blob: 817210c97195a9fc12982e5aae879eb9070bea65 (
plain)
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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_mat_trans_q15.c
* Description: Q15 matrix transpose
*
* $Date: 27. January 2017
* $Revision: V.1.5.1
*
* Target Processor: Cortex-M cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved.
*
* SPDX-License-Identifier: Apache-2.0
*
* Licensed under the Apache License, Version 2.0 (the License); you may
* not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an AS IS BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include "arm_math.h"
/**
* @ingroup groupMatrix
*/
/**
* @addtogroup MatrixTrans
* @{
*/
/*
* @brief Q15 matrix transpose.
* @param[in] *pSrc points to the input matrix
* @param[out] *pDst points to the output matrix
* @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code>
* or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
*/
arm_status arm_mat_trans_q15(
const arm_matrix_instance_q15 * pSrc,
arm_matrix_instance_q15 * pDst)
{
q15_t *pSrcA = pSrc->pData; /* input data matrix pointer */
q15_t *pOut = pDst->pData; /* output data matrix pointer */
uint16_t nRows = pSrc->numRows; /* number of nRows */
uint16_t nColumns = pSrc->numCols; /* number of nColumns */
uint16_t col, row = nRows, i = 0U; /* row and column loop counters */
arm_status status; /* status of matrix transpose */
#if defined (ARM_MATH_DSP)
/* Run the below code for Cortex-M4 and Cortex-M3 */
#ifndef UNALIGNED_SUPPORT_DISABLE
q31_t in; /* variable to hold temporary output */
#else
q15_t in;
#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */
#ifdef ARM_MATH_MATRIX_CHECK
/* Check for matrix mismatch condition */
if ((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
{
/* Set status as ARM_MATH_SIZE_MISMATCH */
status = ARM_MATH_SIZE_MISMATCH;
}
else
#endif /* #ifdef ARM_MATH_MATRIX_CHECK */
{
/* Matrix transpose by exchanging the rows with columns */
/* row loop */
do
{
/* Apply loop unrolling and exchange the columns with row elements */
col = nColumns >> 2U;
/* The pointer pOut is set to starting address of the column being processed */
pOut = pDst->pData + i;
/* 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 (col > 0U)
{
#ifndef UNALIGNED_SUPPORT_DISABLE
/* Read two elements from the row */
in = *__SIMD32(pSrcA)++;
/* Unpack and store one element in the destination */
#ifndef ARM_MATH_BIG_ENDIAN
*pOut = (q15_t) in;
#else
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
/* Update the pointer pOut to point to the next row of the transposed matrix */
pOut += nRows;
/* Unpack and store the second element in the destination */
#ifndef ARM_MATH_BIG_ENDIAN
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
#else
*pOut = (q15_t) in;
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
/* Update the pointer pOut to point to the next row of the transposed matrix */
pOut += nRows;
/* Read two elements from the row */
#ifndef ARM_MATH_BIG_ENDIAN
in = *__SIMD32(pSrcA)++;
#else
in = *__SIMD32(pSrcA)++;
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
/* Unpack and store one element in the destination */
#ifndef ARM_MATH_BIG_ENDIAN
*pOut = (q15_t) in;
#else
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
/* Update the pointer pOut to point to the next row of the transposed matrix */
pOut += nRows;
/* Unpack and store the second element in the destination */
#ifndef ARM_MATH_BIG_ENDIAN
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16);
#else
*pOut = (q15_t) in;
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
#else
/* Read one element from the row */
in = *pSrcA++;
/* Store one element in the destination */
*pOut = in;
/* Update the pointer px to point to the next row of the transposed matrix */
pOut += nRows;
/* Read one element from the row */
in = *pSrcA++;
/* Store one element in the destination */
*pOut = in;
/* Update the pointer px to point to the next row of the transposed matrix */
pOut += nRows;
/* Read one element from the row */
in = *pSrcA++;
/* Store one element in the destination */
*pOut = in;
/* Update the pointer px to point to the next row of the transposed matrix */
pOut += nRows;
/* Read one element from the row */
in = *pSrcA++;
/* Store one element in the destination */
*pOut = in;
#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */
/* Update the pointer pOut to point to the next row of the transposed matrix */
pOut += nRows;
/* Decrement the column loop counter */
col--;
}
/* Perform matrix transpose for last 3 samples here. */
col = nColumns % 0x4U;
#else
/* Run the below code for Cortex-M0 */
#ifdef ARM_MATH_MATRIX_CHECK
/* Check for matrix mismatch condition */
if ((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows))
{
/* Set status as ARM_MATH_SIZE_MISMATCH */
status = ARM_MATH_SIZE_MISMATCH;
}
else
#endif /* #ifdef ARM_MATH_MATRIX_CHECK */
{
/* Matrix transpose by exchanging the rows with columns */
/* row loop */
do
{
/* The pointer pOut is set to starting address of the column being processed */
pOut = pDst->pData + i;
/* Initialize column loop counter */
col = nColumns;
#endif /* #if defined (ARM_MATH_DSP) */
while (col > 0U)
{
/* Read and store the input element in the destination */
*pOut = *pSrcA++;
/* Update the pointer pOut to point to the next row of the transposed matrix */
pOut += nRows;
/* Decrement the column loop counter */
col--;
}
i++;
/* Decrement the row loop counter */
row--;
} while (row > 0U);
/* set status as ARM_MATH_SUCCESS */
status = ARM_MATH_SUCCESS;
}
/* Return to application */
return (status);
}
/**
* @} end of MatrixTrans group
*/
|