Eli Hughes / CMSIS_DSP_401

V4.0.1 of the ARM CMSIS DSP libraries. Note that arm_bitreversal2.s, arm_cfft_f32.c and arm_rfft_fast_f32.c had to be removed. arm_bitreversal2.s will not assemble with the online tools. So, the fast f32 FFT functions are not yet available. All the other FFT functions are available.

Dependents:   MPU9150_Example fir_f32 fir_f32 MPU9150_nucleo_noni2cdev ... more

MatrixFunctions/arm_mat_scale_q31.c@0:3d9c67d97d6f, 2014-07-28 (annotated)

Committer:
emh203
Date:
Mon Jul 28 15:03:15 2014 +0000
Revision:
0:3d9c67d97d6f
1st working commit.   Had to remove arm_bitreversal2.s     arm_cfft_f32.c and arm_rfft_fast_f32.c.    The .s will not assemble.      For now I removed these functions so we could at least have a library for the other functions.

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emh203 0:3d9c67d97d6f 1 /* ----------------------------------------------------------------------
emh203 0:3d9c67d97d6f 2 * Copyright (C) 2010-2014 ARM Limited. All rights reserved.
emh203 0:3d9c67d97d6f 3 *
emh203 0:3d9c67d97d6f 4 * $Date: 12. March 2014
emh203 0:3d9c67d97d6f 5 * $Revision: V1.4.3
emh203 0:3d9c67d97d6f 6 *
emh203 0:3d9c67d97d6f 7 * Project: CMSIS DSP Library
emh203 0:3d9c67d97d6f 8 * Title: arm_mat_scale_q31.c
emh203 0:3d9c67d97d6f 9 *
emh203 0:3d9c67d97d6f 10 * Description: Multiplies a Q31 matrix by a scalar.
emh203 0:3d9c67d97d6f 11 *
emh203 0:3d9c67d97d6f 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emh203 0:3d9c67d97d6f 13 *
emh203 0:3d9c67d97d6f 14 * Redistribution and use in source and binary forms, with or without
emh203 0:3d9c67d97d6f 15 * modification, are permitted provided that the following conditions
emh203 0:3d9c67d97d6f 16 * are met:
emh203 0:3d9c67d97d6f 17 * - Redistributions of source code must retain the above copyright
emh203 0:3d9c67d97d6f 18 * notice, this list of conditions and the following disclaimer.
emh203 0:3d9c67d97d6f 19 * - Redistributions in binary form must reproduce the above copyright
emh203 0:3d9c67d97d6f 20 * notice, this list of conditions and the following disclaimer in
emh203 0:3d9c67d97d6f 21 * the documentation and/or other materials provided with the
emh203 0:3d9c67d97d6f 22 * distribution.
emh203 0:3d9c67d97d6f 23 * - Neither the name of ARM LIMITED nor the names of its contributors
emh203 0:3d9c67d97d6f 24 * may be used to endorse or promote products derived from this
emh203 0:3d9c67d97d6f 25 * software without specific prior written permission.
emh203 0:3d9c67d97d6f 26 *
emh203 0:3d9c67d97d6f 27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
emh203 0:3d9c67d97d6f 28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
emh203 0:3d9c67d97d6f 29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
emh203 0:3d9c67d97d6f 30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
emh203 0:3d9c67d97d6f 31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
emh203 0:3d9c67d97d6f 32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
emh203 0:3d9c67d97d6f 33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
emh203 0:3d9c67d97d6f 34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
emh203 0:3d9c67d97d6f 35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
emh203 0:3d9c67d97d6f 36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
emh203 0:3d9c67d97d6f 37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
emh203 0:3d9c67d97d6f 38 * POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------ */
emh203 0:3d9c67d97d6f 39
emh203 0:3d9c67d97d6f 40 #include "arm_math.h"
emh203 0:3d9c67d97d6f 41
emh203 0:3d9c67d97d6f 42 /**
emh203 0:3d9c67d97d6f 43 * @ingroup groupMatrix
emh203 0:3d9c67d97d6f 44 */
emh203 0:3d9c67d97d6f 45
emh203 0:3d9c67d97d6f 46 /**
emh203 0:3d9c67d97d6f 47 * @addtogroup MatrixScale
emh203 0:3d9c67d97d6f 48 * @{
emh203 0:3d9c67d97d6f 49 */
emh203 0:3d9c67d97d6f 50
emh203 0:3d9c67d97d6f 51 /**
emh203 0:3d9c67d97d6f 52 * @brief Q31 matrix scaling.
emh203 0:3d9c67d97d6f 53 * @param[in] *pSrc points to input matrix
emh203 0:3d9c67d97d6f 54 * @param[in] scaleFract fractional portion of the scale factor
emh203 0:3d9c67d97d6f 55 * @param[in] shift number of bits to shift the result by
emh203 0:3d9c67d97d6f 56 * @param[out] *pDst points to output matrix structure
emh203 0:3d9c67d97d6f 57 * @return The function returns either
emh203 0:3d9c67d97d6f 58 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emh203 0:3d9c67d97d6f 59 *
emh203 0:3d9c67d97d6f 60 * @details
emh203 0:3d9c67d97d6f 61 * <b>Scaling and Overflow Behavior:</b>
emh203 0:3d9c67d97d6f 62 * \par
emh203 0:3d9c67d97d6f 63 * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.
emh203 0:3d9c67d97d6f 64 * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.
emh203 0:3d9c67d97d6f 65 */
emh203 0:3d9c67d97d6f 66
emh203 0:3d9c67d97d6f 67 arm_status arm_mat_scale_q31(
emh203 0:3d9c67d97d6f 68 const arm_matrix_instance_q31 * pSrc,
emh203 0:3d9c67d97d6f 69 q31_t scaleFract,
emh203 0:3d9c67d97d6f 70 int32_t shift,
emh203 0:3d9c67d97d6f 71 arm_matrix_instance_q31 * pDst)
emh203 0:3d9c67d97d6f 72 {
emh203 0:3d9c67d97d6f 73 q31_t *pIn = pSrc->pData; /* input data matrix pointer */
emh203 0:3d9c67d97d6f 74 q31_t *pOut = pDst->pData; /* output data matrix pointer */
emh203 0:3d9c67d97d6f 75 uint32_t numSamples; /* total number of elements in the matrix */
emh203 0:3d9c67d97d6f 76 int32_t totShift = shift + 1; /* shift to apply after scaling */
emh203 0:3d9c67d97d6f 77 uint32_t blkCnt; /* loop counters */
emh203 0:3d9c67d97d6f 78 arm_status status; /* status of matrix scaling */
emh203 0:3d9c67d97d6f 79 q31_t in1, in2, out1; /* temporary variabels */
emh203 0:3d9c67d97d6f 80
emh203 0:3d9c67d97d6f 81 #ifndef ARM_MATH_CM0_FAMILY
emh203 0:3d9c67d97d6f 82
emh203 0:3d9c67d97d6f 83 q31_t in3, in4, out2, out3, out4; /* temporary variables */
emh203 0:3d9c67d97d6f 84
emh203 0:3d9c67d97d6f 85 #endif // #ifndef ARM_MAT_CM0
emh203 0:3d9c67d97d6f 86
emh203 0:3d9c67d97d6f 87 #ifdef ARM_MATH_MATRIX_CHECK
emh203 0:3d9c67d97d6f 88 /* Check for matrix mismatch */
emh203 0:3d9c67d97d6f 89 if((pSrc->numRows != pDst->numRows) || (pSrc->numCols != pDst->numCols))
emh203 0:3d9c67d97d6f 90 {
emh203 0:3d9c67d97d6f 91 /* Set status as ARM_MATH_SIZE_MISMATCH */
emh203 0:3d9c67d97d6f 92 status = ARM_MATH_SIZE_MISMATCH;
emh203 0:3d9c67d97d6f 93 }
emh203 0:3d9c67d97d6f 94 else
emh203 0:3d9c67d97d6f 95 #endif // #ifdef ARM_MATH_MATRIX_CHECK
emh203 0:3d9c67d97d6f 96 {
emh203 0:3d9c67d97d6f 97 /* Total number of samples in the input matrix */
emh203 0:3d9c67d97d6f 98 numSamples = (uint32_t) pSrc->numRows * pSrc->numCols;
emh203 0:3d9c67d97d6f 99
emh203 0:3d9c67d97d6f 100 #ifndef ARM_MATH_CM0_FAMILY
emh203 0:3d9c67d97d6f 101
emh203 0:3d9c67d97d6f 102 /* Run the below code for Cortex-M4 and Cortex-M3 */
emh203 0:3d9c67d97d6f 103
emh203 0:3d9c67d97d6f 104 /* Loop Unrolling */
emh203 0:3d9c67d97d6f 105 blkCnt = numSamples >> 2u;
emh203 0:3d9c67d97d6f 106
emh203 0:3d9c67d97d6f 107 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emh203 0:3d9c67d97d6f 108 ** a second loop below computes the remaining 1 to 3 samples. */
emh203 0:3d9c67d97d6f 109 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 110 {
emh203 0:3d9c67d97d6f 111 /* C(m,n) = A(m,n) * k */
emh203 0:3d9c67d97d6f 112 /* Read values from input */
emh203 0:3d9c67d97d6f 113 in1 = *pIn;
emh203 0:3d9c67d97d6f 114 in2 = *(pIn + 1);
emh203 0:3d9c67d97d6f 115 in3 = *(pIn + 2);
emh203 0:3d9c67d97d6f 116 in4 = *(pIn + 3);
emh203 0:3d9c67d97d6f 117
emh203 0:3d9c67d97d6f 118 /* multiply input with scaler value */
emh203 0:3d9c67d97d6f 119 in1 = ((q63_t) in1 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 120 in2 = ((q63_t) in2 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 121 in3 = ((q63_t) in3 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 122 in4 = ((q63_t) in4 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 123
emh203 0:3d9c67d97d6f 124 /* apply shifting */
emh203 0:3d9c67d97d6f 125 out1 = in1 << totShift;
emh203 0:3d9c67d97d6f 126 out2 = in2 << totShift;
emh203 0:3d9c67d97d6f 127
emh203 0:3d9c67d97d6f 128 /* saturate the results. */
emh203 0:3d9c67d97d6f 129 if(in1 != (out1 >> totShift))
emh203 0:3d9c67d97d6f 130 out1 = 0x7FFFFFFF ^ (in1 >> 31);
emh203 0:3d9c67d97d6f 131
emh203 0:3d9c67d97d6f 132 if(in2 != (out2 >> totShift))
emh203 0:3d9c67d97d6f 133 out2 = 0x7FFFFFFF ^ (in2 >> 31);
emh203 0:3d9c67d97d6f 134
emh203 0:3d9c67d97d6f 135 out3 = in3 << totShift;
emh203 0:3d9c67d97d6f 136 out4 = in4 << totShift;
emh203 0:3d9c67d97d6f 137
emh203 0:3d9c67d97d6f 138 *pOut = out1;
emh203 0:3d9c67d97d6f 139 *(pOut + 1) = out2;
emh203 0:3d9c67d97d6f 140
emh203 0:3d9c67d97d6f 141 if(in3 != (out3 >> totShift))
emh203 0:3d9c67d97d6f 142 out3 = 0x7FFFFFFF ^ (in3 >> 31);
emh203 0:3d9c67d97d6f 143
emh203 0:3d9c67d97d6f 144 if(in4 != (out4 >> totShift))
emh203 0:3d9c67d97d6f 145 out4 = 0x7FFFFFFF ^ (in4 >> 31);
emh203 0:3d9c67d97d6f 146
emh203 0:3d9c67d97d6f 147
emh203 0:3d9c67d97d6f 148 *(pOut + 2) = out3;
emh203 0:3d9c67d97d6f 149 *(pOut + 3) = out4;
emh203 0:3d9c67d97d6f 150
emh203 0:3d9c67d97d6f 151 /* update pointers to process next sampels */
emh203 0:3d9c67d97d6f 152 pIn += 4u;
emh203 0:3d9c67d97d6f 153 pOut += 4u;
emh203 0:3d9c67d97d6f 154
emh203 0:3d9c67d97d6f 155
emh203 0:3d9c67d97d6f 156 /* Decrement the numSamples loop counter */
emh203 0:3d9c67d97d6f 157 blkCnt--;
emh203 0:3d9c67d97d6f 158 }
emh203 0:3d9c67d97d6f 159
emh203 0:3d9c67d97d6f 160 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emh203 0:3d9c67d97d6f 161 ** No loop unrolling is used. */
emh203 0:3d9c67d97d6f 162 blkCnt = numSamples % 0x4u;
emh203 0:3d9c67d97d6f 163
emh203 0:3d9c67d97d6f 164 #else
emh203 0:3d9c67d97d6f 165
emh203 0:3d9c67d97d6f 166 /* Run the below code for Cortex-M0 */
emh203 0:3d9c67d97d6f 167
emh203 0:3d9c67d97d6f 168 /* Initialize blkCnt with number of samples */
emh203 0:3d9c67d97d6f 169 blkCnt = numSamples;
emh203 0:3d9c67d97d6f 170
emh203 0:3d9c67d97d6f 171 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emh203 0:3d9c67d97d6f 172
emh203 0:3d9c67d97d6f 173 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 174 {
emh203 0:3d9c67d97d6f 175 /* C(m,n) = A(m,n) * k */
emh203 0:3d9c67d97d6f 176 /* Scale, saturate and then store the results in the destination buffer. */
emh203 0:3d9c67d97d6f 177 in1 = *pIn++;
emh203 0:3d9c67d97d6f 178
emh203 0:3d9c67d97d6f 179 in2 = ((q63_t) in1 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 180
emh203 0:3d9c67d97d6f 181 out1 = in2 << totShift;
emh203 0:3d9c67d97d6f 182
emh203 0:3d9c67d97d6f 183 if(in2 != (out1 >> totShift))
emh203 0:3d9c67d97d6f 184 out1 = 0x7FFFFFFF ^ (in2 >> 31);
emh203 0:3d9c67d97d6f 185
emh203 0:3d9c67d97d6f 186 *pOut++ = out1;
emh203 0:3d9c67d97d6f 187
emh203 0:3d9c67d97d6f 188 /* Decrement the numSamples loop counter */
emh203 0:3d9c67d97d6f 189 blkCnt--;
emh203 0:3d9c67d97d6f 190 }
emh203 0:3d9c67d97d6f 191
emh203 0:3d9c67d97d6f 192 /* Set status as ARM_MATH_SUCCESS */
emh203 0:3d9c67d97d6f 193 status = ARM_MATH_SUCCESS;
emh203 0:3d9c67d97d6f 194 }
emh203 0:3d9c67d97d6f 195
emh203 0:3d9c67d97d6f 196 /* Return to application */
emh203 0:3d9c67d97d6f 197 return (status);
emh203 0:3d9c67d97d6f 198 }
emh203 0:3d9c67d97d6f 199
emh203 0:3d9c67d97d6f 200 /**
emh203 0:3d9c67d97d6f 201 * @} end of MatrixScale group
emh203 0:3d9c67d97d6f 202 */