arm_dot_prod_f32.c

00001 /* ----------------------------------------------------------------------  
00002 * Copyright (C) 2010 ARM Limited. All rights reserved.  
00003 *  
00004 * $Date:        29. November 2010  
00005 * $Revision:    V1.0.3  
00006 *  
00007 * Project:      CMSIS DSP Library  
00008 * Title:        arm_dot_prod_f32.c  
00009 *  
00010 * Description:  Floating-point dot product.  
00011 *  
00012 * Target Processor: Cortex-M4/Cortex-M3
00013 *  
00014 * Version 1.0.3 2010/11/29 
00015 *    Re-organized the CMSIS folders and updated documentation.  
00016 *   
00017 * Version 1.0.2 2010/11/11  
00018 *    Documentation updated.   
00019 *  
00020 * Version 1.0.1 2010/10/05   
00021 *    Production release and review comments incorporated.  
00022 *  
00023 * Version 1.0.0 2010/09/20   
00024 *    Production release and review comments incorporated.  
00025 *  
00026 * Version 0.0.7  2010/06/10   
00027 *    Misra-C changes done  
00028 * ---------------------------------------------------------------------------- */ 
00029  
00030 #include "arm_math.h" 
00031  
00032 /**  
00033  * @ingroup groupMath  
00034  */ 
00035  
00036 /**  
00037  * @defgroup dot_prod Vector Dot Product  
00038  *  
00039  * Computes the dot product of two vectors.  
00040  * The vectors are multiplied element-by-element and then summed.  
00041  * There are separate functions for floating-point, Q7, Q15, and Q31 data types.  
00042  */ 
00043  
00044 /**  
00045  * @addtogroup dot_prod  
00046  * @{  
00047  */ 
00048  
00049 /**  
00050  * @brief Dot product of floating-point vectors.  
00051  * @param[in]       *pSrcA points to the first input vector  
00052  * @param[in]       *pSrcB points to the second input vector  
00053  * @param[in]       blockSize number of samples in each vector  
00054  * @param[out]      *result output result returned here  
00055  * @return none.  
00056  */ 
00057  
00058  
00059 void arm_dot_prod_f32( 
00060   float32_t * pSrcA, 
00061   float32_t * pSrcB, 
00062   uint32_t blockSize, 
00063   float32_t * result) 
00064 { 
00065   float32_t sum = 0.0f;                          /* Temporary result storage */ 
00066   uint32_t blkCnt;                               /* loop counter */ 
00067  
00068   /*loop Unrolling */ 
00069   blkCnt = blockSize >> 2u; 
00070  
00071   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00072    ** a second loop below computes the remaining 1 to 3 samples. */ 
00073   while(blkCnt > 0u) 
00074   { 
00075     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */ 
00076     /* Calculate dot product and then store the result in a temporary buffer */ 
00077     sum += (*pSrcA++) * (*pSrcB++); 
00078     sum += (*pSrcA++) * (*pSrcB++); 
00079     sum += (*pSrcA++) * (*pSrcB++); 
00080     sum += (*pSrcA++) * (*pSrcB++); 
00081  
00082     /* Decrement the loop counter */ 
00083     blkCnt--; 
00084   } 
00085  
00086   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00087    ** No loop unrolling is used. */ 
00088   blkCnt = blockSize % 0x4u; 
00089  
00090   while(blkCnt > 0u) 
00091   { 
00092     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */ 
00093     /* Calculate dot product and then store the result in a temporary buffer. */ 
00094     sum += (*pSrcA++) * (*pSrcB++); 
00095  
00096     /* Decrement the loop counter */ 
00097     blkCnt--; 
00098   } 
00099  
00100   /* Store the result back in the destination buffer */ 
00101   *result = sum; 
00102 } 
00103  
00104 /**  
00105  * @} end of dot_prod group  
00106  */