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

BasicMathFunctions/arm_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_scale_q31.c
emh203 0:3d9c67d97d6f 9 *
emh203 0:3d9c67d97d6f 10 * Description: Multiplies a Q31 vector 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
emh203 0:3d9c67d97d6f 41 #include "arm_math.h"
emh203 0:3d9c67d97d6f 42
emh203 0:3d9c67d97d6f 43 /**
emh203 0:3d9c67d97d6f 44 * @ingroup groupMath
emh203 0:3d9c67d97d6f 45 */
emh203 0:3d9c67d97d6f 46
emh203 0:3d9c67d97d6f 47 /**
emh203 0:3d9c67d97d6f 48 * @addtogroup scale
emh203 0:3d9c67d97d6f 49 * @{
emh203 0:3d9c67d97d6f 50 */
emh203 0:3d9c67d97d6f 51
emh203 0:3d9c67d97d6f 52 /**
emh203 0:3d9c67d97d6f 53 * @brief Multiplies a Q31 vector by a scalar.
emh203 0:3d9c67d97d6f 54 * @param[in] *pSrc points to the input vector
emh203 0:3d9c67d97d6f 55 * @param[in] scaleFract fractional portion of the scale value
emh203 0:3d9c67d97d6f 56 * @param[in] shift number of bits to shift the result by
emh203 0:3d9c67d97d6f 57 * @param[out] *pDst points to the output vector
emh203 0:3d9c67d97d6f 58 * @param[in] blockSize number of samples in the vector
emh203 0:3d9c67d97d6f 59 * @return none.
emh203 0:3d9c67d97d6f 60 *
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 void arm_scale_q31(
emh203 0:3d9c67d97d6f 68 q31_t * pSrc,
emh203 0:3d9c67d97d6f 69 q31_t scaleFract,
emh203 0:3d9c67d97d6f 70 int8_t shift,
emh203 0:3d9c67d97d6f 71 q31_t * pDst,
emh203 0:3d9c67d97d6f 72 uint32_t blockSize)
emh203 0:3d9c67d97d6f 73 {
emh203 0:3d9c67d97d6f 74 int8_t kShift = shift + 1; /* Shift to apply after scaling */
emh203 0:3d9c67d97d6f 75 int8_t sign = (kShift & 0x80);
emh203 0:3d9c67d97d6f 76 uint32_t blkCnt; /* loop counter */
emh203 0:3d9c67d97d6f 77 q31_t in, out;
emh203 0:3d9c67d97d6f 78
emh203 0:3d9c67d97d6f 79 #ifndef ARM_MATH_CM0_FAMILY
emh203 0:3d9c67d97d6f 80
emh203 0:3d9c67d97d6f 81 /* Run the below code for Cortex-M4 and Cortex-M3 */
emh203 0:3d9c67d97d6f 82
emh203 0:3d9c67d97d6f 83 q31_t in1, in2, in3, in4; /* temporary input variables */
emh203 0:3d9c67d97d6f 84 q31_t out1, out2, out3, out4; /* temporary output variabels */
emh203 0:3d9c67d97d6f 85
emh203 0:3d9c67d97d6f 86
emh203 0:3d9c67d97d6f 87 /*loop Unrolling */
emh203 0:3d9c67d97d6f 88 blkCnt = blockSize >> 2u;
emh203 0:3d9c67d97d6f 89
emh203 0:3d9c67d97d6f 90 if(sign == 0u)
emh203 0:3d9c67d97d6f 91 {
emh203 0:3d9c67d97d6f 92 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emh203 0:3d9c67d97d6f 93 ** a second loop below computes the remaining 1 to 3 samples. */
emh203 0:3d9c67d97d6f 94 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 95 {
emh203 0:3d9c67d97d6f 96 /* read four inputs from source */
emh203 0:3d9c67d97d6f 97 in1 = *pSrc;
emh203 0:3d9c67d97d6f 98 in2 = *(pSrc + 1);
emh203 0:3d9c67d97d6f 99 in3 = *(pSrc + 2);
emh203 0:3d9c67d97d6f 100 in4 = *(pSrc + 3);
emh203 0:3d9c67d97d6f 101
emh203 0:3d9c67d97d6f 102 /* multiply input with scaler value */
emh203 0:3d9c67d97d6f 103 in1 = ((q63_t) in1 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 104 in2 = ((q63_t) in2 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 105 in3 = ((q63_t) in3 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 106 in4 = ((q63_t) in4 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 107
emh203 0:3d9c67d97d6f 108 /* apply shifting */
emh203 0:3d9c67d97d6f 109 out1 = in1 << kShift;
emh203 0:3d9c67d97d6f 110 out2 = in2 << kShift;
emh203 0:3d9c67d97d6f 111
emh203 0:3d9c67d97d6f 112 /* saturate the results. */
emh203 0:3d9c67d97d6f 113 if(in1 != (out1 >> kShift))
emh203 0:3d9c67d97d6f 114 out1 = 0x7FFFFFFF ^ (in1 >> 31);
emh203 0:3d9c67d97d6f 115
emh203 0:3d9c67d97d6f 116 if(in2 != (out2 >> kShift))
emh203 0:3d9c67d97d6f 117 out2 = 0x7FFFFFFF ^ (in2 >> 31);
emh203 0:3d9c67d97d6f 118
emh203 0:3d9c67d97d6f 119 out3 = in3 << kShift;
emh203 0:3d9c67d97d6f 120 out4 = in4 << kShift;
emh203 0:3d9c67d97d6f 121
emh203 0:3d9c67d97d6f 122 *pDst = out1;
emh203 0:3d9c67d97d6f 123 *(pDst + 1) = out2;
emh203 0:3d9c67d97d6f 124
emh203 0:3d9c67d97d6f 125 if(in3 != (out3 >> kShift))
emh203 0:3d9c67d97d6f 126 out3 = 0x7FFFFFFF ^ (in3 >> 31);
emh203 0:3d9c67d97d6f 127
emh203 0:3d9c67d97d6f 128 if(in4 != (out4 >> kShift))
emh203 0:3d9c67d97d6f 129 out4 = 0x7FFFFFFF ^ (in4 >> 31);
emh203 0:3d9c67d97d6f 130
emh203 0:3d9c67d97d6f 131 /* Store result destination */
emh203 0:3d9c67d97d6f 132 *(pDst + 2) = out3;
emh203 0:3d9c67d97d6f 133 *(pDst + 3) = out4;
emh203 0:3d9c67d97d6f 134
emh203 0:3d9c67d97d6f 135 /* Update pointers to process next sampels */
emh203 0:3d9c67d97d6f 136 pSrc += 4u;
emh203 0:3d9c67d97d6f 137 pDst += 4u;
emh203 0:3d9c67d97d6f 138
emh203 0:3d9c67d97d6f 139 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 140 blkCnt--;
emh203 0:3d9c67d97d6f 141 }
emh203 0:3d9c67d97d6f 142
emh203 0:3d9c67d97d6f 143 }
emh203 0:3d9c67d97d6f 144 else
emh203 0:3d9c67d97d6f 145 {
emh203 0:3d9c67d97d6f 146 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emh203 0:3d9c67d97d6f 147 ** a second loop below computes the remaining 1 to 3 samples. */
emh203 0:3d9c67d97d6f 148 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 149 {
emh203 0:3d9c67d97d6f 150 /* read four inputs from source */
emh203 0:3d9c67d97d6f 151 in1 = *pSrc;
emh203 0:3d9c67d97d6f 152 in2 = *(pSrc + 1);
emh203 0:3d9c67d97d6f 153 in3 = *(pSrc + 2);
emh203 0:3d9c67d97d6f 154 in4 = *(pSrc + 3);
emh203 0:3d9c67d97d6f 155
emh203 0:3d9c67d97d6f 156 /* multiply input with scaler value */
emh203 0:3d9c67d97d6f 157 in1 = ((q63_t) in1 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 158 in2 = ((q63_t) in2 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 159 in3 = ((q63_t) in3 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 160 in4 = ((q63_t) in4 * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 161
emh203 0:3d9c67d97d6f 162 /* apply shifting */
emh203 0:3d9c67d97d6f 163 out1 = in1 >> -kShift;
emh203 0:3d9c67d97d6f 164 out2 = in2 >> -kShift;
emh203 0:3d9c67d97d6f 165
emh203 0:3d9c67d97d6f 166 out3 = in3 >> -kShift;
emh203 0:3d9c67d97d6f 167 out4 = in4 >> -kShift;
emh203 0:3d9c67d97d6f 168
emh203 0:3d9c67d97d6f 169 /* Store result destination */
emh203 0:3d9c67d97d6f 170 *pDst = out1;
emh203 0:3d9c67d97d6f 171 *(pDst + 1) = out2;
emh203 0:3d9c67d97d6f 172
emh203 0:3d9c67d97d6f 173 *(pDst + 2) = out3;
emh203 0:3d9c67d97d6f 174 *(pDst + 3) = out4;
emh203 0:3d9c67d97d6f 175
emh203 0:3d9c67d97d6f 176 /* Update pointers to process next sampels */
emh203 0:3d9c67d97d6f 177 pSrc += 4u;
emh203 0:3d9c67d97d6f 178 pDst += 4u;
emh203 0:3d9c67d97d6f 179
emh203 0:3d9c67d97d6f 180 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 181 blkCnt--;
emh203 0:3d9c67d97d6f 182 }
emh203 0:3d9c67d97d6f 183 }
emh203 0:3d9c67d97d6f 184 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emh203 0:3d9c67d97d6f 185 ** No loop unrolling is used. */
emh203 0:3d9c67d97d6f 186 blkCnt = blockSize % 0x4u;
emh203 0:3d9c67d97d6f 187
emh203 0:3d9c67d97d6f 188 #else
emh203 0:3d9c67d97d6f 189
emh203 0:3d9c67d97d6f 190 /* Run the below code for Cortex-M0 */
emh203 0:3d9c67d97d6f 191
emh203 0:3d9c67d97d6f 192 /* Initialize blkCnt with number of samples */
emh203 0:3d9c67d97d6f 193 blkCnt = blockSize;
emh203 0:3d9c67d97d6f 194
emh203 0:3d9c67d97d6f 195 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emh203 0:3d9c67d97d6f 196
emh203 0:3d9c67d97d6f 197 if(sign == 0)
emh203 0:3d9c67d97d6f 198 {
emh203 0:3d9c67d97d6f 199 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 200 {
emh203 0:3d9c67d97d6f 201 /* C = A * scale */
emh203 0:3d9c67d97d6f 202 /* Scale the input and then store the result in the destination buffer. */
emh203 0:3d9c67d97d6f 203 in = *pSrc++;
emh203 0:3d9c67d97d6f 204 in = ((q63_t) in * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 205
emh203 0:3d9c67d97d6f 206 out = in << kShift;
emh203 0:3d9c67d97d6f 207
emh203 0:3d9c67d97d6f 208 if(in != (out >> kShift))
emh203 0:3d9c67d97d6f 209 out = 0x7FFFFFFF ^ (in >> 31);
emh203 0:3d9c67d97d6f 210
emh203 0:3d9c67d97d6f 211 *pDst++ = out;
emh203 0:3d9c67d97d6f 212
emh203 0:3d9c67d97d6f 213 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 214 blkCnt--;
emh203 0:3d9c67d97d6f 215 }
emh203 0:3d9c67d97d6f 216 }
emh203 0:3d9c67d97d6f 217 else
emh203 0:3d9c67d97d6f 218 {
emh203 0:3d9c67d97d6f 219 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 220 {
emh203 0:3d9c67d97d6f 221 /* C = A * scale */
emh203 0:3d9c67d97d6f 222 /* Scale the input and then store the result in the destination buffer. */
emh203 0:3d9c67d97d6f 223 in = *pSrc++;
emh203 0:3d9c67d97d6f 224 in = ((q63_t) in * scaleFract) >> 32;
emh203 0:3d9c67d97d6f 225
emh203 0:3d9c67d97d6f 226 out = in >> -kShift;
emh203 0:3d9c67d97d6f 227
emh203 0:3d9c67d97d6f 228 *pDst++ = out;
emh203 0:3d9c67d97d6f 229
emh203 0:3d9c67d97d6f 230 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 231 blkCnt--;
emh203 0:3d9c67d97d6f 232 }
emh203 0:3d9c67d97d6f 233
emh203 0:3d9c67d97d6f 234 }
emh203 0:3d9c67d97d6f 235 }
emh203 0:3d9c67d97d6f 236
emh203 0:3d9c67d97d6f 237 /**
emh203 0:3d9c67d97d6f 238 * @} end of scale group
emh203 0:3d9c67d97d6f 239 */