1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
|
/* ----------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. February 2012
* $Revision: V1.1.0
*
* Project: CMSIS DSP Library
* Title: arm_scale_q31.c
*
* Description: Multiplies a Q31 vector by a scalar.
*
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*
* Version 1.1.0 2012/02/15
* Updated with more optimizations, bug fixes and minor API changes.
*
* Version 1.0.10 2011/7/15
* Big Endian support added and Merged M0 and M3/M4 Source code.
*
* Version 1.0.3 2010/11/29
* Re-organized the CMSIS folders and updated documentation.
*
* Version 1.0.2 2010/11/11
* Documentation updated.
*
* Version 1.0.1 2010/10/05
* Production release and review comments incorporated.
*
* Version 1.0.0 2010/09/20
* Production release and review comments incorporated
*
* Version 0.0.7 2010/06/10
* Misra-C changes done
* -------------------------------------------------------------------- */
#include "arm_math.h"
/**
* @ingroup groupMath
*/
/**
* @addtogroup scale
* @{
*/
/**
* @brief Multiplies a Q31 vector by a scalar.
* @param[in] *pSrc points to the input vector
* @param[in] scaleFract fractional portion of the scale value
* @param[in] shift number of bits to shift the result by
* @param[out] *pDst points to the output vector
* @param[in] blockSize number of samples in the vector
* @return none.
*
* <b>Scaling and Overflow Behavior:</b>
* \par
* The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.
* These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.
*/
void arm_scale_q31(
q31_t * pSrc,
q31_t scaleFract,
int8_t shift,
q31_t * pDst,
uint32_t blockSize)
{
int8_t kShift = shift + 1; /* Shift to apply after scaling */
int8_t sign = (kShift & 0x80);
uint32_t blkCnt; /* loop counter */
q31_t in, out;
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t in1, in2, in3, in4; /* temporary input variables */
q31_t out1, out2, out3, out4; /* temporary output variabels */
/*loop Unrolling */
blkCnt = blockSize >> 2u;
if(sign == 0u)
{
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* read four inputs from source */
in1 = *pSrc;
in2 = *(pSrc + 1);
in3 = *(pSrc + 2);
in4 = *(pSrc + 3);
/* multiply input with scaler value */
in1 = ((q63_t) in1 * scaleFract) >> 32;
in2 = ((q63_t) in2 * scaleFract) >> 32;
in3 = ((q63_t) in3 * scaleFract) >> 32;
in4 = ((q63_t) in4 * scaleFract) >> 32;
/* apply shifting */
out1 = in1 << kShift;
out2 = in2 << kShift;
/* saturate the results. */
if(in1 != (out1 >> kShift))
out1 = 0x7FFFFFFF ^ (in1 >> 31);
if(in2 != (out2 >> kShift))
out2 = 0x7FFFFFFF ^ (in2 >> 31);
out3 = in3 << kShift;
out4 = in4 << kShift;
*pDst = out1;
*(pDst + 1) = out2;
if(in3 != (out3 >> kShift))
out3 = 0x7FFFFFFF ^ (in3 >> 31);
if(in4 != (out4 >> kShift))
out4 = 0x7FFFFFFF ^ (in4 >> 31);
/* Store result destination */
*(pDst + 2) = out3;
*(pDst + 3) = out4;
/* Update pointers to process next sampels */
pSrc += 4u;
pDst += 4u;
/* Decrement the loop counter */
blkCnt--;
}
}
else
{
kShift = -kShift;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* read four inputs from source */
in1 = *pSrc;
in2 = *(pSrc + 1);
in3 = *(pSrc + 2);
in4 = *(pSrc + 3);
/* multiply input with scaler value */
in1 = ((q63_t) in1 * scaleFract) >> 32;
in2 = ((q63_t) in2 * scaleFract) >> 32;
in3 = ((q63_t) in3 * scaleFract) >> 32;
in4 = ((q63_t) in4 * scaleFract) >> 32;
/* apply shifting */
out1 = in1 >> kShift;
out2 = in2 >> kShift;
out3 = in3 >> kShift;
out4 = in4 >> kShift;
/* Store result destination */
*pDst = out1;
*(pDst + 1) = out2;
*(pDst + 2) = out3;
*(pDst + 3) = out4;
/* Update pointers to process next sampels */
pSrc += 4u;
pDst += 4u;
/* Decrement the loop counter */
blkCnt--;
}
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4u;
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif /* #ifndef ARM_MATH_CM0 */
while(blkCnt > 0u)
{
/* C = A * scale */
/* Scale the input and then store the result in the destination buffer. */
in = *pSrc++;
in = ((q63_t) in * scaleFract) >> 32;
if(sign == 0)
{
out = in << kShift;
if(in != (out >> kShift))
out = 0x7FFFFFFF ^ (in >> 31);
}
else
{
out = in >> kShift;
}
*pDst++ = out;
/* Decrement the loop counter */
blkCnt--;
}
}
/**
* @} end of scale group
*/
|
