File size: 3,938 Bytes
25ade36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 | #include "edge-impulse-sdk/dsp/config.hpp"
#if EIDSP_LOAD_CMSIS_DSP_SOURCES
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_cmplx_mag_squared_f16.c
* Description: Floating-point complex magnitude squared
*
* $Date: 23 April 2021
* $Revision: V1.9.0
*
* Target Processor: Cortex-M and Cortex-A cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2021 ARM Limited or its affiliates. All rights reserved.
*
* SPDX-License-Identifier: Apache-2.0
*
* Licensed under the Apache License, Version 2.0 (the License); you may
* not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an AS IS BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include "edge-impulse-sdk/CMSIS/DSP/Include/dsp/complex_math_functions_f16.h"
#if defined(ARM_FLOAT16_SUPPORTED)
/**
@ingroup groupCmplxMath
*/
/**
@addtogroup cmplx_mag_squared
@{
*/
/**
@brief Floating-point complex magnitude squared.
@param[in] pSrc points to input vector
@param[out] pDst points to output vector
@param[in] numSamples number of samples in each vector
@return none
*/
#if defined(ARM_MATH_MVE_FLOAT16) && !defined(ARM_MATH_AUTOVECTORIZE)
void arm_cmplx_mag_squared_f16(
const float16_t * pSrc,
float16_t * pDst,
uint32_t numSamples)
{
int32_t blockSize = numSamples; /* loop counters */
f16x8x2_t vecSrc;
f16x8_t sum;
/* Compute 4 complex samples at a time */
while (blockSize > 0)
{
mve_pred16_t p = vctp16q(blockSize);
vecSrc = vld2q(pSrc);
sum = vmulq_m(vuninitializedq_f16(),vecSrc.val[0], vecSrc.val[0],p);
sum = vfmaq_m(sum, vecSrc.val[1], vecSrc.val[1],p);
vstrhq_p_f16(pDst, sum,p);
pSrc += 16;
pDst += 8;
/*
* Decrement the blockSize loop counter
*/
blockSize-= 8;
}
}
#else
void arm_cmplx_mag_squared_f16(
const float16_t * pSrc,
float16_t * pDst,
uint32_t numSamples)
{
uint32_t blkCnt; /* Loop counter */
_Float16 real, imag; /* Temporary input variables */
#if defined (ARM_MATH_LOOPUNROLL) && !defined(ARM_MATH_AUTOVECTORIZE)
/* Loop unrolling: Compute 4 outputs at a time */
blkCnt = numSamples >> 2U;
while (blkCnt > 0U)
{
/* C[0] = (A[0] * A[0] + A[1] * A[1]) */
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
/* Decrement loop counter */
blkCnt--;
}
/* Loop unrolling: Compute remaining outputs */
blkCnt = numSamples % 0x4U;
#else
/* Initialize blkCnt with number of samples */
blkCnt = numSamples;
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
while (blkCnt > 0U)
{
/* C[0] = (A[0] * A[0] + A[1] * A[1]) */
real = *pSrc++;
imag = *pSrc++;
/* store result in destination buffer. */
*pDst++ = (real * real) + (imag * imag);
/* Decrement loop counter */
blkCnt--;
}
}
#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
/**
@} end of cmplx_mag_squared group
*/
#endif /* #if defined(ARM_FLOAT16_SUPPORTED) */
#endif // EIDSP_LOAD_CMSIS_DSP_SOURCES
|