arm_power_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_power_f32.c  
00009 *  
00010 * Description:  sum of the square of the elements in a floating point array  
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 groupStats  
00034  */ 
00035  
00036 /**  
00037  * @defgroup power Power  
00038  *  
00039  * Calculates the sum of the squares of the elements in the input vector.  
00040  * The underlying algorithm is used:  
00041  *  
00042  * <pre>  
00043  *  Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1];  
00044  * </pre>  
00045  * 
00046  * There are separate functions for floating point, Q31, Q15, and Q7 data types.   
00047  */ 
00048  
00049 /**  
00050  * @addtogroup power  
00051  * @{  
00052  */ 
00053  
00054  
00055 /**  
00056  * @brief Sum of the squares of the elements of a floating-point vector.  
00057  * @param[in]       *pSrc points to the input vector  
00058  * @param[in]       blockSize length of the input vector  
00059  * @param[out]      *pResult sum of the squares value returned here  
00060  * @return none.  
00061  *  
00062  */ 
00063  
00064  
00065 void arm_power_f32( 
00066   float32_t * pSrc, 
00067   uint32_t blockSize, 
00068   float32_t * pResult) 
00069 { 
00070   float32_t sum = 0.0f;                          /* accumulator */ 
00071   float32_t in;                                  /* Temporary variable to store input value */ 
00072   uint32_t blkCnt;                               /* loop counter */ 
00073  
00074   /*loop Unrolling */ 
00075   blkCnt = blockSize >> 2u; 
00076  
00077   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00078    ** a second loop below computes the remaining 1 to 3 samples. */ 
00079   while(blkCnt > 0u) 
00080   { 
00081     /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ 
00082     /* Compute Power and then store the result in a temporary variable, sum. */ 
00083     in = *pSrc++; 
00084     sum += in * in; 
00085     in = *pSrc++; 
00086     sum += in * in; 
00087     in = *pSrc++; 
00088     sum += in * in; 
00089     in = *pSrc++; 
00090     sum += in * in; 
00091  
00092     /* Decrement the loop counter */ 
00093     blkCnt--; 
00094   } 
00095  
00096   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00097    ** No loop unrolling is used. */ 
00098   blkCnt = blockSize % 0x4u; 
00099  
00100   while(blkCnt > 0u) 
00101   { 
00102     /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ 
00103     /* compute power and then store the result in a temporary variable, sum. */ 
00104     in = *pSrc++; 
00105     sum += in * in; 
00106  
00107     /* Decrement the loop counter */ 
00108     blkCnt--; 
00109   } 
00110  
00111   /* Store the result to the destination */ 
00112   *pResult = sum; 
00113 } 
00114  
00115 /**  
00116  * @} end of power group  
00117  */