arm_add_q7.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_q7.c  
00009 *  
00010 * Description:  Q7 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  * @brief Q7 vector addition.  
00043  * @param[in]       *pSrcA points to the first input vector  
00044  * @param[in]       *pSrcB points to the second input vector  
00045  * @param[out]      *pDst points to the output vector  
00046  * @param[in]       blockSize number of samples in each vector  
00047  * @return none.  
00048  *  
00049  * <b>Scaling and Overflow Behavior:</b>  
00050  * \par  
00051  * The function uses saturating arithmetic.  
00052  * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.  
00053  */ 
00054  
00055 void arm_add_q7( 
00056   q7_t * pSrcA, 
00057   q7_t * pSrcB, 
00058   q7_t * pDst, 
00059   uint32_t blockSize) 
00060 { 
00061   uint32_t blkCnt;                               /* loop counter */ 
00062  
00063  
00064   /*loop Unrolling */ 
00065   blkCnt = blockSize >> 2u; 
00066  
00067   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00068    ** a second loop below computes the remaining 1 to 3 samples. */ 
00069   while(blkCnt > 0u) 
00070   { 
00071     /* C = A + B */ 
00072     /* Add and then store the results in the destination buffer. */ 
00073     *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++); 
00074  
00075     /* Decrement the loop counter */ 
00076     blkCnt--; 
00077   } 
00078  
00079   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00080    ** No loop unrolling is used. */ 
00081   blkCnt = blockSize % 0x4u; 
00082  
00083   while(blkCnt > 0u) 
00084   { 
00085     /* C = A + B */ 
00086     /* Add and then store the results in the destination buffer. */ 
00087     *pDst++ = (q7_t) __SSAT(*pSrcA++ + *pSrcB++, 8); 
00088  
00089     /* Decrement the loop counter */ 
00090     blkCnt--; 
00091   } 
00092  
00093 } 
00094  
00095 /**  
00096  * @} end of BasicAdd group  
00097  */