##// END OF EJS Templates
HG_REPOSITORIES » LPP » INSTRUMENTATION » libuc2
RSS

Clone from http://pc-instru.lpp.polytechnique.fr:5000/libuc2

Added Oplayer BSP, Fixed bug on GPIO library(gpiosetval change all the port...
Added Oplayer BSP, Fixed bug on GPIO library(gpiosetval change all the port instead of the desired bit).
jeandet@pc-de-jeandet3.LAB-LPP.LOCAL - - Load All Authors

File last commit:

r41:27c5438a4566 dev_alexis
r60:17402611bd25 dev_alexis
Show More
arm_cmplx_dot_prod_f32.c
157 lines | 4.8 KiB | text/x-c | CLexer
/ lib / src / stm32f4 / CPU / CMSIS / DSP_Lib / Source / ComplexMathFunctions / arm_cmplx_dot_prod_f32.c
History | Source | Raw |Copy content |Copy permalink
jeandet@pc-de-jeandet3.LAB-LPP.LOCAL
Added ARM CMSIS for fast math and circle drawing function for ili9328 driver.
 r41 /* ----------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. July 2011
* $Revision: V1.0.10
*
* Project: CMSIS DSP Library
* Title: arm_cmplx_dot_prod_f32.c
*
* Description: Floating-point complex dot product
*
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*
* Version 1.0.10 2011/7/15
* Big Endian support added and Merged M0 and M3/M4 Source code.
*
* Version 1.0.3 2010/11/29
* Re-organized the CMSIS folders and updated documentation.
*
* Version 1.0.2 2010/11/11
* Documentation updated.
*
* Version 1.0.1 2010/10/05
* Production release and review comments incorporated.
*
* Version 1.0.0 2010/09/20
* Production release and review comments incorporated.
* ---------------------------------------------------------------------------- */
#include "arm_math.h"
/**
* @ingroup groupCmplxMath
*/
/**
* @defgroup cmplx_dot_prod Complex Dot Product
*
* Computes the dot product of two complex vectors.
* The vectors are multiplied element-by-element and then summed.
*
* The <code>pSrcA</code> points to the first complex input vector and
* <code>pSrcB</code> points to the second complex input vector.
* <code>numSamples</code> specifies the number of complex samples
* and the data in each array is stored in an interleaved fashion
* (real, imag, real, imag, ...).
* Each array has a total of <code>2*numSamples</code> values.
*
* The underlying algorithm is used:
* <pre>
* realResult=0;
* imagResult=0;
* for(n=0; n<numSamples; n++) {
* realResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+0] - pSrcA[(2*n)+1]*pSrcB[(2*n)+1];
* imagResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+1] + pSrcA[(2*n)+1]*pSrcB[(2*n)+0];
* }
* </pre>
*
* There are separate functions for floating-point, Q15, and Q31 data types.
*/
/**
* @addtogroup cmplx_dot_prod
* @{
*/
/**
* @brief Floating-point complex dot product
* @param *pSrcA points to the first input vector
* @param *pSrcB points to the second input vector
* @param numSamples number of complex samples in each vector
* @param *realResult real part of the result returned here
* @param *imagResult imaginary part of the result returned here
* @return none.
*/
void arm_cmplx_dot_prod_f32(
float32_t * pSrcA,
float32_t * pSrcB,
uint32_t numSamples,
float32_t * realResult,
float32_t * imagResult)
{
float32_t real_sum = 0.0f, imag_sum = 0.0f; /* Temporary result storage */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
uint32_t blkCnt; /* loop counter */
/*loop Unrolling */
blkCnt = numSamples >> 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)
{
/* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
real_sum += (*pSrcA++) * (*pSrcB++);
/* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
imag_sum += (*pSrcA++) * (*pSrcB++);
real_sum += (*pSrcA++) * (*pSrcB++);
imag_sum += (*pSrcA++) * (*pSrcB++);
real_sum += (*pSrcA++) * (*pSrcB++);
imag_sum += (*pSrcA++) * (*pSrcB++);
real_sum += (*pSrcA++) * (*pSrcB++);
imag_sum += (*pSrcA++) * (*pSrcB++);
/* Decrement the loop counter */
blkCnt--;
}
/* If the numSamples is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = numSamples % 0x4u;
while(blkCnt > 0u)
{
/* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
real_sum += (*pSrcA++) * (*pSrcB++);
/* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
imag_sum += (*pSrcA++) * (*pSrcB++);
/* Decrement the loop counter */
blkCnt--;
}
#else
/* Run the below code for Cortex-M0 */
while(numSamples > 0u)
{
/* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
real_sum += (*pSrcA++) * (*pSrcB++);
/* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
imag_sum += (*pSrcA++) * (*pSrcB++);
/* Decrement the loop counter */
numSamples--;
}
#endif /* #ifndef ARM_MATH_CM0 */
/* Store the real and imaginary results in the destination buffers */
*realResult = real_sum;
*imagResult = imag_sum;
}
/**
* @} end of cmplx_dot_prod group
*/