arm_mat_sub_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_mat_sub_f32.c  
00009 *  
00010 * Description:  Floating-point matrix subtraction.  
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 0.0.5  2010/04/26   
00027 *    incorporated review comments and updated with latest CMSIS layer  
00028 *  
00029 * Version 0.0.3  2010/03/10   
00030 *    Initial version  
00031 * -------------------------------------------------------------------- */ 
00032  
00033 #include "arm_math.h" 
00034  
00035 /**  
00036  * @ingroup groupMatrix  
00037  */ 
00038  
00039 /**  
00040  * @defgroup MatrixSub Matrix Subtraction  
00041  *  
00042  * Subtract two matrices.  
00043  * \image html MatrixSubtraction.gif "Subraction of two 3 x 3 matrices"  
00044  *  
00045  * The functions check to make sure that  
00046  * <code>pSrcA</code>, <code>pSrcB</code>, and <code>pDst</code> have the same  
00047  * number of rows and columns.  
00048  */ 
00049  
00050 /**  
00051  * @addtogroup MatrixSub  
00052  * @{  
00053  */ 
00054  
00055 /**  
00056  * @brief Floating-point matrix subtraction  
00057  * @param[in]       *pSrcA points to the first input matrix structure  
00058  * @param[in]       *pSrcB points to the second input matrix structure  
00059  * @param[out]      *pDst points to output matrix structure  
00060  * @return          The function returns either  
00061  * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.  
00062  */ 
00063  
00064 arm_status arm_mat_sub_f32( 
00065   const arm_matrix_instance_f32 * pSrcA, 
00066   const arm_matrix_instance_f32 * pSrcB, 
00067   arm_matrix_instance_f32 * pDst) 
00068 { 
00069   float32_t *pIn1 = pSrcA->pData;                /* input data matrix pointer A */ 
00070   float32_t *pIn2 = pSrcB->pData;                /* input data matrix pointer B */ 
00071   float32_t *pOut = pDst->pData;                 /* output data matrix pointer  */ 
00072   uint32_t numSamples;                           /* total number of elements in the matrix  */ 
00073   uint32_t blkCnt;                               /* loop counters */ 
00074   arm_status status;                             /* status of matrix subtraction */ 
00075  
00076 #ifdef ARM_MATH_MATRIX_CHECK 
00077   /* Check for matrix mismatch condition */ 
00078   if((pSrcA->numRows != pSrcB->numRows) || 
00079      (pSrcA->numCols != pSrcB->numCols) || 
00080      (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols)) 
00081   { 
00082     /* Set status as ARM_MATH_SIZE_MISMATCH */ 
00083     status = ARM_MATH_SIZE_MISMATCH; 
00084   } 
00085   else 
00086 #endif 
00087   { 
00088     /* Total number of samples in the input matrix */ 
00089     numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols; 
00090  
00091     /* Loop Unrolling */ 
00092     blkCnt = numSamples >> 2u; 
00093  
00094     /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00095      ** a second loop below computes the remaining 1 to 3 samples. */ 
00096     while(blkCnt > 0u) 
00097     { 
00098       /* C(m,n) = A(m,n) - B(m,n) */ 
00099       /* Subtract and then store the results in the destination buffer. */ 
00100       *pOut++ = (*pIn1++) - (*pIn2++); 
00101       *pOut++ = (*pIn1++) - (*pIn2++); 
00102       *pOut++ = (*pIn1++) - (*pIn2++); 
00103       *pOut++ = (*pIn1++) - (*pIn2++); 
00104  
00105       /* Decrement the loop counter */ 
00106       blkCnt--; 
00107     } 
00108  
00109     /* If the numSamples is not a multiple of 4, compute any remaining output samples here.  
00110      ** No loop unrolling is used. */ 
00111     blkCnt = numSamples % 0x4u; 
00112  
00113     while(blkCnt > 0u) 
00114     { 
00115       /* C(m,n) = A(m,n) - B(m,n) */ 
00116       /* Subtract and then store the results in the destination buffer. */ 
00117       *pOut++ = (*pIn1++) - (*pIn2++); 
00118  
00119       /* Decrement the loop counter */ 
00120       blkCnt--; 
00121     } 
00122  
00123     /* Set status as ARM_MATH_SUCCESS */ 
00124     status = ARM_MATH_SUCCESS; 
00125   } 
00126  
00127   /* Return to application */ 
00128   return (status); 
00129 } 
00130  
00131 /**  
00132  * @} end of MatrixSub group  
00133  */