft_q31( |
emilmont | 1:fdd22bb7aa52 | 273 | q31_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 274 | uint32_t fftLen, |
emilmont | 1:fdd22bb7aa52 | 275 | q31_t * pATable, |
emilmont | 1:fdd22bb7aa52 | 276 | q31_t * pBTable, |
emilmont | 1:fdd22bb7aa52 | 277 | q31_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 278 | uint32_t modifier) |
emilmont | 1:fdd22bb7aa52 | 279 | { |
emilmont | 1:fdd22bb7aa52 | 280 | q31_t outR, outI; /* Temporary variables for output */ |
emilmont | 1:fdd22bb7aa52 | 281 | q31_t *pCoefA, *pCoefB; /* Temporary pointers for twiddle factors */ |
emilmont | 1:fdd22bb7aa52 | 282 | q31_t CoefA1, CoefA2, CoefB1; /* Temporary variables for twiddle coefficients */ |
emilmont | 1:fdd22bb7aa52 | 283 | q31_t *pIn1 = &pSrc[0], *pIn2 = &pSrc[(2u * fftLen) + 1u]; |
emilmont | 1:fdd22bb7aa52 | 284 | |
emilmont | 1:fdd22bb7aa52 | 285 | pCoefA = &pATable[0]; |
emilmont | 1:fdd22bb7aa52 | 286 | pCoefB = &pBTable[0]; |
emilmont | 1:fdd22bb7aa52 | 287 | |
emilmont | 1:fdd22bb7aa52 | 288 | while(fftLen > 0u) |
emilmont | 1:fdd22bb7aa52 | 289 | { |
emilmont | 1:fdd22bb7aa52 | 290 | /* |
emilmont | 1:fdd22bb7aa52 | 291 | outR = (pIn[2 * i] * pATable[2 * i] + pIn[2 * i + 1] * pATable[2 * i + 1] + |
emilmont | 1:fdd22bb7aa52 | 292 | pIn[2 * n - 2 * i] * pBTable[2 * i] - |
emilmont | 1:fdd22bb7aa52 | 293 | pIn[2 * n - 2 * i + 1] * pBTable[2 * i + 1]); |
emilmont | 1:fdd22bb7aa52 | 294 | |
emilmont | 1:fdd22bb7aa52 | 295 | outI = (pIn[2 * i + 1] * pATable[2 * i] - pIn[2 * i] * pATable[2 * i + 1] - |
emilmont | 1:fdd22bb7aa52 | 296 | pIn[2 * n - 2 * i] * pBTable[2 * i + 1] - |
emilmont | 1:fdd22bb7aa52 | 297 | pIn[2 * n - 2 * i + 1] * pBTable[2 * i]); |
emilmont | 1:fdd22bb7aa52 | 298 | |
emilmont | 1:fdd22bb7aa52 | 299 | */ |
emilmont | 1:fdd22bb7aa52 | 300 | CoefA1 = *pCoefA++; |
emilmont | 1:fdd22bb7aa52 | 301 | CoefA2 = *pCoefA; |
emilmont | 1:fdd22bb7aa52 | 302 | |
emilmont | 1:fdd22bb7aa52 | 303 | /* outR = (pIn[2 * i] * pATable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 304 | outR = ((int32_t) (((q63_t) * pIn1 * CoefA1) >> 32)); |
emilmont | 1:fdd22bb7aa52 | 305 | |
emilmont | 1:fdd22bb7aa52 | 306 | /* - pIn[2 * i] * pATable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 307 | outI = -((int32_t) (((q63_t) * pIn1++ * CoefA2) >> 32)); |
emilmont | 1:fdd22bb7aa52 | 308 | |
emilmont | 1:fdd22bb7aa52 | 309 | /* pIn[2 * i + 1] * pATable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 310 | outR = |
emilmont | 1:fdd22bb7aa52 | 311 | (q31_t) ((((q63_t) outR << 32) + ((q63_t) * pIn1 * (CoefA2))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 312 | |
emilmont | 1:fdd22bb7aa52 | 313 | /* pIn[2 * i + 1] * pATable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 314 | outI = |
emilmont | 1:fdd22bb7aa52 | 315 | (q31_t) ((((q63_t) outI << 32) + ((q63_t) * pIn1++ * (CoefA1))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 316 | |
emilmont | 1:fdd22bb7aa52 | 317 | /* pIn[2 * n - 2 * i] * pBTable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 318 | outR = |
emilmont | 1:fdd22bb7aa52 | 319 | (q31_t) ((((q63_t) outR << 32) + ((q63_t) * pIn2 * (CoefA2))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 320 | |
emilmont | 1:fdd22bb7aa52 | 321 | CoefB1 = *pCoefB; |
emilmont | 1:fdd22bb7aa52 | 322 | |
emilmont | 1:fdd22bb7aa52 | 323 | /* pIn[2 * n - 2 * i] * pBTable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 324 | outI = |
emilmont | 1:fdd22bb7aa52 | 325 | (q31_t) ((((q63_t) outI << 32) - ((q63_t) * pIn2-- * (CoefB1))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 326 | |
emilmont | 1:fdd22bb7aa52 | 327 | /* pIn[2 * n - 2 * i + 1] * pBTable[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 328 | outR = |
emilmont | 1:fdd22bb7aa52 | 329 | (q31_t) ((((q63_t) outR << 32) + ((q63_t) * pIn2 * (CoefB1))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 330 | |
emilmont | 1:fdd22bb7aa52 | 331 | /* pIn[2 * n - 2 * i + 1] * pBTable[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 332 | outI = |
emilmont | 1:fdd22bb7aa52 | 333 | (q31_t) ((((q63_t) outI << 32) + ((q63_t) * pIn2-- * (CoefA2))) >> 32); |
emilmont | 1:fdd22bb7aa52 | 334 | |
emilmont | 1:fdd22bb7aa52 | 335 | /* write output */ |
emilmont | 1:fdd22bb7aa52 | 336 | *pDst++ = (outR << 1u); |
emilmont | 1:fdd22bb7aa52 | 337 | *pDst++ = (outI << 1u); |
emilmont | 1:fdd22bb7aa52 | 338 | |
emilmont | 1:fdd22bb7aa52 | 339 | /* update coefficient pointer */ |
emilmont | 1:fdd22bb7aa52 | 340 | pCoefB = pCoefB + (modifier * 2u); |
emilmont | 1:fdd22bb7aa52 | 341 | pCoefA = pCoefA + ((modifier * 2u) - 1u); |
emilmont | 1:fdd22bb7aa52 | 342 | |
emilmont | 1:fdd22bb7aa52 | 343 | /* Decrement loop count */ |
emilmont | 1:fdd22bb7aa52 | 344 | fftLen--; |
emilmont | 1:fdd22bb7aa52 | 345 | |
emilmont | 1:fdd22bb7aa52 | 346 | } |
emilmont | 1:fdd22bb7aa52 | 347 | |
emilmont | 1:fdd22bb7aa52 | 348 | |
emilmont | 1:fdd22bb7aa52 | 349 | } |