Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_scale_q15.c@3:7a284390b0ce, 2013-11-08 (annotated)

Committer:
mbed_official
Date:
Fri Nov 08 13:45:10 2013 +0000
Revision:
3:7a284390b0ce
Parent:
2:da51fb522205 
Synchronized with git revision e69956aba2f68a2a26ac26b051f8d349deaa1ce8

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
mbed_official 3:7a284390b0ce 2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 3:7a284390b0ce 4 * $Date: 17. January 2013
mbed_official 3:7a284390b0ce 5 * $Revision: V1.4.1
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_mat_scale_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Multiplies a Q15 matrix by a scalar.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
mbed_official 3:7a284390b0ce 14 * Redistribution and use in source and binary forms, with or without
mbed_official 3:7a284390b0ce 15 * modification, are permitted provided that the following conditions
mbed_official 3:7a284390b0ce 16 * are met:
mbed_official 3:7a284390b0ce 17 * - Redistributions of source code must retain the above copyright
mbed_official 3:7a284390b0ce 18 * notice, this list of conditions and the following disclaimer.
mbed_official 3:7a284390b0ce 19 * - Redistributions in binary form must reproduce the above copyright
mbed_official 3:7a284390b0ce 20 * notice, this list of conditions and the following disclaimer in
mbed_official 3:7a284390b0ce 21 * the documentation and/or other materials provided with the
mbed_official 3:7a284390b0ce 22 * distribution.
mbed_official 3:7a284390b0ce 23 * - Neither the name of ARM LIMITED nor the names of its contributors
mbed_official 3:7a284390b0ce 24 * may be used to endorse or promote products derived from this
mbed_official 3:7a284390b0ce 25 * software without specific prior written permission.
mbed_official 3:7a284390b0ce 26 *
mbed_official 3:7a284390b0ce 27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
mbed_official 3:7a284390b0ce 28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
mbed_official 3:7a284390b0ce 29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
mbed_official 3:7a284390b0ce 30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
mbed_official 3:7a284390b0ce 31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
mbed_official 3:7a284390b0ce 32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
mbed_official 3:7a284390b0ce 33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
mbed_official 3:7a284390b0ce 34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
mbed_official 3:7a284390b0ce 35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
mbed_official 3:7a284390b0ce 36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
mbed_official 3:7a284390b0ce 37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
mbed_official 3:7a284390b0ce 38 * POSSIBILITY OF SUCH DAMAGE.
emilmont 1:fdd22bb7aa52 39 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 40
emilmont 1:fdd22bb7aa52 41 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @addtogroup MatrixScale
emilmont 1:fdd22bb7aa52 49 * @{
emilmont 1:fdd22bb7aa52 50 */
emilmont 1:fdd22bb7aa52 51
emilmont 1:fdd22bb7aa52 52 /**
emilmont 1:fdd22bb7aa52 53 * @brief Q15 matrix scaling.
emilmont 1:fdd22bb7aa52 54 * @param[in] *pSrc points to input matrix
emilmont 1:fdd22bb7aa52 55 * @param[in] scaleFract fractional portion of the scale factor
emilmont 1:fdd22bb7aa52 56 * @param[in] shift number of bits to shift the result by
emilmont 1:fdd22bb7aa52 57 * @param[out] *pDst points to output matrix structure
emilmont 2:da51fb522205 58 * @return The function returns either
emilmont 1:fdd22bb7aa52 59 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 60 *
emilmont 1:fdd22bb7aa52 61 * @details
emilmont 1:fdd22bb7aa52 62 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 63 * \par
emilmont 1:fdd22bb7aa52 64 * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.
emilmont 1:fdd22bb7aa52 65 * These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.
emilmont 1:fdd22bb7aa52 66 */
emilmont 1:fdd22bb7aa52 67
emilmont 1:fdd22bb7aa52 68 arm_status arm_mat_scale_q15(
emilmont 1:fdd22bb7aa52 69 const arm_matrix_instance_q15 * pSrc,
emilmont 1:fdd22bb7aa52 70 q15_t scaleFract,
emilmont 1:fdd22bb7aa52 71 int32_t shift,
emilmont 1:fdd22bb7aa52 72 arm_matrix_instance_q15 * pDst)
emilmont 1:fdd22bb7aa52 73 {
emilmont 1:fdd22bb7aa52 74 q15_t *pIn = pSrc->pData; /* input data matrix pointer */
emilmont 1:fdd22bb7aa52 75 q15_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 76 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 77 int32_t totShift = 15 - shift; /* total shift to apply after scaling */
emilmont 1:fdd22bb7aa52 78 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 79 arm_status status; /* status of matrix scaling */
emilmont 1:fdd22bb7aa52 80
mbed_official 3:7a284390b0ce 81 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 q15_t in1, in2, in3, in4;
emilmont 1:fdd22bb7aa52 84 q31_t out1, out2, out3, out4;
emilmont 1:fdd22bb7aa52 85 q31_t inA1, inA2;
emilmont 1:fdd22bb7aa52 86
mbed_official 3:7a284390b0ce 87 #endif // #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 88
emilmont 1:fdd22bb7aa52 89 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 90 /* Check for matrix mismatch */
emilmont 1:fdd22bb7aa52 91 if((pSrc->numRows != pDst->numRows) || (pSrc->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 92 {
emilmont 1:fdd22bb7aa52 93 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 94 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 95 }
emilmont 1:fdd22bb7aa52 96 else
emilmont 1:fdd22bb7aa52 97 #endif // #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 98 {
emilmont 1:fdd22bb7aa52 99 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 100 numSamples = (uint32_t) pSrc->numRows * pSrc->numCols;
emilmont 1:fdd22bb7aa52 101
mbed_official 3:7a284390b0ce 102 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 105 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 106 blkCnt = numSamples >> 2;
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 109 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 110 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 111 {
emilmont 1:fdd22bb7aa52 112 /* C(m,n) = A(m,n) * k */
emilmont 1:fdd22bb7aa52 113 /* Scale, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 114 /* Reading 2 inputs from memory */
emilmont 1:fdd22bb7aa52 115 inA1 = _SIMD32_OFFSET(pIn);
emilmont 1:fdd22bb7aa52 116 inA2 = _SIMD32_OFFSET(pIn + 2);
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* C = A * scale */
emilmont 1:fdd22bb7aa52 119 /* Scale the inputs and then store the 2 results in the destination buffer
emilmont 1:fdd22bb7aa52 120 * in single cycle by packing the outputs */
emilmont 1:fdd22bb7aa52 121 out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract);
emilmont 1:fdd22bb7aa52 122 out2 = (q31_t) ((q15_t) inA1 * scaleFract);
emilmont 1:fdd22bb7aa52 123 out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract);
emilmont 1:fdd22bb7aa52 124 out4 = (q31_t) ((q15_t) inA2 * scaleFract);
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 out1 = out1 >> totShift;
emilmont 1:fdd22bb7aa52 127 inA1 = _SIMD32_OFFSET(pIn + 4);
emilmont 1:fdd22bb7aa52 128 out2 = out2 >> totShift;
emilmont 1:fdd22bb7aa52 129 inA2 = _SIMD32_OFFSET(pIn + 6);
emilmont 1:fdd22bb7aa52 130 out3 = out3 >> totShift;
emilmont 1:fdd22bb7aa52 131 out4 = out4 >> totShift;
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 in1 = (q15_t) (__SSAT(out1, 16));
emilmont 1:fdd22bb7aa52 134 in2 = (q15_t) (__SSAT(out2, 16));
emilmont 1:fdd22bb7aa52 135 in3 = (q15_t) (__SSAT(out3, 16));
emilmont 1:fdd22bb7aa52 136 in4 = (q15_t) (__SSAT(out4, 16));
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 _SIMD32_OFFSET(pOut) = __PKHBT(in2, in1, 16);
emilmont 1:fdd22bb7aa52 139 _SIMD32_OFFSET(pOut + 2) = __PKHBT(in4, in3, 16);
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 142 pIn += 4u;
emilmont 1:fdd22bb7aa52 143 pOut += 4u;
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 147 blkCnt--;
emilmont 1:fdd22bb7aa52 148 }
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 151 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 152 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 #else
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 157
emilmont 1:fdd22bb7aa52 158 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 159 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 160
mbed_official 3:7a284390b0ce 161 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 162
emilmont 1:fdd22bb7aa52 163 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 164 {
emilmont 1:fdd22bb7aa52 165 /* C(m,n) = A(m,n) * k */
emilmont 1:fdd22bb7aa52 166 /* Scale, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 167 *pOut++ =
emilmont 1:fdd22bb7aa52 168 (q15_t) (__SSAT(((q31_t) (*pIn++) * scaleFract) >> totShift, 16));
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 171 blkCnt--;
emilmont 1:fdd22bb7aa52 172 }
emilmont 1:fdd22bb7aa52 173 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 174 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 175 }
emilmont 1:fdd22bb7aa52 176
emilmont 1:fdd22bb7aa52 177 /* Return to application */
emilmont 1:fdd22bb7aa52 178 return (status);
emilmont 1:fdd22bb7aa52 179 }
emilmont 1:fdd22bb7aa52 180
emilmont 1:fdd22bb7aa52 181 /**
emilmont 1:fdd22bb7aa52 182 * @} end of MatrixScale group
emilmont 1:fdd22bb7aa52 183 */