Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_scale_q31.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_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Multiplies a Q31 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 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 41
emilmont 1:fdd22bb7aa52 42 /**
emilmont 1:fdd22bb7aa52 43 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 44 */
emilmont 1:fdd22bb7aa52 45
emilmont 1:fdd22bb7aa52 46 /**
emilmont 1:fdd22bb7aa52 47 * @addtogroup MatrixScale
emilmont 1:fdd22bb7aa52 48 * @{
emilmont 1:fdd22bb7aa52 49 */
emilmont 1:fdd22bb7aa52 50
emilmont 1:fdd22bb7aa52 51 /**
emilmont 1:fdd22bb7aa52 52 * @brief Q31 matrix scaling.
emilmont 1:fdd22bb7aa52 53 * @param[in] *pSrc points to input matrix
emilmont 1:fdd22bb7aa52 54 * @param[in] scaleFract fractional portion of the scale factor
emilmont 1:fdd22bb7aa52 55 * @param[in] shift number of bits to shift the result by
emilmont 1:fdd22bb7aa52 56 * @param[out] *pDst points to output matrix structure
emilmont 2:da51fb522205 57 * @return The function returns either
emilmont 1:fdd22bb7aa52 58 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 59 *
emilmont 1:fdd22bb7aa52 60 * @details
emilmont 1:fdd22bb7aa52 61 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 62 * \par
emilmont 1:fdd22bb7aa52 63 * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.
emilmont 1:fdd22bb7aa52 64 * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.
emilmont 1:fdd22bb7aa52 65 */
emilmont 1:fdd22bb7aa52 66
emilmont 1:fdd22bb7aa52 67 arm_status arm_mat_scale_q31(
emilmont 1:fdd22bb7aa52 68 const arm_matrix_instance_q31 * pSrc,
emilmont 1:fdd22bb7aa52 69 q31_t scaleFract,
emilmont 1:fdd22bb7aa52 70 int32_t shift,
emilmont 1:fdd22bb7aa52 71 arm_matrix_instance_q31 * pDst)
emilmont 1:fdd22bb7aa52 72 {
emilmont 1:fdd22bb7aa52 73 q31_t *pIn = pSrc->pData; /* input data matrix pointer */
emilmont 1:fdd22bb7aa52 74 q31_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 75 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 76 int32_t totShift = shift + 1; /* shift to apply after scaling */
emilmont 1:fdd22bb7aa52 77 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 78 arm_status status; /* status of matrix scaling */
emilmont 1:fdd22bb7aa52 79 q31_t in1, in2, out1; /* temporary variabels */
emilmont 1:fdd22bb7aa52 80
mbed_official 3:7a284390b0ce 81 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 q31_t in3, in4, out2, out3, out4; /* temporary variables */
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 #endif // #ifndef ARM_MAT_CM0
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 88 /* Check for matrix mismatch */
emilmont 1:fdd22bb7aa52 89 if((pSrc->numRows != pDst->numRows) || (pSrc->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 90 {
emilmont 1:fdd22bb7aa52 91 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 92 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 93 }
emilmont 1:fdd22bb7aa52 94 else
emilmont 1:fdd22bb7aa52 95 #endif // #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 96 {
emilmont 1:fdd22bb7aa52 97 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 98 numSamples = (uint32_t) pSrc->numRows * pSrc->numCols;
emilmont 1:fdd22bb7aa52 99
mbed_official 3:7a284390b0ce 100 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 105 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 108 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 109 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 110 {
emilmont 1:fdd22bb7aa52 111 /* C(m,n) = A(m,n) * k */
emilmont 1:fdd22bb7aa52 112 /* Read values from input */
emilmont 1:fdd22bb7aa52 113 in1 = *pIn;
emilmont 1:fdd22bb7aa52 114 in2 = *(pIn + 1);
emilmont 1:fdd22bb7aa52 115 in3 = *(pIn + 2);
emilmont 1:fdd22bb7aa52 116 in4 = *(pIn + 3);
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* multiply input with scaler value */
emilmont 1:fdd22bb7aa52 119 in1 = ((q63_t) in1 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 120 in2 = ((q63_t) in2 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 121 in3 = ((q63_t) in3 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 122 in4 = ((q63_t) in4 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 123
emilmont 1:fdd22bb7aa52 124 /* apply shifting */
emilmont 1:fdd22bb7aa52 125 out1 = in1 << totShift;
emilmont 1:fdd22bb7aa52 126 out2 = in2 << totShift;
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 /* saturate the results. */
emilmont 1:fdd22bb7aa52 129 if(in1 != (out1 >> totShift))
emilmont 1:fdd22bb7aa52 130 out1 = 0x7FFFFFFF ^ (in1 >> 31);
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 if(in2 != (out2 >> totShift))
emilmont 1:fdd22bb7aa52 133 out2 = 0x7FFFFFFF ^ (in2 >> 31);
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 out3 = in3 << totShift;
emilmont 1:fdd22bb7aa52 136 out4 = in4 << totShift;
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 *pOut = out1;
emilmont 1:fdd22bb7aa52 139 *(pOut + 1) = out2;
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 if(in3 != (out3 >> totShift))
emilmont 1:fdd22bb7aa52 142 out3 = 0x7FFFFFFF ^ (in3 >> 31);
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 if(in4 != (out4 >> totShift))
emilmont 1:fdd22bb7aa52 145 out4 = 0x7FFFFFFF ^ (in4 >> 31);
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 *(pOut + 2) = out3;
emilmont 1:fdd22bb7aa52 149 *(pOut + 3) = out4;
emilmont 1:fdd22bb7aa52 150
emilmont 1:fdd22bb7aa52 151 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 152 pIn += 4u;
emilmont 1:fdd22bb7aa52 153 pOut += 4u;
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 157 blkCnt--;
emilmont 1:fdd22bb7aa52 158 }
emilmont 1:fdd22bb7aa52 159
emilmont 1:fdd22bb7aa52 160 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 161 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 162 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164 #else
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 167
emilmont 1:fdd22bb7aa52 168 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 169 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 170
mbed_official 3:7a284390b0ce 171 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 172
emilmont 1:fdd22bb7aa52 173 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 174 {
emilmont 1:fdd22bb7aa52 175 /* C(m,n) = A(m,n) * k */
emilmont 1:fdd22bb7aa52 176 /* Scale, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 177 in1 = *pIn++;
emilmont 1:fdd22bb7aa52 178
emilmont 1:fdd22bb7aa52 179 in2 = ((q63_t) in1 * scaleFract) >> 32;
emilmont 1:fdd22bb7aa52 180
emilmont 1:fdd22bb7aa52 181 out1 = in2 << totShift;
emilmont 1:fdd22bb7aa52 182
emilmont 1:fdd22bb7aa52 183 if(in2 != (out1 >> totShift))
emilmont 1:fdd22bb7aa52 184 out1 = 0x7FFFFFFF ^ (in2 >> 31);
emilmont 1:fdd22bb7aa52 185
emilmont 1:fdd22bb7aa52 186 *pOut++ = out1;
emilmont 1:fdd22bb7aa52 187
emilmont 1:fdd22bb7aa52 188 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 189 blkCnt--;
emilmont 1:fdd22bb7aa52 190 }
emilmont 1:fdd22bb7aa52 191
emilmont 1:fdd22bb7aa52 192 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 193 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 194 }
emilmont 1:fdd22bb7aa52 195
emilmont 1:fdd22bb7aa52 196 /* Return to application */
emilmont 1:fdd22bb7aa52 197 return (status);
emilmont 1:fdd22bb7aa52 198 }
emilmont 1:fdd22bb7aa52 199
emilmont 1:fdd22bb7aa52 200 /**
emilmont 1:fdd22bb7aa52 201 * @} end of MatrixScale group
emilmont 1:fdd22bb7aa52 202 */