File size: 4,803 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 | #include "edge-impulse-sdk/dsp/config.hpp"
#if EIDSP_LOAD_CMSIS_DSP_SOURCES
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_mult_q7.c
* Description: Q7 vector multiplication
*
* $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/basic_math_functions.h"
/**
@ingroup groupMath
*/
/**
@addtogroup BasicMult
@{
*/
/**
@brief Q7 vector multiplication
@param[in] pSrcA points to the first input vector
@param[in] pSrcB points to the second input vector
@param[out] pDst points to the output vector
@param[in] blockSize number of samples in each vector
@return none
@par Scaling and Overflow Behavior
The function uses saturating arithmetic.
Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
*/
#if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE)
#include "edge-impulse-sdk/CMSIS/DSP/Include/arm_helium_utils.h"
void arm_mult_q7(
const q7_t * pSrcA,
const q7_t * pSrcB,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counters */
q7x16_t vecA, vecB;
/* Compute 16 outputs at a time */
blkCnt = blockSize >> 4;
while (blkCnt > 0U)
{
/*
* C = A * B
* Multiply the inputs and then store the results in the destination buffer.
*/
vecA = vld1q(pSrcA);
vecB = vld1q(pSrcB);
vst1q(pDst, vqdmulhq(vecA, vecB));
/*
* Decrement the blockSize loop counter
*/
blkCnt--;
/*
* advance vector source and destination pointers
*/
pSrcA += 16;
pSrcB += 16;
pDst += 16;
}
/*
* tail
*/
blkCnt = blockSize & 0xF;
if (blkCnt > 0U)
{
mve_pred16_t p0 = vctp8q(blkCnt);
vecA = vld1q(pSrcA);
vecB = vld1q(pSrcB);
vstrbq_p(pDst, vqdmulhq(vecA, vecB), p0);
}
}
#else
void arm_mult_q7(
const q7_t * pSrcA,
const q7_t * pSrcB,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* Loop counter */
#if defined (ARM_MATH_LOOPUNROLL)
#if defined (ARM_MATH_DSP)
q7_t out1, out2, out3, out4; /* Temporary output variables */
#endif
/* Loop unrolling: Compute 4 outputs at a time */
blkCnt = blockSize >> 2U;
while (blkCnt > 0U)
{
/* C = A * B */
#if defined (ARM_MATH_DSP)
/* Multiply inputs and store results in temporary variables */
out1 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
out2 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
out3 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
out4 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
/* Pack and store result in destination buffer (in single write) */
write_q7x4_ia (&pDst, __PACKq7(out1, out2, out3, out4));
#else
*pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
*pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
*pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
*pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
#endif
/* Decrement loop counter */
blkCnt--;
}
/* Loop unrolling: Compute remaining outputs */
blkCnt = blockSize % 0x4U;
#else
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
while (blkCnt > 0U)
{
/* C = A * B */
/* Multiply input and store result in destination buffer. */
*pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
/* Decrement loop counter */
blkCnt--;
}
}
#endif /* defined(ARM_MATH_MVEI) */
/**
@} end of BasicMult group
*/
#endif // EIDSP_LOAD_CMSIS_DSP_SOURCES
|