arm_cmplx_mag_squared_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_mag_squared_q15.c  
00009 *  
00010 * Description:  Q15 complex magnitude squared.  
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 cmplx_mag_squared  
00035  * @{  
00036  */ 
00037  
00038 /**  
00039  * @brief  Q15 complex magnitude squared  
00040  * @param  *pSrc points to the complex input vector  
00041  * @param  *pDst points to the real output vector  
00042  * @param  numSamples number of complex samples in the input vector  
00043  * @return none.  
00044  *  
00045  * <b>Scaling and Overflow Behavior:</b>  
00046  * \par  
00047  * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.  
00048  */ 
00049  
00050 void arm_cmplx_mag_squared_q15( 
00051   q15_t * pSrc, 
00052   q15_t * pDst, 
00053   uint32_t numSamples) 
00054 { 
00055   q15_t real, imag;                              /* Temporary variables to store real and imaginary values */ 
00056   q31_t acc0, acc1;                              /* Accumulators */ 
00057   uint32_t blkCnt;                               /* loop counter */ 
00058  
00059   /*loop Unrolling */ 
00060   blkCnt = numSamples >> 2u; 
00061  
00062   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00063    ** a second loop below computes the remaining 1 to 3 samples. */ 
00064   while(blkCnt > 0u) 
00065   { 
00066     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ 
00067     real = *pSrc++; 
00068     imag = *pSrc++; 
00069     acc0 = __SMUAD(real, real); 
00070     acc1 = __SMUAD(imag, imag); 
00071     /* store the result in 3.13 format in the destination buffer. */ 
00072     *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17); 
00073  
00074     real = *pSrc++; 
00075     imag = *pSrc++; 
00076     acc0 = __SMUAD(real, real); 
00077     acc1 = __SMUAD(imag, imag); 
00078     /* store the result in 3.13 format in the destination buffer. */ 
00079     *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17); 
00080  
00081     real = *pSrc++; 
00082     imag = *pSrc++; 
00083     acc0 = __SMUAD(real, real); 
00084     acc1 = __SMUAD(imag, imag); 
00085     /* store the result in 3.13 format in the destination buffer. */ 
00086     *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17); 
00087  
00088     real = *pSrc++; 
00089     imag = *pSrc++; 
00090     acc0 = __SMUAD(real, real); 
00091     acc1 = __SMUAD(imag, imag); 
00092     /* store the result in 3.13 format in the destination buffer. */ 
00093     *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17); 
00094  
00095     /* Decrement the loop counter */ 
00096     blkCnt--; 
00097   } 
00098  
00099   /* If the numSamples is not a multiple of 4, compute any remaining output samples here.  
00100    ** No loop unrolling is used. */ 
00101   blkCnt = numSamples % 0x4u; 
00102  
00103   while(blkCnt > 0u) 
00104   { 
00105     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ 
00106     real = *pSrc++; 
00107     imag = *pSrc++; 
00108     acc0 = __SMUAD(real, real); 
00109     acc1 = __SMUAD(imag, imag); 
00110     /* store the result in 3.13 format in the destination buffer. */ 
00111     *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17); 
00112  
00113     /* Decrement the loop counter */ 
00114     blkCnt--; 
00115   } 
00116 } 
00117  
00118 /**  
00119  * @} end of cmplx_mag_squared group  
00120  */