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
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
|
/***************************************************************************
* Copyright (C) 2006 *
* *
* *
* This program is free software; you can redistribute it and/or modify *
* it under the terms of the GNU General Public License as published by *
* the Free Software Foundation; either version 2 of the License, or *
* (at your option) any later version. *
* *
* This program is distributed in the hope that it will be useful, *
* but WITHOUT ANY WARRANTY; without even the implied warranty of *
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
* GNU General Public License for more details. *
* *
* You should have received a copy of the GNU General Public License *
* along with this program; if not, write to the *
* Free Software Foundation, Inc., *
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. *
***************************************************************************/
/**
@author Svetlin Manavski <[email protected]>
*/
/* aes decryption operation:
* Device code.
*
*/
#ifndef _AESDECRYPT_KERNEL_H_
#define _AESDECRYPT_KERNEL_H_
#include <stdio.h>
// Thread block size
#define BSIZE 256
#define STAGEBLOCK1(index) CUT_BANK_CHECKER( stageBlock1, index )
#define STAGEBLOCK2(index) CUT_BANK_CHECKER( stageBlock2, index )
#define TBOXE0(index) CUT_BANK_CHECKER( tBox0Block, index )
#define TBOXE1(index) CUT_BANK_CHECKER( tBox1Block, index )
#define TBOXE2(index) CUT_BANK_CHECKER( tBox2Block, index )
#define TBOXE3(index) CUT_BANK_CHECKER( tBox3Block, index )
#define INVSBOX(index) CUT_BANK_CHECKER( invSBoxBlock, index )
texture<unsigned, 1, cudaReadModeElementType> texDKey;
__global__ void aesDecrypt256( unsigned * result, unsigned * inData, int inputSize)
{
unsigned bx = blockIdx.x;
unsigned tx = threadIdx.x;
unsigned mod4tx = tx%4;
unsigned int4tx = tx/4;
unsigned idx2 = int4tx*4;
int x;
unsigned keyElem;
__shared__ UByte4 stageBlock1[BSIZE];
__shared__ UByte4 stageBlock2[BSIZE];
__shared__ UByte4 tBox0Block[BSIZE];
__shared__ UByte4 tBox1Block[BSIZE];
__shared__ UByte4 tBox2Block[BSIZE];
__shared__ UByte4 tBox3Block[BSIZE];
__shared__ UByte4 invSBoxBlock[BSIZE];
// input caricati in memoria
STAGEBLOCK1(tx).uival = inData[BSIZE * bx + tx ];
TBOXE0(tx).uival = TBoxi0[tx];
TBOXE1(tx).uival = TBoxi1[tx];
TBOXE2(tx).uival = TBoxi2[tx];
TBOXE3(tx).uival = TBoxi3[tx];
INVSBOX(tx).ubval[0] = inv_SBox[tx];
__syncthreads();
//----------------------------------- 1st stage -----------------------------------
x = mod4tx;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).uival = STAGEBLOCK1(tx).uival ^ keyElem;
__syncthreads();
//-------------------------------- end of 1st stage --------------------------------
//----------------------------------- 2nd stage -----------------------------------
unsigned op1 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
unsigned op2 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
unsigned op3 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
unsigned op4 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+4;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK1(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 2nd stage --------------------------------
//----------------------------------- 3th stage -----------------------------------
op1 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+8;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 3th stage --------------------------------
//----------------------------------- 4th stage -----------------------------------
op1 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+12;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK1(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 4th stage --------------------------------
//----------------------------------- 5th stage -----------------------------------
op1 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+16;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 5th stage --------------------------------
//----------------------------------- 6th stage -----------------------------------
op1 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+20;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK1(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 6th stage --------------------------------
//----------------------------------- 7th stage -----------------------------------
op1 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+24;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 7th stage --------------------------------
//----------------------------------- 8th stage -----------------------------------
op1 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+28;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK1(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 8th stage --------------------------------
//----------------------------------- 9th stage -----------------------------------
op1 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+32;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 9th stage --------------------------------
//----------------------------------- 10th stage -----------------------------------
op1 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+36;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK1(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 10th stage --------------------------------
//----------------------------------- 11th stage -----------------------------------
op1 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+40;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 11th stage --------------------------------
//----------------------------------- 12th stage -----------------------------------
op1 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+44;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK1(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 12th stage --------------------------------
//----------------------------------- 13th stage -----------------------------------
op1 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+48;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 13th stage --------------------------------
//----------------------------------- 14th stage -----------------------------------
op1 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK2( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
op1 = TBOXE0(op1).uival;
op2 = TBOXE1(op2).uival;
op3 = TBOXE2(op3).uival;
op4 = TBOXE3(op4).uival;
x = mod4tx+52;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK1(tx).uival = op1^op2^op3^op4^keyElem;
__syncthreads();
//-------------------------------- end of 14th stage --------------------------------
//----------------------------------- 15th stage -----------------------------------
op1 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4] + idx2 ).ubval[0];
op2 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+1] + idx2 ).ubval[1];
op3 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+2] + idx2 ).ubval[2];
op4 = STAGEBLOCK1( posIdx_D[16 + mod4tx*4+3] + idx2 ).ubval[3];
x = mod4tx+56;
keyElem = tex1Dfetch(texDKey, x);
STAGEBLOCK2(tx).ubval[3] = INVSBOX(op4).ubval[0]^( keyElem>>24);
STAGEBLOCK2(tx).ubval[2] = INVSBOX(op3).ubval[0]^( keyElem>>16 & 0x000000FF);
STAGEBLOCK2(tx).ubval[1] = INVSBOX(op2).ubval[0]^( keyElem>>8 & 0x000000FF);
STAGEBLOCK2(tx).ubval[0] = INVSBOX(op1).ubval[0]^( keyElem & 0x000000FF);
__syncthreads();
//-------------------------------- end of 15th stage --------------------------------
result[BSIZE * bx + tx] = STAGEBLOCK2(tx).uival;
// end of AES
}
#endif // #ifndef _AESDECRYPT_KERNEL_H_
|
