arm_fill_q15.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_fill_q15.c  
00009 *  
00010 * Description:  Processing function for the Q15 fill  
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 Fill  
00038  * @{  
00039  */ 
00040  
00041 /**  
00042  * @brief Fills a constant value into a Q15 vector.  
00043  * @param[in]       value input value to be filled 
00044  * @param[out]      *pDst points to output vector  
00045  * @param[in]       blockSize length of the output vector 
00046  * @return none.  
00047  *  
00048  */ 
00049  
00050 void arm_fill_q15( 
00051   q15_t value, 
00052   q15_t * pDst, 
00053   uint32_t blockSize) 
00054 { 
00055   uint32_t blkCnt;                               /* loop counter */ 
00056   q31_t packedValue;                             /* value packed to 32 bits */ 
00057  
00058  
00059   /*loop Unrolling */ 
00060   blkCnt = blockSize >> 2u; 
00061  
00062   /* Packing two 16 bit values to 32 bit value in order to use SIMD */ 
00063   packedValue = __PKHBT(value, value, 16u); 
00064  
00065   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00066    ** a second loop below computes the remaining 1 to 3 samples. */ 
00067   while(blkCnt > 0u) 
00068   { 
00069     /* C = value */ 
00070     /* Fill the value in the destination buffer */ 
00071     *__SIMD32(pDst)++ = packedValue; 
00072     *__SIMD32(pDst)++ = packedValue; 
00073  
00074     /* Decrement the loop counter */ 
00075     blkCnt--; 
00076   } 
00077  
00078   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00079    ** No loop unrolling is used. */ 
00080   blkCnt = blockSize % 0x4u; 
00081  
00082   while(blkCnt > 0u) 
00083   { 
00084     /* C = value */ 
00085     /* Fill the value in the destination buffer */ 
00086     *pDst++ = value; 
00087  
00088     /* Decrement the loop counter */ 
00089     blkCnt--; 
00090   } 
00091 } 
00092  
00093 /**  
00094  * @} end of Fill group  
00095  */