arm_scale_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_scale_q15.c  
00009 *  
00010 * Description:  Multiplies a Q15 vector by a scalar.  
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 scale  
00038  * @{  
00039  */ 
00040  
00041 /**  
00042  * @brief Multiplies a Q15 vector by a scalar.  
00043  * @param[in]       *pSrc points to the input vector  
00044  * @param[in]       scaleFract fractional portion of the scale value  
00045  * @param[in]       shift number of bits to shift the result by  
00046  * @param[out]      *pDst points to the output vector  
00047  * @param[in]       blockSize number of samples in the vector  
00048  * @return none.  
00049  *  
00050  * <b>Scaling and Overflow Behavior:</b>  
00051  * \par  
00052  * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.  
00053  * These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.  
00054  */ 
00055  
00056  
00057 void arm_scale_q15( 
00058   q15_t * pSrc, 
00059   q15_t scaleFract, 
00060   int8_t shift, 
00061   q15_t * pDst, 
00062   uint32_t blockSize) 
00063 { 
00064   int8_t kShift = 15 - shift;                    /* shift to apply after scaling */ 
00065   uint32_t blkCnt;                               /* loop counter */ 
00066   q15_t in1, in2;                                /* Temporary variables */ 
00067  
00068  
00069   /*loop Unrolling */ 
00070   blkCnt = blockSize >> 2u; 
00071  
00072   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00073    ** a second loop below computes the remaining 1 to 3 samples. */ 
00074   while(blkCnt > 0u) 
00075   { 
00076     /* Reading 2 inputs from memory */ 
00077     in1 = *pSrc++; 
00078     in2 = *pSrc++; 
00079     /* C = A * scale */ 
00080     /* Scale the inputs and then store the 2 results in the destination buffer  
00081      * in single cycle by packing the outputs */ 
00082     *__SIMD32(pDst)++ = 
00083       __PKHBT(__SSAT((in1 * scaleFract) >> kShift, 16), 
00084               __SSAT((in2 * scaleFract) >> kShift, 16), 16); 
00085  
00086     in1 = *pSrc++; 
00087     in2 = *pSrc++; 
00088  
00089     *__SIMD32(pDst)++ = 
00090       __PKHBT(__SSAT((in1 * scaleFract) >> kShift, 16), 
00091               __SSAT((in2 * scaleFract) >> kShift, 16), 16); 
00092  
00093     /* Decrement the loop counter */ 
00094     blkCnt--; 
00095   } 
00096  
00097   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00098    ** No loop unrolling is used. */ 
00099   blkCnt = blockSize % 0x4u; 
00100  
00101   while(blkCnt > 0u) 
00102   { 
00103     /* C = A * scale */ 
00104     /* Scale the input and then store the result in the destination buffer. */ 
00105     *pDst++ = (q15_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 16)); 
00106  
00107     /* Decrement the loop counter */ 
00108     blkCnt--; 
00109   } 
00110 } 
00111  
00112 /**  
00113  * @} end of scale group  
00114  */