arm_cmplx_mag_squared_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_cmplx_mag_squared_q31.c  
00009 *  
00010 * Description:  Q31 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 /**  
00040  * @brief  Q31 complex magnitude squared  
00041  * @param  *pSrc points to the complex input vector  
00042  * @param  *pDst points to the real output vector  
00043  * @param  numSamples number of complex samples in the input vector  
00044  * @return none.  
00045  *  
00046  * <b>Scaling and Overflow Behavior:</b>  
00047  * \par  
00048  * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.  
00049  * Input down scaling is not required.  
00050  */ 
00051  
00052 void arm_cmplx_mag_squared_q31( 
00053   q31_t * pSrc, 
00054   q31_t * pDst, 
00055   uint32_t numSamples) 
00056 { 
00057   q31_t real, imag;                              /* Temporary variables to store real and imaginary values */ 
00058   q31_t acc0, acc1;                              /* Accumulators */ 
00059   uint32_t blkCnt;                               /* loop counter */ 
00060  
00061   /* loop Unrolling */ 
00062   blkCnt = numSamples >> 2u; 
00063  
00064   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00065    ** a second loop below computes the remaining 1 to 3 samples. */ 
00066   while(blkCnt > 0u) 
00067   { 
00068     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ 
00069     real = *pSrc++; 
00070     imag = *pSrc++; 
00071     acc0 = (q31_t) (((q63_t) real * real) >> 33); 
00072     acc1 = (q31_t) (((q63_t) imag * imag) >> 33); 
00073     /* store the result in 3.29 format in the destination buffer. */ 
00074     *pDst++ = acc0 + acc1; 
00075  
00076     real = *pSrc++; 
00077     imag = *pSrc++; 
00078     acc0 = (q31_t) (((q63_t) real * real) >> 33); 
00079     acc1 = (q31_t) (((q63_t) imag * imag) >> 33); 
00080     /* store the result in 3.29 format in the destination buffer. */ 
00081     *pDst++ = acc0 + acc1; 
00082  
00083     real = *pSrc++; 
00084     imag = *pSrc++; 
00085     acc0 = (q31_t) (((q63_t) real * real) >> 33); 
00086     acc1 = (q31_t) (((q63_t) imag * imag) >> 33); 
00087     /* store the result in 3.29 format in the destination buffer. */ 
00088     *pDst++ = acc0 + acc1; 
00089  
00090     real = *pSrc++; 
00091     imag = *pSrc++; 
00092     acc0 = (q31_t) (((q63_t) real * real) >> 33); 
00093     acc1 = (q31_t) (((q63_t) imag * imag) >> 33); 
00094     /* store the result in 3.29 format in the destination buffer. */ 
00095     *pDst++ = acc0 + acc1; 
00096  
00097     /* Decrement the loop counter */ 
00098     blkCnt--; 
00099   } 
00100  
00101   /* If the numSamples is not a multiple of 4, compute any remaining output samples here.  
00102    ** No loop unrolling is used. */ 
00103   blkCnt = numSamples % 0x4u; 
00104  
00105   while(blkCnt > 0u) 
00106   { 
00107     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ 
00108     real = *pSrc++; 
00109     imag = *pSrc++; 
00110     acc0 = (q31_t) (((q63_t) real * real) >> 33); 
00111     acc1 = (q31_t) (((q63_t) imag * imag) >> 33); 
00112     /* store the result in 3.29 format in the destination buffer. */ 
00113     *pDst++ = acc0 + acc1; 
00114  
00115     /* Decrement the loop counter */ 
00116     blkCnt--; 
00117   } 
00118 } 
00119  
00120 /**  
00121  * @} end of cmplx_mag_squared group  
00122  */