arm_cmplx_mult_cmplx_f32.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_f32.c  
00009 *  
00010 * Description:  Floating-point 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  * @defgroup CmplxByCmplxMult Complex-by-Complex Multiplication  
00035  *  
00036  * Multiplies a complex vector by another complex vector and generates a complex result.  
00037  * The data in the complex arrays is stored in an interleaved fashion  
00038  * (real, imag, real, imag, ...).  
00039  * The parameter <code>numSamples</code> represents the number of complex  
00040  * samples processed.  The complex arrays have a total of <code>2*numSamples</code>  
00041  * real values.  
00042  *  
00043  * The underlying algorithm is used:  
00044  *  
00045  * <pre>  
00046  * for(n=0; n<numSamples; n++) {  
00047  *     pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1];  
00048  *     pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0];  
00049  * }  
00050  * </pre>  
00051  *  
00052  * There are separate functions for floating-point, Q15, and Q31 data types.  
00053  */ 
00054  
00055 /**  
00056  * @addtogroup CmplxByCmplxMult  
00057  * @{  
00058  */ 
00059  
00060  
00061 /**  
00062  * @brief  Floating-point complex-by-complex multiplication  
00063  * @param[in]  *pSrcA points to the first input vector  
00064  * @param[in]  *pSrcB points to the second input vector  
00065  * @param[out]  *pDst  points to the output vector  
00066  * @param[in]  numSamples number of complex samples in each vector  
00067  * @return none.  
00068  */ 
00069  
00070 void arm_cmplx_mult_cmplx_f32( 
00071   float32_t * pSrcA, 
00072   float32_t * pSrcB, 
00073   float32_t * pDst, 
00074   uint32_t numSamples) 
00075 { 
00076   float32_t a, b, c, d;                          /* Temporary variables to store real and imaginary values */ 
00077   uint32_t blkCnt;                               /* loop counters */ 
00078  
00079   /* loop Unrolling */ 
00080   blkCnt = numSamples >> 2u; 
00081  
00082   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00083    ** a second loop below computes the remaining 1 to 3 samples. */ 
00084   while(blkCnt > 0u) 
00085   { 
00086     /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */ 
00087     /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */ 
00088     a = *pSrcA++; 
00089     b = *pSrcA++; 
00090     c = *pSrcB++; 
00091     d = *pSrcB++; 
00092  
00093     /* store the result in the destination buffer. */ 
00094     *pDst++ = (a * c) - (b * d); 
00095     *pDst++ = (a * d) + (b * c); 
00096  
00097     a = *pSrcA++; 
00098     b = *pSrcA++; 
00099     c = *pSrcB++; 
00100     d = *pSrcB++; 
00101  
00102     *pDst++ = (a * c) - (b * d); 
00103     *pDst++ = (a * d) + (b * c); 
00104  
00105     a = *pSrcA++; 
00106     b = *pSrcA++; 
00107     c = *pSrcB++; 
00108     d = *pSrcB++; 
00109  
00110     *pDst++ = (a * c) - (b * d); 
00111     *pDst++ = (a * d) + (b * c); 
00112  
00113     a = *pSrcA++; 
00114     b = *pSrcA++; 
00115     c = *pSrcB++; 
00116     d = *pSrcB++; 
00117  
00118     *pDst++ = (a * c) - (b * d); 
00119     *pDst++ = (a * d) + (b * c); 
00120  
00121     /* Decrement the numSamples loop counter */ 
00122     blkCnt--; 
00123   } 
00124  
00125   /* If the numSamples is not a multiple of 4, compute any remaining output samples here.  
00126    ** No loop unrolling is used. */ 
00127   blkCnt = numSamples % 0x4u; 
00128  
00129   while(blkCnt > 0u) 
00130   { 
00131     /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */ 
00132     /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */ 
00133     a = *pSrcA++; 
00134     b = *pSrcA++; 
00135     c = *pSrcB++; 
00136     d = *pSrcB++; 
00137  
00138     /* store the result in the destination buffer. */ 
00139     *pDst++ = (a * c) - (b * d); 
00140     *pDst++ = (a * d) + (b * c); 
00141  
00142     /* Decrement the numSamples loop counter */ 
00143     blkCnt--; 
00144   } 
00145 } 
00146  
00147 /**  
00148  * @} end of CmplxByCmplxMult group  
00149  */