<<<<<<< HEAD
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_mult_f32.c
* Description: Floating-point 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 "dsp/basic_math_functions.h"
/**
@ingroup groupMath
*/
/**
@defgroup BasicMult Vector Multiplication
Element-by-element multiplication of two vectors.
pDst[n] = pSrcA[n] * pSrcB[n], 0 <= n < blockSize.
There are separate functions for floating-point, Q7, Q15, and Q31 data types.
*/
/**
@addtogroup BasicMult
@{
*/
/**
@brief Floating-point 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
*/
#if defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE)
#include "arm_helium_utils.h"
void arm_mult_f32(
const float32_t * pSrcA,
const float32_t * pSrcB,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* Loop counter */
f32x4_t vec1;
f32x4_t vec2;
f32x4_t res;
/* Compute 4 outputs at a time */
blkCnt = blockSize >> 2U;
while (blkCnt > 0U)
{
/* C = A + B */
/* Add and then store the results in the destination buffer. */
vec1 = vld1q(pSrcA);
vec2 = vld1q(pSrcB);
res = vmulq(vec1, vec2);
vst1q(pDst, res);
/* Increment pointers */
pSrcA += 4;
pSrcB += 4;
pDst += 4;
/* Decrement the loop counter */
blkCnt--;
}
/* Tail */
blkCnt = blockSize & 0x3;
if (blkCnt > 0U)
{
/* C = A + B */
mve_pred16_t p0 = vctp32q(blkCnt);
vec1 = vld1q(pSrcA);
vec2 = vld1q(pSrcB);
vstrwq_p(pDst, vmulq(vec1,vec2), p0);
}
}
#else
void arm_mult_f32(
const float32_t * pSrcA,
const float32_t * pSrcB,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* Loop counter */
#if defined(ARM_MATH_NEON) && !defined(ARM_MATH_AUTOVECTORIZE)
f32x4_t vec1;
f32x4_t vec2;
f32x4_t res;
/* Compute 4 outputs at a time */
blkCnt = blockSize >> 2U;
while (blkCnt > 0U)
{
/* C = A * B */
/* Multiply the inputs and then store the results in the destination buffer. */
vec1 = vld1q_f32(pSrcA);
vec2 = vld1q_f32(pSrcB);
res = vmulq_f32(vec1, vec2);
vst1q_f32(pDst, res);
/* Increment pointers */
pSrcA += 4;
pSrcB += 4;
pDst += 4;
/* Decrement the loop counter */
blkCnt--;
}
/* Tail */
blkCnt = blockSize & 0x3;
#else
#if defined (ARM_MATH_LOOPUNROLL) && !defined(ARM_MATH_AUTOVECTORIZE)
/* Loop unrolling: Compute 4 outputs at a time */
blkCnt = blockSize >> 2U;
while (blkCnt > 0U)
{
/* C = A * B */
/* Multiply inputs and store result in destination buffer. */
*pDst++ = (*pSrcA++) * (*pSrcB++);
*pDst++ = (*pSrcA++) * (*pSrcB++);
*pDst++ = (*pSrcA++) * (*pSrcB++);
*pDst++ = (*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) */
#endif /* #if defined(ARM_MATH_NEON) */
while (blkCnt > 0U)
{
/* C = A * B */
/* Multiply input and store result in destination buffer. */
*pDst++ = (*pSrcA++) * (*pSrcB++);
/* Decrement loop counter */
blkCnt--;
}
}
#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
/**
@} end of BasicMult group
*/
=======
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_mult_f32.c
* Description: Floating-point vector multiplication
*
* $Date: 27. January 2017
* $Revision: V.1.5.1
*
* Target Processor: Cortex-M cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2017 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 BasicMult Vector Multiplication
*
* Element-by-element multiplication of two vectors.
*
*
* pDst[n] = pSrcA[n] * pSrcB[n], 0 <= n < blockSize.
*
*
* There are separate functions for floating-point, Q7, Q15, and Q31 data types.
*/
/**
* @addtogroup BasicMult
* @{
*/
/**
* @brief Floating-point 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.
*/
void arm_mult_f32(
float32_t * pSrcA,
float32_t * pSrcB,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counters */
#if defined (ARM_MATH_DSP)
/* Run the below code for Cortex-M4 and Cortex-M3 */
float32_t inA1, inA2, inA3, inA4; /* temporary input variables */
float32_t inB1, inB2, inB3, inB4; /* temporary input variables */
float32_t out1, out2, out3, out4; /* temporary output variables */
/* loop Unrolling */
blkCnt = blockSize >> 2U;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while (blkCnt > 0U)
{
/* C = A * B */
/* Multiply the inputs and store the results in output buffer */
/* read sample from sourceA */
inA1 = *pSrcA;
/* read sample from sourceB */
inB1 = *pSrcB;
/* read sample from sourceA */
inA2 = *(pSrcA + 1);
/* read sample from sourceB */
inB2 = *(pSrcB + 1);
/* out = sourceA * sourceB */
out1 = inA1 * inB1;
/* read sample from sourceA */
inA3 = *(pSrcA + 2);
/* read sample from sourceB */
inB3 = *(pSrcB + 2);
/* out = sourceA * sourceB */
out2 = inA2 * inB2;
/* read sample from sourceA */
inA4 = *(pSrcA + 3);
/* store result to destination buffer */
*pDst = out1;
/* read sample from sourceB */
inB4 = *(pSrcB + 3);
/* out = sourceA * sourceB */
out3 = inA3 * inB3;
/* store result to destination buffer */
*(pDst + 1) = out2;
/* out = sourceA * sourceB */
out4 = inA4 * inB4;
/* store result to destination buffer */
*(pDst + 2) = out3;
/* store result to destination buffer */
*(pDst + 3) = out4;
/* update pointers to process next samples */
pSrcA += 4U;
pSrcB += 4U;
pDst += 4U;
/* Decrement the blockSize loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4U;
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif /* #if defined (ARM_MATH_DSP) */
while (blkCnt > 0U)
{
/* C = A * B */
/* Multiply the inputs and store the results in output buffer */
*pDst++ = (*pSrcA++) * (*pSrcB++);
/* Decrement the blockSize loop counter */
blkCnt--;
}
}
/**
* @} end of BasicMult group
*/
>>>>>>> upper