提交 | 用户 | age
|
8b51c7
|
1 |
/* ---------------------------------------------------------------------- |
Q |
2 |
* Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
|
3 |
* |
|
4 |
* $Date: 19. March 2015 |
|
5 |
* $Revision: V.1.4.5 |
|
6 |
* |
|
7 |
* Project: CMSIS DSP Library |
|
8 |
* Title: arm_mat_trans_q15.c |
|
9 |
* |
|
10 |
* Description: Q15 matrix transpose. |
|
11 |
* |
|
12 |
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
|
13 |
* |
|
14 |
* Redistribution and use in source and binary forms, with or without |
|
15 |
* modification, are permitted provided that the following conditions |
|
16 |
* are met: |
|
17 |
* - Redistributions of source code must retain the above copyright |
|
18 |
* notice, this list of conditions and the following disclaimer. |
|
19 |
* - Redistributions in binary form must reproduce the above copyright |
|
20 |
* notice, this list of conditions and the following disclaimer in |
|
21 |
* the documentation and/or other materials provided with the |
|
22 |
* distribution. |
|
23 |
* - Neither the name of ARM LIMITED nor the names of its contributors |
|
24 |
* may be used to endorse or promote products derived from this |
|
25 |
* software without specific prior written permission. |
|
26 |
* |
|
27 |
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|
28 |
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|
29 |
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
|
30 |
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
|
31 |
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
|
32 |
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
|
33 |
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
|
34 |
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
|
35 |
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
|
36 |
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
|
37 |
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
|
38 |
* POSSIBILITY OF SUCH DAMAGE. |
|
39 |
* -------------------------------------------------------------------- */ |
|
40 |
|
|
41 |
#include "arm_math.h" |
|
42 |
|
|
43 |
/** |
|
44 |
* @ingroup groupMatrix |
|
45 |
*/ |
|
46 |
|
|
47 |
/** |
|
48 |
* @addtogroup MatrixTrans |
|
49 |
* @{ |
|
50 |
*/ |
|
51 |
|
|
52 |
/* |
|
53 |
* @brief Q15 matrix transpose. |
|
54 |
* @param[in] *pSrc points to the input matrix |
|
55 |
* @param[out] *pDst points to the output matrix |
|
56 |
* @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code> |
|
57 |
* or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking. |
|
58 |
*/ |
|
59 |
|
|
60 |
arm_status arm_mat_trans_q15( |
|
61 |
const arm_matrix_instance_q15 * pSrc, |
|
62 |
arm_matrix_instance_q15 * pDst) |
|
63 |
{ |
|
64 |
q15_t *pSrcA = pSrc->pData; /* input data matrix pointer */ |
|
65 |
q15_t *pOut = pDst->pData; /* output data matrix pointer */ |
|
66 |
uint16_t nRows = pSrc->numRows; /* number of nRows */ |
|
67 |
uint16_t nColumns = pSrc->numCols; /* number of nColumns */ |
|
68 |
uint16_t col, row = nRows, i = 0u; /* row and column loop counters */ |
|
69 |
arm_status status; /* status of matrix transpose */ |
|
70 |
|
|
71 |
#ifndef ARM_MATH_CM0_FAMILY |
|
72 |
|
|
73 |
/* Run the below code for Cortex-M4 and Cortex-M3 */ |
|
74 |
#ifndef UNALIGNED_SUPPORT_DISABLE |
|
75 |
|
|
76 |
q31_t in; /* variable to hold temporary output */ |
|
77 |
|
|
78 |
#else |
|
79 |
|
|
80 |
q15_t in; |
|
81 |
|
|
82 |
#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ |
|
83 |
|
|
84 |
#ifdef ARM_MATH_MATRIX_CHECK |
|
85 |
|
|
86 |
|
|
87 |
/* Check for matrix mismatch condition */ |
|
88 |
if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows)) |
|
89 |
{ |
|
90 |
/* Set status as ARM_MATH_SIZE_MISMATCH */ |
|
91 |
status = ARM_MATH_SIZE_MISMATCH; |
|
92 |
} |
|
93 |
else |
|
94 |
#endif /* #ifdef ARM_MATH_MATRIX_CHECK */ |
|
95 |
|
|
96 |
{ |
|
97 |
/* Matrix transpose by exchanging the rows with columns */ |
|
98 |
/* row loop */ |
|
99 |
do |
|
100 |
{ |
|
101 |
|
|
102 |
/* Apply loop unrolling and exchange the columns with row elements */ |
|
103 |
col = nColumns >> 2u; |
|
104 |
|
|
105 |
/* The pointer pOut is set to starting address of the column being processed */ |
|
106 |
pOut = pDst->pData + i; |
|
107 |
|
|
108 |
/* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
|
109 |
** a second loop below computes the remaining 1 to 3 samples. */ |
|
110 |
while(col > 0u) |
|
111 |
{ |
|
112 |
#ifndef UNALIGNED_SUPPORT_DISABLE |
|
113 |
|
|
114 |
/* Read two elements from the row */ |
|
115 |
in = *__SIMD32(pSrcA)++; |
|
116 |
|
|
117 |
/* Unpack and store one element in the destination */ |
|
118 |
#ifndef ARM_MATH_BIG_ENDIAN |
|
119 |
|
|
120 |
*pOut = (q15_t) in; |
|
121 |
|
|
122 |
#else |
|
123 |
|
|
124 |
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); |
|
125 |
|
|
126 |
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ |
|
127 |
|
|
128 |
/* Update the pointer pOut to point to the next row of the transposed matrix */ |
|
129 |
pOut += nRows; |
|
130 |
|
|
131 |
/* Unpack and store the second element in the destination */ |
|
132 |
|
|
133 |
#ifndef ARM_MATH_BIG_ENDIAN |
|
134 |
|
|
135 |
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); |
|
136 |
|
|
137 |
#else |
|
138 |
|
|
139 |
*pOut = (q15_t) in; |
|
140 |
|
|
141 |
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ |
|
142 |
|
|
143 |
/* Update the pointer pOut to point to the next row of the transposed matrix */ |
|
144 |
pOut += nRows; |
|
145 |
|
|
146 |
/* Read two elements from the row */ |
|
147 |
#ifndef ARM_MATH_BIG_ENDIAN |
|
148 |
|
|
149 |
in = *__SIMD32(pSrcA)++; |
|
150 |
|
|
151 |
#else |
|
152 |
|
|
153 |
in = *__SIMD32(pSrcA)++; |
|
154 |
|
|
155 |
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ |
|
156 |
|
|
157 |
/* Unpack and store one element in the destination */ |
|
158 |
#ifndef ARM_MATH_BIG_ENDIAN |
|
159 |
|
|
160 |
*pOut = (q15_t) in; |
|
161 |
|
|
162 |
#else |
|
163 |
|
|
164 |
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); |
|
165 |
|
|
166 |
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ |
|
167 |
|
|
168 |
/* Update the pointer pOut to point to the next row of the transposed matrix */ |
|
169 |
pOut += nRows; |
|
170 |
|
|
171 |
/* Unpack and store the second element in the destination */ |
|
172 |
#ifndef ARM_MATH_BIG_ENDIAN |
|
173 |
|
|
174 |
*pOut = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); |
|
175 |
|
|
176 |
#else |
|
177 |
|
|
178 |
*pOut = (q15_t) in; |
|
179 |
|
|
180 |
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ |
|
181 |
|
|
182 |
#else |
|
183 |
/* Read one element from the row */ |
|
184 |
in = *pSrcA++; |
|
185 |
|
|
186 |
/* Store one element in the destination */ |
|
187 |
*pOut = in; |
|
188 |
|
|
189 |
/* Update the pointer px to point to the next row of the transposed matrix */ |
|
190 |
pOut += nRows; |
|
191 |
|
|
192 |
/* Read one element from the row */ |
|
193 |
in = *pSrcA++; |
|
194 |
|
|
195 |
/* Store one element in the destination */ |
|
196 |
*pOut = in; |
|
197 |
|
|
198 |
/* Update the pointer px to point to the next row of the transposed matrix */ |
|
199 |
pOut += nRows; |
|
200 |
|
|
201 |
/* Read one element from the row */ |
|
202 |
in = *pSrcA++; |
|
203 |
|
|
204 |
/* Store one element in the destination */ |
|
205 |
*pOut = in; |
|
206 |
|
|
207 |
/* Update the pointer px to point to the next row of the transposed matrix */ |
|
208 |
pOut += nRows; |
|
209 |
|
|
210 |
/* Read one element from the row */ |
|
211 |
in = *pSrcA++; |
|
212 |
|
|
213 |
/* Store one element in the destination */ |
|
214 |
*pOut = in; |
|
215 |
|
|
216 |
#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ |
|
217 |
|
|
218 |
/* Update the pointer pOut to point to the next row of the transposed matrix */ |
|
219 |
pOut += nRows; |
|
220 |
|
|
221 |
/* Decrement the column loop counter */ |
|
222 |
col--; |
|
223 |
} |
|
224 |
|
|
225 |
/* Perform matrix transpose for last 3 samples here. */ |
|
226 |
col = nColumns % 0x4u; |
|
227 |
|
|
228 |
#else |
|
229 |
|
|
230 |
/* Run the below code for Cortex-M0 */ |
|
231 |
|
|
232 |
#ifdef ARM_MATH_MATRIX_CHECK |
|
233 |
|
|
234 |
/* Check for matrix mismatch condition */ |
|
235 |
if((pSrc->numRows != pDst->numCols) || (pSrc->numCols != pDst->numRows)) |
|
236 |
{ |
|
237 |
/* Set status as ARM_MATH_SIZE_MISMATCH */ |
|
238 |
status = ARM_MATH_SIZE_MISMATCH; |
|
239 |
} |
|
240 |
else |
|
241 |
#endif /* #ifdef ARM_MATH_MATRIX_CHECK */ |
|
242 |
|
|
243 |
{ |
|
244 |
/* Matrix transpose by exchanging the rows with columns */ |
|
245 |
/* row loop */ |
|
246 |
do |
|
247 |
{ |
|
248 |
/* The pointer pOut is set to starting address of the column being processed */ |
|
249 |
pOut = pDst->pData + i; |
|
250 |
|
|
251 |
/* Initialize column loop counter */ |
|
252 |
col = nColumns; |
|
253 |
|
|
254 |
#endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
|
255 |
|
|
256 |
while(col > 0u) |
|
257 |
{ |
|
258 |
/* Read and store the input element in the destination */ |
|
259 |
*pOut = *pSrcA++; |
|
260 |
|
|
261 |
/* Update the pointer pOut to point to the next row of the transposed matrix */ |
|
262 |
pOut += nRows; |
|
263 |
|
|
264 |
/* Decrement the column loop counter */ |
|
265 |
col--; |
|
266 |
} |
|
267 |
|
|
268 |
i++; |
|
269 |
|
|
270 |
/* Decrement the row loop counter */ |
|
271 |
row--; |
|
272 |
|
|
273 |
} while(row > 0u); |
|
274 |
|
|
275 |
/* set status as ARM_MATH_SUCCESS */ |
|
276 |
status = ARM_MATH_SUCCESS; |
|
277 |
} |
|
278 |
/* Return to application */ |
|
279 |
return (status); |
|
280 |
} |
|
281 |
|
|
282 |
/** |
|
283 |
* @} end of MatrixTrans group |
|
284 |
*/ |