arm_copy_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_copy_q7.c  
00009 *  
00010 * Description:  Processing function for the Q7 copy  
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 groupSupport  
00034  */ 
00035  
00036 /**  
00037  * @addtogroup copy  
00038  * @{  
00039  */ 
00040  
00041 /**  
00042  * @brief Copies the elements of a Q7 vector.  
00043  * @param[in]       *pSrc points to input vector  
00044  * @param[out]      *pDst points to output vector  
00045  * @param[in]       blockSize length of the input vector 
00046  * @return none.  
00047  *  
00048  */ 
00049  
00050 void arm_copy_q7( 
00051   q7_t * pSrc, 
00052   q7_t * pDst, 
00053   uint32_t blockSize) 
00054 { 
00055   uint32_t blkCnt;                               /* loop counter */ 
00056  
00057   /*loop Unrolling */ 
00058   blkCnt = blockSize >> 2u; 
00059  
00060   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00061    ** a second loop below computes the remaining 1 to 3 samples. */ 
00062   while(blkCnt > 0u) 
00063   { 
00064     /* C = A */ 
00065     /* Copy and then store the results in the destination buffer */ 
00066     /* 4 samples are copied and stored at a time using SIMD */ 
00067     *__SIMD32(pDst)++ = *__SIMD32(pSrc)++; 
00068  
00069     /* Decrement the loop counter */ 
00070     blkCnt--; 
00071   } 
00072  
00073   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00074    ** No loop unrolling is used. */ 
00075   blkCnt = blockSize % 0x4u; 
00076  
00077   while(blkCnt > 0u) 
00078   { 
00079     /* C = A */ 
00080     /* Copy and then store the results in the destination buffer */ 
00081     *pDst++ = *pSrc++; 
00082  
00083     /* Decrement the loop counter */ 
00084     blkCnt--; 
00085   } 
00086 } 
00087  
00088 /**  
00089  * @} end of BasicCopy group  
00090  */