tmk_core/tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/BasicMathFunctions/arm_dot_prod_f32.c

   1 /* ----------------------------------------------------------------------
   2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
   3 *
   4 * $Date:        17. January 2013
   5 * $Revision:    V1.4.1
   6 *
   7 * Project:          CMSIS DSP Library
   8 * Title:                arm_dot_prod_f32.c
   9 *
  10 * Description:  Floating-point dot product.
  11 *
  12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
  13 *
  14 * Redistribution and use in source and binary forms, with or without
  15 * modification, are permitted provided that the following conditions
  16 * are met:
  17 *   - Redistributions of source code must retain the above copyright
  18 *     notice, this list of conditions and the following disclaimer.
  19 *   - Redistributions in binary form must reproduce the above copyright
  20 *     notice, this list of conditions and the following disclaimer in
  21 *     the documentation and/or other materials provided with the
  22 *     distribution.
  23 *   - Neither the name of ARM LIMITED nor the names of its contributors
  24 *     may be used to endorse or promote products derived from this
  25 *     software without specific prior written permission.
  26 *
  27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
  30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
  31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
  32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
  33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
  37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  38 * POSSIBILITY OF SUCH DAMAGE.
  39 * ---------------------------------------------------------------------------- */
  40
  41 #include "arm_math.h"
  42
  43 /**
  44  * @ingroup groupMath
  45  */
  46
  47 /**
  48  * @defgroup dot_prod Vector Dot Product
  49  *
  50  * Computes the dot product of two vectors.
  51  * The vectors are multiplied element-by-element and then summed.
  52  *
  53  * <pre>
  54  *     sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
  55  * </pre>
  56  *
  57  * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  58  */
  59
  60 /**
  61  * @addtogroup dot_prod
  62  * @{
  63  */
  64
  65 /**
  66  * @brief Dot product of floating-point vectors.
  67  * @param[in]       *pSrcA points to the first input vector
  68  * @param[in]       *pSrcB points to the second input vector
  69  * @param[in]       blockSize number of samples in each vector
  70  * @param[out]      *result output result returned here
  71  * @return none.
  72  */
  73
  74
  75 void arm_dot_prod_f32(
  76   float32_t * pSrcA,
  77   float32_t * pSrcB,
  78   uint32_t blockSize,
  79   float32_t * result)
  80 {
  81   float32_t sum = 0.0f;                          /* Temporary result storage */
  82   uint32_t blkCnt;                               /* loop counter */
  83
  84
  85 #ifndef ARM_MATH_CM0_FAMILY
  86
  87 /* Run the below code for Cortex-M4 and Cortex-M3 */
  88   /*loop Unrolling */
  89   blkCnt = blockSize >> 2u;
  90
  91   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
  92    ** a second loop below computes the remaining 1 to 3 samples. */
  93   while(blkCnt > 0u)
  94   {
  95     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
  96     /* Calculate dot product and then store the result in a temporary buffer */
  97     sum += (*pSrcA++) * (*pSrcB++);
  98     sum += (*pSrcA++) * (*pSrcB++);
  99     sum += (*pSrcA++) * (*pSrcB++);
 100     sum += (*pSrcA++) * (*pSrcB++);
 101
 102     /* Decrement the loop counter */
 103     blkCnt--;
 104   }
 105
 106   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
 107    ** No loop unrolling is used. */
 108   blkCnt = blockSize % 0x4u;
 109
 110 #else
 111
 112   /* Run the below code for Cortex-M0 */
 113
 114   /* Initialize blkCnt with number of samples */
 115   blkCnt = blockSize;
 116
 117 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 118
 119
 120   while(blkCnt > 0u)
 121   {
 122     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
 123     /* Calculate dot product and then store the result in a temporary buffer. */
 124     sum += (*pSrcA++) * (*pSrcB++);
 125
 126     /* Decrement the loop counter */
 127     blkCnt--;
 128   }
 129   /* Store the result back in the destination buffer */
 130   *result = sum;
 131 }
 132
 133 /**
 134  * @} end of dot_prod group
 135  */