arm_cmplx_mult_cmplx_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_cmplx_mult_cmplx_q15.c  
00009 *  
00010 * Description:  Q15 complex-by-complex 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  
00027 #include "arm_math.h" 
00028  
00029 /**  
00030  * @ingroup groupCmplxMath  
00031  */ 
00032  
00033 /**  
00034  * @addtogroup CmplxByCmplxMult  
00035  * @{  
00036  */ 
00037  
00038 /**  
00039  * @brief  Q15 complex-by-complex multiplication  
00040  * @param[in]  *pSrcA points to the first input vector  
00041  * @param[in]  *pSrcB points to the second input vector  
00042  * @param[out]  *pDst  points to the output vector  
00043  * @param[in]  numSamples number of complex samples in each vector  
00044  * @return none.  
00045  *  
00046  * <b>Scaling and Overflow Behavior:</b>  
00047  * \par  
00048  * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.  
00049  */ 
00050  
00051 void arm_cmplx_mult_cmplx_q15( 
00052   q15_t * pSrcA, 
00053   q15_t * pSrcB, 
00054   q15_t * pDst, 
00055   uint32_t numSamples) 
00056 { 
00057   q15_t a, b, c, d;                              /* Temporary variables to store real and imaginary values */ 
00058   uint32_t blkCnt;                               /* loop counters */ 
00059  
00060   /* loop Unrolling */ 
00061   blkCnt = numSamples >> 2u; 
00062  
00063   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00064    ** a second loop below computes the remaining 1 to 3 samples. */ 
00065   while(blkCnt > 0u) 
00066   { 
00067     /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */ 
00068     /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */ 
00069     a = *pSrcA++; 
00070     b = *pSrcA++; 
00071     c = *pSrcB++; 
00072     d = *pSrcB++; 
00073  
00074     /* store the result in 3.13 format in the destination buffer. */ 
00075     *pDst++ = 
00076       (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); 
00077     /* store the result in 3.13 format in the destination buffer. */ 
00078     *pDst++ = 
00079       (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); 
00080  
00081     a = *pSrcA++; 
00082     b = *pSrcA++; 
00083     c = *pSrcB++; 
00084     d = *pSrcB++; 
00085  
00086     /* store the result in 3.13 format in the destination buffer. */ 
00087     *pDst++ = 
00088       (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); 
00089     /* store the result in 3.13 format in the destination buffer. */ 
00090     *pDst++ = 
00091       (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); 
00092  
00093     a = *pSrcA++; 
00094     b = *pSrcA++; 
00095     c = *pSrcB++; 
00096     d = *pSrcB++; 
00097  
00098     /* store the result in 3.13 format in the destination buffer. */ 
00099     *pDst++ = 
00100       (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); 
00101     /* store the result in 3.13 format in the destination buffer. */ 
00102     *pDst++ = 
00103       (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); 
00104  
00105     a = *pSrcA++; 
00106     b = *pSrcA++; 
00107     c = *pSrcB++; 
00108     d = *pSrcB++; 
00109  
00110     /* store the result in 3.13 format in the destination buffer. */ 
00111     *pDst++ = 
00112       (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); 
00113     /* store the result in 3.13 format in the destination buffer. */ 
00114     *pDst++ = 
00115       (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); 
00116  
00117     /* Decrement the blockSize loop counter */ 
00118     blkCnt--; 
00119   } 
00120  
00121   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00122    ** No loop unrolling is used. */ 
00123   blkCnt = numSamples % 0x4u; 
00124  
00125   while(blkCnt > 0u) 
00126   { 
00127     /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */ 
00128     /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */ 
00129     a = *pSrcA++; 
00130     b = *pSrcA++; 
00131     c = *pSrcB++; 
00132     d = *pSrcB++; 
00133  
00134     /* store the result in 3.13 format in the destination buffer. */ 
00135     *pDst++ = 
00136       (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); 
00137     /* store the result in 3.13 format in the destination buffer. */ 
00138     *pDst++ = 
00139       (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); 
00140  
00141     /* Decrement the blockSize loop counter */ 
00142     blkCnt--; 
00143   } 
00144 } 
00145  
00146 /**  
00147  * @} end of CmplxByCmplxMult group  
00148  */