121 lines
3.1 KiB
C
121 lines
3.1 KiB
C
/* ----------------------------------------------------------------------
|
|
* Project: CMSIS DSP Library
|
|
* Title: arm_dot_prod_f32.c
|
|
* Description: Floating-point dot product
|
|
*
|
|
* $Date: 18. March 2019
|
|
* $Revision: V1.6.0
|
|
*
|
|
* Target Processor: Cortex-M cores
|
|
* -------------------------------------------------------------------- */
|
|
/*
|
|
* Copyright (C) 2010-2019 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 "arm_math.h"
|
|
|
|
/**
|
|
@ingroup groupMath
|
|
*/
|
|
|
|
/**
|
|
@defgroup BasicDotProd Vector Dot Product
|
|
|
|
Computes the dot product of two vectors.
|
|
The vectors are multiplied element-by-element and then summed.
|
|
|
|
<pre>
|
|
sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
|
|
</pre>
|
|
|
|
There are separate functions for floating-point, Q7, Q15, and Q31 data types.
|
|
*/
|
|
|
|
/**
|
|
@addtogroup BasicDotProd
|
|
@{
|
|
*/
|
|
|
|
/**
|
|
@brief Dot product of floating-point vectors.
|
|
@param[in] pSrcA points to the first input vector.
|
|
@param[in] pSrcB points to the second input vector.
|
|
@param[in] blockSize number of samples in each vector.
|
|
@param[out] result output result returned here.
|
|
@return none
|
|
*/
|
|
|
|
void arm_dot_prod_f32(
|
|
const float32_t * pSrcA,
|
|
const float32_t * pSrcB,
|
|
uint32_t blockSize,
|
|
float32_t * result)
|
|
{
|
|
uint32_t blkCnt; /* Loop counter */
|
|
float32_t sum = 0.0f; /* Temporary return variable */
|
|
|
|
#if defined (ARM_MATH_LOOPUNROLL)
|
|
|
|
/* Loop unrolling: Compute 4 outputs at a time */
|
|
blkCnt = blockSize >> 2U;
|
|
|
|
while (blkCnt > 0U)
|
|
{
|
|
/* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
|
|
|
|
/* Calculate dot product and store result in a temporary buffer. */
|
|
sum += (*pSrcA++) * (*pSrcB++);
|
|
|
|
sum += (*pSrcA++) * (*pSrcB++);
|
|
|
|
sum += (*pSrcA++) * (*pSrcB++);
|
|
|
|
sum += (*pSrcA++) * (*pSrcB++);
|
|
|
|
/* 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[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
|
|
|
|
/* Calculate dot product and store result in a temporary buffer. */
|
|
sum += (*pSrcA++) * (*pSrcB++);
|
|
|
|
/* Decrement loop counter */
|
|
blkCnt--;
|
|
}
|
|
|
|
/* Store result in destination buffer */
|
|
*result = sum;
|
|
}
|
|
|
|
/**
|
|
@} end of BasicDotProd group
|
|
*/
|