arm_offset_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_offset_q15.c  
00009 *  
00010 * Description:  Q15 vector offset.  
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 offset  
00038  * @{  
00039  */ 
00040  
00041 /**  
00042  * @brief  Adds a constant offset to a Q15 vector.  
00043  * @param  *pSrc points to the input vector  
00044  * @param  offset is the offset to be added  
00045  * @param  *pDst points to the output vector  
00046  * @param  blockSize number of samples in the 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 Q15 range [0x8000 0x7FFF] are saturated.  
00053  */ 
00054  
00055 void arm_offset_q15( 
00056   q15_t * pSrc, 
00057   q15_t offset, 
00058   q15_t * pDst, 
00059   uint32_t blockSize) 
00060 { 
00061   uint32_t blkCnt;                               /* loop counter */ 
00062   q31_t offset_packed;                           /* Offset packed to 32 bit */ 
00063  
00064  
00065   /*loop Unrolling */ 
00066   blkCnt = blockSize >> 2u; 
00067  
00068   /* Offset is packed to 32 bit in order to use SIMD32 for addition */ 
00069   offset_packed = __PKHBT(offset, offset, 16); 
00070  
00071   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00072    ** a second loop below computes the remaining 1 to 3 samples. */ 
00073   while(blkCnt > 0u) 
00074   { 
00075     /* C = A + offset */ 
00076     /* Add offset and then store the results in the destination buffer, 2 samples at a time. */ 
00077     *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed); 
00078     *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed); 
00079  
00080     /* Decrement the loop counter */ 
00081     blkCnt--; 
00082   } 
00083  
00084   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00085    ** No loop unrolling is used. */ 
00086   blkCnt = blockSize % 0x4u; 
00087  
00088   while(blkCnt > 0u) 
00089   { 
00090     /* C = A + offset */ 
00091     /* Add offset and then store the results in the destination buffer. */ 
00092     *pDst++ = (q15_t) __QADD16(*pSrc++, offset); 
00093  
00094     /* Decrement the loop counter */ 
00095     blkCnt--; 
00096   } 
00097 } 
00098  
00099 /**  
00100  * @} end of offset group  
00101  */