arm_add_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_add_f32.c  
00009 *  
00010 * Description:  Floating-point vector addition.  
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 BasicAdd Vector Addition  
00038  *  
00039  * Element-by-element addition of two vectors.  
00040  *  
00041  * <pre>  
00042  *     pDst[n] = pSrcA[n] + pSrcB[n],   0 <= n < blockSize.  
00043  * </pre>  
00044  *  
00045  * There are separate functions for floating-point, Q7, Q15, and Q31 data types.  
00046  */ 
00047  
00048 /**  
00049  * @addtogroup BasicAdd  
00050  * @{  
00051  */ 
00052  
00053 /**  
00054  * @brief Floating-point vector addition.  
00055  * @param[in]       *pSrcA points to the first input vector  
00056  * @param[in]       *pSrcB points to the second input vector  
00057  * @param[out]      *pDst points to the output vector  
00058  * @param[in]       blockSize number of samples in each vector  
00059  * @return none.  
00060  */ 
00061  
00062 void arm_add_f32( 
00063   float32_t * pSrcA, 
00064   float32_t * pSrcB, 
00065   float32_t * pDst, 
00066   uint32_t blockSize) 
00067 { 
00068   uint32_t blkCnt;                               /* loop counter */ 
00069  
00070   /*loop Unrolling */ 
00071   blkCnt = blockSize >> 2u; 
00072  
00073   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00074    ** a second loop below computes the remaining 1 to 3 samples. */ 
00075   while(blkCnt > 0u) 
00076   { 
00077     /* C = A + B */ 
00078     /* Add and then store the results in the destination buffer. */ 
00079     *pDst++ = (*pSrcA++) + (*pSrcB++); 
00080     *pDst++ = (*pSrcA++) + (*pSrcB++); 
00081     *pDst++ = (*pSrcA++) + (*pSrcB++); 
00082     *pDst++ = (*pSrcA++) + (*pSrcB++); 
00083  
00084     /* Decrement the loop counter */ 
00085     blkCnt--; 
00086   } 
00087  
00088   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00089    ** No loop unrolling is used. */ 
00090   blkCnt = blockSize % 0x4u; 
00091  
00092   while(blkCnt > 0u) 
00093   { 
00094     /* C = A + B */ 
00095     /* Add and then store the results in the destination buffer. */ 
00096     *pDst++ = (*pSrcA++) + (*pSrcB++); 
00097  
00098     /* Decrement the loop counter */ 
00099     blkCnt--; 
00100   } 
00101 } 
00102  
00103 /**  
00104  * @} end of BasicAdd group  
00105  */