arm_mult_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_mult_f32.c  
00009 *  
00010 * Description:  Floating-point vector multiplication.  
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 0.0.5  2010/04/26   
00027 *    incorporated review comments and updated with latest CMSIS layer  
00028 *  
00029 * Version 0.0.3  2010/03/10   
00030 *    Initial version  
00031 * -------------------------------------------------------------------- */ 
00032  
00033 #include "arm_math.h" 
00034  
00035 /**  
00036  * @ingroup groupMath  
00037  */ 
00038  
00039 /**  
00040  * @defgroup BasicMult Vector Multiplication  
00041  *  
00042  * Element-by-element multiplication of two vectors.  
00043  *  
00044  * <pre>  
00045  *     pDst[n] = pSrcA[n] * pSrcB[n],   0 <= n < blockSize.  
00046  * </pre>  
00047  *  
00048  * There are separate functions for floating-point, Q7, Q15, and Q31 data types.  
00049  */ 
00050  
00051 /**  
00052  * @addtogroup BasicMult  
00053  * @{  
00054  */ 
00055  
00056 /**  
00057  * @brief Floating-point vector multiplication.  
00058  * @param[in]       *pSrcA points to the first input vector  
00059  * @param[in]       *pSrcB points to the second input vector  
00060  * @param[out]      *pDst points to the output vector  
00061  * @param[in]       blockSize number of samples in each vector  
00062  * @return none.  
00063  */ 
00064  
00065 void arm_mult_f32( 
00066   float32_t * pSrcA, 
00067   float32_t * pSrcB, 
00068   float32_t * pDst, 
00069   uint32_t blockSize) 
00070 { 
00071   uint32_t blkCnt;                               /* loop counters */ 
00072  
00073   /* loop Unrolling */ 
00074   blkCnt = blockSize >> 2u; 
00075  
00076   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00077    ** a second loop below computes the remaining 1 to 3 samples. */ 
00078   while(blkCnt > 0u) 
00079   { 
00080     /* C = A * B */ 
00081     /* Multiply the inputs and store the results in output buffer */ 
00082     *pDst++ = (*pSrcA++) * (*pSrcB++); 
00083     *pDst++ = (*pSrcA++) * (*pSrcB++); 
00084     *pDst++ = (*pSrcA++) * (*pSrcB++); 
00085     *pDst++ = (*pSrcA++) * (*pSrcB++); 
00086  
00087     /* Decrement the blockSize loop counter */ 
00088     blkCnt--; 
00089   } 
00090  
00091   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00092    ** No loop unrolling is used. */ 
00093   blkCnt = blockSize % 0x4u; 
00094  
00095   while(blkCnt > 0u) 
00096   { 
00097     /* C = A * B */ 
00098     /* Multiply the inputs and store the results in output buffer */ 
00099     *pDst++ = (*pSrcA++) * (*pSrcB++); 
00100  
00101     /* Decrement the blockSize loop counter */ 
00102     blkCnt--; 
00103   } 
00104 } 
00105  
00106 /**  
00107  * @} end of BasicMult group  
00108  */