arm_mult_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_mult_q31.c  
00009 *  
00010 * Description:  Q31 vector multiplication.  
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 0.0.5  2010/04/26   
00027 *    incorporated review comments and updated with latest CMSIS layer  
00028 *  
00029 * Version 0.0.3  2010/03/10   
00030 *    Initial version  
00031 * -------------------------------------------------------------------- */ 
00032  
00033 #include "arm_math.h" 
00034  
00035 /**  
00036  * @ingroup groupMath  
00037  */ 
00038  
00039 /**  
00040  * @addtogroup BasicMult  
00041  * @{  
00042  */ 
00043  
00044 /**  
00045  * @brief Q31 vector multiplication.  
00046  * @param[in]       *pSrcA points to the first input vector  
00047  * @param[in]       *pSrcB points to the second input vector  
00048  * @param[out]      *pDst points to the output vector  
00049  * @param[in]       blockSize number of samples in each vector  
00050  * @return none.  
00051  *  
00052  * <b>Scaling and Overflow Behavior:</b>  
00053  * \par  
00054  * The function uses saturating arithmetic.  
00055  * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.  
00056  */ 
00057  
00058 void arm_mult_q31( 
00059   q31_t * pSrcA, 
00060   q31_t * pSrcB, 
00061   q31_t * pDst, 
00062   uint32_t blockSize) 
00063 { 
00064   uint32_t blkCnt;                               /* loop counters */ 
00065  
00066   /* loop Unrolling */ 
00067   blkCnt = blockSize >> 2u; 
00068  
00069   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00070    ** a second loop below computes the remaining 1 to 3 samples. */ 
00071   while(blkCnt > 0u) 
00072   { 
00073     /* C = A * B */ 
00074     /* Multiply the inputs and then store the results in the destination buffer. */ 
00075     *pDst++ = (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31); 
00076     *pDst++ = (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31); 
00077     *pDst++ = (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31); 
00078     *pDst++ = (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31); 
00079  
00080     /* Decrement the blockSize 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 * B */ 
00091     /* Multiply the inputs and then store the results in the destination buffer. */ 
00092     *pDst++ = (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31); 
00093  
00094     /* Decrement the blockSize loop counter */ 
00095     blkCnt--; 
00096   } 
00097 } 
00098  
00099 /**  
00100  * @} end of BasicMult group  
00101  */