arm_add_q31.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_q31.c  
00009 *  
00010 * Description:  Q31 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  * @addtogroup BasicAdd  
00038  * @{  
00039  */ 
00040  
00041  
00042 /**  
00043  * @brief Q31 vector addition.  
00044  * @param[in]       *pSrcA points to the first input vector  
00045  * @param[in]       *pSrcB points to the second input vector  
00046  * @param[out]      *pDst points to the output vector  
00047  * @param[in]       blockSize number of samples in each vector  
00048  * @return none.  
00049  *  
00050  * <b>Scaling and Overflow Behavior:</b>  
00051  * \par  
00052  * The function uses saturating arithmetic.  
00053  * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.  
00054  */ 
00055  
00056 void arm_add_q31( 
00057   q31_t * pSrcA, 
00058   q31_t * pSrcB, 
00059   q31_t * pDst, 
00060   uint32_t blockSize) 
00061 { 
00062   uint32_t blkCnt;                               /* loop counter */ 
00063  
00064  
00065   /*loop Unrolling */ 
00066   blkCnt = blockSize >> 2u; 
00067  
00068   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00069    ** a second loop below computes the remaining 1 to 3 samples. */ 
00070   while(blkCnt > 0u) 
00071   { 
00072     /* C = A + B */ 
00073     /* Add and then store the results in the destination buffer. */ 
00074     *pDst++ = __QADD(*pSrcA++, *pSrcB++); 
00075     *pDst++ = __QADD(*pSrcA++, *pSrcB++); 
00076     *pDst++ = __QADD(*pSrcA++, *pSrcB++); 
00077     *pDst++ = __QADD(*pSrcA++, *pSrcB++); 
00078  
00079     /* Decrement the loop counter */ 
00080     blkCnt--; 
00081   } 
00082  
00083   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00084    ** No loop unrolling is used. */ 
00085   blkCnt = blockSize % 0x4u; 
00086  
00087   while(blkCnt > 0u) 
00088   { 
00089     /* C = A + B */ 
00090     /* Add and then store the results in the destination buffer. */ 
00091     *pDst++ = __QADD(*pSrcA++, *pSrcB++); 
00092  
00093     /* Decrement the loop counter */ 
00094     blkCnt--; 
00095   } 
00096 } 
00097  
00098 /**  
00099  * @} end of BasicAdd group  
00100  */