tmk_core/tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/BasicMathFunctions/arm_scale_q7.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_scale_q7.c
   9 *
  10 * Description:  Multiplies a Q7 vector by a scalar.
  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  * @addtogroup scale
  49  * @{
  50  */
  51
  52 /**
  53  * @brief Multiplies a Q7 vector by a scalar.
  54  * @param[in]       *pSrc points to the input vector
  55  * @param[in]       scaleFract fractional portion of the scale value
  56  * @param[in]       shift number of bits to shift the result by
  57  * @param[out]      *pDst points to the output vector
  58  * @param[in]       blockSize number of samples in the vector
  59  * @return none.
  60  *
  61  * <b>Scaling and Overflow Behavior:</b>
  62  * \par
  63  * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.7 format.
  64  * These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format.
  65  */
  66
  67 void arm_scale_q7(
  68   q7_t * pSrc,
  69   q7_t scaleFract,
  70   int8_t shift,
  71   q7_t * pDst,
  72   uint32_t blockSize)
  73 {
  74   int8_t kShift = 7 - shift;                     /* shift to apply after scaling */
  75   uint32_t blkCnt;                               /* loop counter */
  76
  77 #ifndef ARM_MATH_CM0_FAMILY
  78
  79 /* Run the below code for Cortex-M4 and Cortex-M3 */
  80   q7_t in1, in2, in3, in4, out1, out2, out3, out4;      /* Temporary variables to store input & output */
  81
  82
  83   /*loop Unrolling */
  84   blkCnt = blockSize >> 2u;
  85
  86
  87   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
  88    ** a second loop below computes the remaining 1 to 3 samples. */
  89   while(blkCnt > 0u)
  90   {
  91     /* Reading 4 inputs from memory */
  92     in1 = *pSrc++;
  93     in2 = *pSrc++;
  94     in3 = *pSrc++;
  95     in4 = *pSrc++;
  96
  97     /* C = A * scale */
  98     /* Scale the inputs and then store the results in the temporary variables. */
  99     out1 = (q7_t) (__SSAT(((in1) * scaleFract) >> kShift, 8));
 100     out2 = (q7_t) (__SSAT(((in2) * scaleFract) >> kShift, 8));
 101     out3 = (q7_t) (__SSAT(((in3) * scaleFract) >> kShift, 8));
 102     out4 = (q7_t) (__SSAT(((in4) * scaleFract) >> kShift, 8));
 103
 104     /* Packing the individual outputs into 32bit and storing in
 105      * destination buffer in single write */
 106     *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
 107
 108     /* Decrement the loop counter */
 109     blkCnt--;
 110   }
 111
 112   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
 113    ** No loop unrolling is used. */
 114   blkCnt = blockSize % 0x4u;
 115
 116   while(blkCnt > 0u)
 117   {
 118     /* C = A * scale */
 119     /* Scale the input and then store the result in the destination buffer. */
 120     *pDst++ = (q7_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 8));
 121
 122     /* Decrement the loop counter */
 123     blkCnt--;
 124   }
 125
 126 #else
 127
 128   /* Run the below code for Cortex-M0 */
 129
 130   /* Initialize blkCnt with number of samples */
 131   blkCnt = blockSize;
 132
 133   while(blkCnt > 0u)
 134   {
 135     /* C = A * scale */
 136     /* Scale the input and then store the result in the destination buffer. */
 137     *pDst++ = (q7_t) (__SSAT((((q15_t) * pSrc++ * scaleFract) >> kShift), 8));
 138
 139     /* Decrement the loop counter */
 140     blkCnt--;
 141   }
 142
 143 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 144
 145 }
 146
 147 /**
 148  * @} end of scale group
 149  */