1 /* SPDX-License-Identifier: GPL-2.0-or-later */
2 /*
3 * include/asm-alpha/xor.h
4 *
5 * Optimized RAID-5 checksumming functions for alpha EV5 and EV6
6 */
7
8 extern void
9 xor_alpha_2(unsigned long bytes, unsigned long * __restrict p1,
10 const unsigned long * __restrict p2);
11 extern void
12 xor_alpha_3(unsigned long bytes, unsigned long * __restrict p1,
13 const unsigned long * __restrict p2,
14 const unsigned long * __restrict p3);
15 extern void
16 xor_alpha_4(unsigned long bytes, unsigned long * __restrict p1,
17 const unsigned long * __restrict p2,
18 const unsigned long * __restrict p3,
19 const unsigned long * __restrict p4);
20 extern void
21 xor_alpha_5(unsigned long bytes, unsigned long * __restrict p1,
22 const unsigned long * __restrict p2,
23 const unsigned long * __restrict p3,
24 const unsigned long * __restrict p4,
25 const unsigned long * __restrict p5);
26
27 extern void
28 xor_alpha_prefetch_2(unsigned long bytes, unsigned long * __restrict p1,
29 const unsigned long * __restrict p2);
30 extern void
31 xor_alpha_prefetch_3(unsigned long bytes, unsigned long * __restrict p1,
32 const unsigned long * __restrict p2,
33 const unsigned long * __restrict p3);
34 extern void
35 xor_alpha_prefetch_4(unsigned long bytes, unsigned long * __restrict p1,
36 const unsigned long * __restrict p2,
37 const unsigned long * __restrict p3,
38 const unsigned long * __restrict p4);
39 extern void
40 xor_alpha_prefetch_5(unsigned long bytes, unsigned long * __restrict p1,
41 const unsigned long * __restrict p2,
42 const unsigned long * __restrict p3,
43 const unsigned long * __restrict p4,
44 const unsigned long * __restrict p5);
45
46 asm(" \n\
47 .text \n\
48 .align 3 \n\
49 .ent xor_alpha_2 \n\
50 xor_alpha_2: \n\
51 .prologue 0 \n\
52 srl $16, 6, $16 \n\
53 .align 4 \n\
54 2: \n\
55 ldq $0,0($17) \n\
56 ldq $1,0($18) \n\
57 ldq $2,8($17) \n\
58 ldq $3,8($18) \n\
59 \n\
60 ldq $4,16($17) \n\
61 ldq $5,16($18) \n\
62 ldq $6,24($17) \n\
63 ldq $7,24($18) \n\
64 \n\
65 ldq $19,32($17) \n\
66 ldq $20,32($18) \n\
67 ldq $21,40($17) \n\
68 ldq $22,40($18) \n\
69 \n\
70 ldq $23,48($17) \n\
71 ldq $24,48($18) \n\
72 ldq $25,56($17) \n\
73 xor $0,$1,$0 # 7 cycles from $1 load \n\
74 \n\
75 ldq $27,56($18) \n\
76 xor $2,$3,$2 \n\
77 stq $0,0($17) \n\
78 xor $4,$5,$4 \n\
79 \n\
80 stq $2,8($17) \n\
81 xor $6,$7,$6 \n\
82 stq $4,16($17) \n\
83 xor $19,$20,$19 \n\
84 \n\
85 stq $6,24($17) \n\
86 xor $21,$22,$21 \n\
87 stq $19,32($17) \n\
88 xor $23,$24,$23 \n\
89 \n\
90 stq $21,40($17) \n\
91 xor $25,$27,$25 \n\
92 stq $23,48($17) \n\
93 subq $16,1,$16 \n\
94 \n\
95 stq $25,56($17) \n\
96 addq $17,64,$17 \n\
97 addq $18,64,$18 \n\
98 bgt $16,2b \n\
99 \n\
100 ret \n\
101 .end xor_alpha_2 \n\
102 \n\
103 .align 3 \n\
104 .ent xor_alpha_3 \n\
105 xor_alpha_3: \n\
106 .prologue 0 \n\
107 srl $16, 6, $16 \n\
108 .align 4 \n\
109 3: \n\
110 ldq $0,0($17) \n\
111 ldq $1,0($18) \n\
112 ldq $2,0($19) \n\
113 ldq $3,8($17) \n\
114 \n\
115 ldq $4,8($18) \n\
116 ldq $6,16($17) \n\
117 ldq $7,16($18) \n\
118 ldq $21,24($17) \n\
119 \n\
120 ldq $22,24($18) \n\
121 ldq $24,32($17) \n\
122 ldq $25,32($18) \n\
123 ldq $5,8($19) \n\
124 \n\
125 ldq $20,16($19) \n\
126 ldq $23,24($19) \n\
127 ldq $27,32($19) \n\
128 nop \n\
129 \n\
130 xor $0,$1,$1 # 8 cycles from $0 load \n\
131 xor $3,$4,$4 # 6 cycles from $4 load \n\
132 xor $6,$7,$7 # 6 cycles from $7 load \n\
133 xor $21,$22,$22 # 5 cycles from $22 load \n\
134 \n\
135 xor $1,$2,$2 # 9 cycles from $2 load \n\
136 xor $24,$25,$25 # 5 cycles from $25 load \n\
137 stq $2,0($17) \n\
138 xor $4,$5,$5 # 6 cycles from $5 load \n\
139 \n\
140 stq $5,8($17) \n\
141 xor $7,$20,$20 # 7 cycles from $20 load \n\
142 stq $20,16($17) \n\
143 xor $22,$23,$23 # 7 cycles from $23 load \n\
144 \n\
145 stq $23,24($17) \n\
146 xor $25,$27,$27 # 7 cycles from $27 load \n\
147 stq $27,32($17) \n\
148 nop \n\
149 \n\
150 ldq $0,40($17) \n\
151 ldq $1,40($18) \n\
152 ldq $3,48($17) \n\
153 ldq $4,48($18) \n\
154 \n\
155 ldq $6,56($17) \n\
156 ldq $7,56($18) \n\
157 ldq $2,40($19) \n\
158 ldq $5,48($19) \n\
159 \n\
160 ldq $20,56($19) \n\
161 xor $0,$1,$1 # 4 cycles from $1 load \n\
162 xor $3,$4,$4 # 5 cycles from $4 load \n\
163 xor $6,$7,$7 # 5 cycles from $7 load \n\
164 \n\
165 xor $1,$2,$2 # 4 cycles from $2 load \n\
166 xor $4,$5,$5 # 5 cycles from $5 load \n\
167 stq $2,40($17) \n\
168 xor $7,$20,$20 # 4 cycles from $20 load \n\
169 \n\
170 stq $5,48($17) \n\
171 subq $16,1,$16 \n\
172 stq $20,56($17) \n\
173 addq $19,64,$19 \n\
174 \n\
175 addq $18,64,$18 \n\
176 addq $17,64,$17 \n\
177 bgt $16,3b \n\
178 ret \n\
179 .end xor_alpha_3 \n\
180 \n\
181 .align 3 \n\
182 .ent xor_alpha_4 \n\
183 xor_alpha_4: \n\
184 .prologue 0 \n\
185 srl $16, 6, $16 \n\
186 .align 4 \n\
187 4: \n\
188 ldq $0,0($17) \n\
189 ldq $1,0($18) \n\
190 ldq $2,0($19) \n\
191 ldq $3,0($20) \n\
192 \n\
193 ldq $4,8($17) \n\
194 ldq $5,8($18) \n\
195 ldq $6,8($19) \n\
196 ldq $7,8($20) \n\
197 \n\
198 ldq $21,16($17) \n\
199 ldq $22,16($18) \n\
200 ldq $23,16($19) \n\
201 ldq $24,16($20) \n\
202 \n\
203 ldq $25,24($17) \n\
204 xor $0,$1,$1 # 6 cycles from $1 load \n\
205 ldq $27,24($18) \n\
206 xor $2,$3,$3 # 6 cycles from $3 load \n\
207 \n\
208 ldq $0,24($19) \n\
209 xor $1,$3,$3 \n\
210 ldq $1,24($20) \n\
211 xor $4,$5,$5 # 7 cycles from $5 load \n\
212 \n\
213 stq $3,0($17) \n\
214 xor $6,$7,$7 \n\
215 xor $21,$22,$22 # 7 cycles from $22 load \n\
216 xor $5,$7,$7 \n\
217 \n\
218 stq $7,8($17) \n\
219 xor $23,$24,$24 # 7 cycles from $24 load \n\
220 ldq $2,32($17) \n\
221 xor $22,$24,$24 \n\
222 \n\
223 ldq $3,32($18) \n\
224 ldq $4,32($19) \n\
225 ldq $5,32($20) \n\
226 xor $25,$27,$27 # 8 cycles from $27 load \n\
227 \n\
228 ldq $6,40($17) \n\
229 ldq $7,40($18) \n\
230 ldq $21,40($19) \n\
231 ldq $22,40($20) \n\
232 \n\
233 stq $24,16($17) \n\
234 xor $0,$1,$1 # 9 cycles from $1 load \n\
235 xor $2,$3,$3 # 5 cycles from $3 load \n\
236 xor $27,$1,$1 \n\
237 \n\
238 stq $1,24($17) \n\
239 xor $4,$5,$5 # 5 cycles from $5 load \n\
240 ldq $23,48($17) \n\
241 ldq $24,48($18) \n\
242 \n\
243 ldq $25,48($19) \n\
244 xor $3,$5,$5 \n\
245 ldq $27,48($20) \n\
246 ldq $0,56($17) \n\
247 \n\
248 ldq $1,56($18) \n\
249 ldq $2,56($19) \n\
250 xor $6,$7,$7 # 8 cycles from $6 load \n\
251 ldq $3,56($20) \n\
252 \n\
253 stq $5,32($17) \n\
254 xor $21,$22,$22 # 8 cycles from $22 load \n\
255 xor $7,$22,$22 \n\
256 xor $23,$24,$24 # 5 cycles from $24 load \n\
257 \n\
258 stq $22,40($17) \n\
259 xor $25,$27,$27 # 5 cycles from $27 load \n\
260 xor $24,$27,$27 \n\
261 xor $0,$1,$1 # 5 cycles from $1 load \n\
262 \n\
263 stq $27,48($17) \n\
264 xor $2,$3,$3 # 4 cycles from $3 load \n\
265 xor $1,$3,$3 \n\
266 subq $16,1,$16 \n\
267 \n\
268 stq $3,56($17) \n\
269 addq $20,64,$20 \n\
270 addq $19,64,$19 \n\
271 addq $18,64,$18 \n\
272 \n\
273 addq $17,64,$17 \n\
274 bgt $16,4b \n\
275 ret \n\
276 .end xor_alpha_4 \n\
277 \n\
278 .align 3 \n\
279 .ent xor_alpha_5 \n\
280 xor_alpha_5: \n\
281 .prologue 0 \n\
282 srl $16, 6, $16 \n\
283 .align 4 \n\
284 5: \n\
285 ldq $0,0($17) \n\
286 ldq $1,0($18) \n\
287 ldq $2,0($19) \n\
288 ldq $3,0($20) \n\
289 \n\
290 ldq $4,0($21) \n\
291 ldq $5,8($17) \n\
292 ldq $6,8($18) \n\
293 ldq $7,8($19) \n\
294 \n\
295 ldq $22,8($20) \n\
296 ldq $23,8($21) \n\
297 ldq $24,16($17) \n\
298 ldq $25,16($18) \n\
299 \n\
300 ldq $27,16($19) \n\
301 xor $0,$1,$1 # 6 cycles from $1 load \n\
302 ldq $28,16($20) \n\
303 xor $2,$3,$3 # 6 cycles from $3 load \n\
304 \n\
305 ldq $0,16($21) \n\
306 xor $1,$3,$3 \n\
307 ldq $1,24($17) \n\
308 xor $3,$4,$4 # 7 cycles from $4 load \n\
309 \n\
310 stq $4,0($17) \n\
311 xor $5,$6,$6 # 7 cycles from $6 load \n\
312 xor $7,$22,$22 # 7 cycles from $22 load \n\
313 xor $6,$23,$23 # 7 cycles from $23 load \n\
314 \n\
315 ldq $2,24($18) \n\
316 xor $22,$23,$23 \n\
317 ldq $3,24($19) \n\
318 xor $24,$25,$25 # 8 cycles from $25 load \n\
319 \n\
320 stq $23,8($17) \n\
321 xor $25,$27,$27 # 8 cycles from $27 load \n\
322 ldq $4,24($20) \n\
323 xor $28,$0,$0 # 7 cycles from $0 load \n\
324 \n\
325 ldq $5,24($21) \n\
326 xor $27,$0,$0 \n\
327 ldq $6,32($17) \n\
328 ldq $7,32($18) \n\
329 \n\
330 stq $0,16($17) \n\
331 xor $1,$2,$2 # 6 cycles from $2 load \n\
332 ldq $22,32($19) \n\
333 xor $3,$4,$4 # 4 cycles from $4 load \n\
334 \n\
335 ldq $23,32($20) \n\
336 xor $2,$4,$4 \n\
337 ldq $24,32($21) \n\
338 ldq $25,40($17) \n\
339 \n\
340 ldq $27,40($18) \n\
341 ldq $28,40($19) \n\
342 ldq $0,40($20) \n\
343 xor $4,$5,$5 # 7 cycles from $5 load \n\
344 \n\
345 stq $5,24($17) \n\
346 xor $6,$7,$7 # 7 cycles from $7 load \n\
347 ldq $1,40($21) \n\
348 ldq $2,48($17) \n\
349 \n\
350 ldq $3,48($18) \n\
351 xor $7,$22,$22 # 7 cycles from $22 load \n\
352 ldq $4,48($19) \n\
353 xor $23,$24,$24 # 6 cycles from $24 load \n\
354 \n\
355 ldq $5,48($20) \n\
356 xor $22,$24,$24 \n\
357 ldq $6,48($21) \n\
358 xor $25,$27,$27 # 7 cycles from $27 load \n\
359 \n\
360 stq $24,32($17) \n\
361 xor $27,$28,$28 # 8 cycles from $28 load \n\
362 ldq $7,56($17) \n\
363 xor $0,$1,$1 # 6 cycles from $1 load \n\
364 \n\
365 ldq $22,56($18) \n\
366 ldq $23,56($19) \n\
367 ldq $24,56($20) \n\
368 ldq $25,56($21) \n\
369 \n\
370 xor $28,$1,$1 \n\
371 xor $2,$3,$3 # 9 cycles from $3 load \n\
372 xor $3,$4,$4 # 9 cycles from $4 load \n\
373 xor $5,$6,$6 # 8 cycles from $6 load \n\
374 \n\
375 stq $1,40($17) \n\
376 xor $4,$6,$6 \n\
377 xor $7,$22,$22 # 7 cycles from $22 load \n\
378 xor $23,$24,$24 # 6 cycles from $24 load \n\
379 \n\
380 stq $6,48($17) \n\
381 xor $22,$24,$24 \n\
382 subq $16,1,$16 \n\
383 xor $24,$25,$25 # 8 cycles from $25 load \n\
384 \n\
385 stq $25,56($17) \n\
386 addq $21,64,$21 \n\
387 addq $20,64,$20 \n\
388 addq $19,64,$19 \n\
389 \n\
390 addq $18,64,$18 \n\
391 addq $17,64,$17 \n\
392 bgt $16,5b \n\
393 ret \n\
394 .end xor_alpha_5 \n\
395 \n\
396 .align 3 \n\
397 .ent xor_alpha_prefetch_2 \n\
398 xor_alpha_prefetch_2: \n\
399 .prologue 0 \n\
400 srl $16, 6, $16 \n\
401 \n\
402 ldq $31, 0($17) \n\
403 ldq $31, 0($18) \n\
404 \n\
405 ldq $31, 64($17) \n\
406 ldq $31, 64($18) \n\
407 \n\
408 ldq $31, 128($17) \n\
409 ldq $31, 128($18) \n\
410 \n\
411 ldq $31, 192($17) \n\
412 ldq $31, 192($18) \n\
413 .align 4 \n\
414 2: \n\
415 ldq $0,0($17) \n\
416 ldq $1,0($18) \n\
417 ldq $2,8($17) \n\
418 ldq $3,8($18) \n\
419 \n\
420 ldq $4,16($17) \n\
421 ldq $5,16($18) \n\
422 ldq $6,24($17) \n\
423 ldq $7,24($18) \n\
424 \n\
425 ldq $19,32($17) \n\
426 ldq $20,32($18) \n\
427 ldq $21,40($17) \n\
428 ldq $22,40($18) \n\
429 \n\
430 ldq $23,48($17) \n\
431 ldq $24,48($18) \n\
432 ldq $25,56($17) \n\
433 ldq $27,56($18) \n\
434 \n\
435 ldq $31,256($17) \n\
436 xor $0,$1,$0 # 8 cycles from $1 load \n\
437 ldq $31,256($18) \n\
438 xor $2,$3,$2 \n\
439 \n\
440 stq $0,0($17) \n\
441 xor $4,$5,$4 \n\
442 stq $2,8($17) \n\
443 xor $6,$7,$6 \n\
444 \n\
445 stq $4,16($17) \n\
446 xor $19,$20,$19 \n\
447 stq $6,24($17) \n\
448 xor $21,$22,$21 \n\
449 \n\
450 stq $19,32($17) \n\
451 xor $23,$24,$23 \n\
452 stq $21,40($17) \n\
453 xor $25,$27,$25 \n\
454 \n\
455 stq $23,48($17) \n\
456 subq $16,1,$16 \n\
457 stq $25,56($17) \n\
458 addq $17,64,$17 \n\
459 \n\
460 addq $18,64,$18 \n\
461 bgt $16,2b \n\
462 ret \n\
463 .end xor_alpha_prefetch_2 \n\
464 \n\
465 .align 3 \n\
466 .ent xor_alpha_prefetch_3 \n\
467 xor_alpha_prefetch_3: \n\
468 .prologue 0 \n\
469 srl $16, 6, $16 \n\
470 \n\
471 ldq $31, 0($17) \n\
472 ldq $31, 0($18) \n\
473 ldq $31, 0($19) \n\
474 \n\
475 ldq $31, 64($17) \n\
476 ldq $31, 64($18) \n\
477 ldq $31, 64($19) \n\
478 \n\
479 ldq $31, 128($17) \n\
480 ldq $31, 128($18) \n\
481 ldq $31, 128($19) \n\
482 \n\
483 ldq $31, 192($17) \n\
484 ldq $31, 192($18) \n\
485 ldq $31, 192($19) \n\
486 .align 4 \n\
487 3: \n\
488 ldq $0,0($17) \n\
489 ldq $1,0($18) \n\
490 ldq $2,0($19) \n\
491 ldq $3,8($17) \n\
492 \n\
493 ldq $4,8($18) \n\
494 ldq $6,16($17) \n\
495 ldq $7,16($18) \n\
496 ldq $21,24($17) \n\
497 \n\
498 ldq $22,24($18) \n\
499 ldq $24,32($17) \n\
500 ldq $25,32($18) \n\
501 ldq $5,8($19) \n\
502 \n\
503 ldq $20,16($19) \n\
504 ldq $23,24($19) \n\
505 ldq $27,32($19) \n\
506 nop \n\
507 \n\
508 xor $0,$1,$1 # 8 cycles from $0 load \n\
509 xor $3,$4,$4 # 7 cycles from $4 load \n\
510 xor $6,$7,$7 # 6 cycles from $7 load \n\
511 xor $21,$22,$22 # 5 cycles from $22 load \n\
512 \n\
513 xor $1,$2,$2 # 9 cycles from $2 load \n\
514 xor $24,$25,$25 # 5 cycles from $25 load \n\
515 stq $2,0($17) \n\
516 xor $4,$5,$5 # 6 cycles from $5 load \n\
517 \n\
518 stq $5,8($17) \n\
519 xor $7,$20,$20 # 7 cycles from $20 load \n\
520 stq $20,16($17) \n\
521 xor $22,$23,$23 # 7 cycles from $23 load \n\
522 \n\
523 stq $23,24($17) \n\
524 xor $25,$27,$27 # 7 cycles from $27 load \n\
525 stq $27,32($17) \n\
526 nop \n\
527 \n\
528 ldq $0,40($17) \n\
529 ldq $1,40($18) \n\
530 ldq $3,48($17) \n\
531 ldq $4,48($18) \n\
532 \n\
533 ldq $6,56($17) \n\
534 ldq $7,56($18) \n\
535 ldq $2,40($19) \n\
536 ldq $5,48($19) \n\
537 \n\
538 ldq $20,56($19) \n\
539 ldq $31,256($17) \n\
540 ldq $31,256($18) \n\
541 ldq $31,256($19) \n\
542 \n\
543 xor $0,$1,$1 # 6 cycles from $1 load \n\
544 xor $3,$4,$4 # 5 cycles from $4 load \n\
545 xor $6,$7,$7 # 5 cycles from $7 load \n\
546 xor $1,$2,$2 # 4 cycles from $2 load \n\
547 \n\
548 xor $4,$5,$5 # 5 cycles from $5 load \n\
549 xor $7,$20,$20 # 4 cycles from $20 load \n\
550 stq $2,40($17) \n\
551 subq $16,1,$16 \n\
552 \n\
553 stq $5,48($17) \n\
554 addq $19,64,$19 \n\
555 stq $20,56($17) \n\
556 addq $18,64,$18 \n\
557 \n\
558 addq $17,64,$17 \n\
559 bgt $16,3b \n\
560 ret \n\
561 .end xor_alpha_prefetch_3 \n\
562 \n\
563 .align 3 \n\
564 .ent xor_alpha_prefetch_4 \n\
565 xor_alpha_prefetch_4: \n\
566 .prologue 0 \n\
567 srl $16, 6, $16 \n\
568 \n\
569 ldq $31, 0($17) \n\
570 ldq $31, 0($18) \n\
571 ldq $31, 0($19) \n\
572 ldq $31, 0($20) \n\
573 \n\
574 ldq $31, 64($17) \n\
575 ldq $31, 64($18) \n\
576 ldq $31, 64($19) \n\
577 ldq $31, 64($20) \n\
578 \n\
579 ldq $31, 128($17) \n\
580 ldq $31, 128($18) \n\
581 ldq $31, 128($19) \n\
582 ldq $31, 128($20) \n\
583 \n\
584 ldq $31, 192($17) \n\
585 ldq $31, 192($18) \n\
586 ldq $31, 192($19) \n\
587 ldq $31, 192($20) \n\
588 .align 4 \n\
589 4: \n\
590 ldq $0,0($17) \n\
591 ldq $1,0($18) \n\
592 ldq $2,0($19) \n\
593 ldq $3,0($20) \n\
594 \n\
595 ldq $4,8($17) \n\
596 ldq $5,8($18) \n\
597 ldq $6,8($19) \n\
598 ldq $7,8($20) \n\
599 \n\
600 ldq $21,16($17) \n\
601 ldq $22,16($18) \n\
602 ldq $23,16($19) \n\
603 ldq $24,16($20) \n\
604 \n\
605 ldq $25,24($17) \n\
606 xor $0,$1,$1 # 6 cycles from $1 load \n\
607 ldq $27,24($18) \n\
608 xor $2,$3,$3 # 6 cycles from $3 load \n\
609 \n\
610 ldq $0,24($19) \n\
611 xor $1,$3,$3 \n\
612 ldq $1,24($20) \n\
613 xor $4,$5,$5 # 7 cycles from $5 load \n\
614 \n\
615 stq $3,0($17) \n\
616 xor $6,$7,$7 \n\
617 xor $21,$22,$22 # 7 cycles from $22 load \n\
618 xor $5,$7,$7 \n\
619 \n\
620 stq $7,8($17) \n\
621 xor $23,$24,$24 # 7 cycles from $24 load \n\
622 ldq $2,32($17) \n\
623 xor $22,$24,$24 \n\
624 \n\
625 ldq $3,32($18) \n\
626 ldq $4,32($19) \n\
627 ldq $5,32($20) \n\
628 xor $25,$27,$27 # 8 cycles from $27 load \n\
629 \n\
630 ldq $6,40($17) \n\
631 ldq $7,40($18) \n\
632 ldq $21,40($19) \n\
633 ldq $22,40($20) \n\
634 \n\
635 stq $24,16($17) \n\
636 xor $0,$1,$1 # 9 cycles from $1 load \n\
637 xor $2,$3,$3 # 5 cycles from $3 load \n\
638 xor $27,$1,$1 \n\
639 \n\
640 stq $1,24($17) \n\
641 xor $4,$5,$5 # 5 cycles from $5 load \n\
642 ldq $23,48($17) \n\
643 xor $3,$5,$5 \n\
644 \n\
645 ldq $24,48($18) \n\
646 ldq $25,48($19) \n\
647 ldq $27,48($20) \n\
648 ldq $0,56($17) \n\
649 \n\
650 ldq $1,56($18) \n\
651 ldq $2,56($19) \n\
652 ldq $3,56($20) \n\
653 xor $6,$7,$7 # 8 cycles from $6 load \n\
654 \n\
655 ldq $31,256($17) \n\
656 xor $21,$22,$22 # 8 cycles from $22 load \n\
657 ldq $31,256($18) \n\
658 xor $7,$22,$22 \n\
659 \n\
660 ldq $31,256($19) \n\
661 xor $23,$24,$24 # 6 cycles from $24 load \n\
662 ldq $31,256($20) \n\
663 xor $25,$27,$27 # 6 cycles from $27 load \n\
664 \n\
665 stq $5,32($17) \n\
666 xor $24,$27,$27 \n\
667 xor $0,$1,$1 # 7 cycles from $1 load \n\
668 xor $2,$3,$3 # 6 cycles from $3 load \n\
669 \n\
670 stq $22,40($17) \n\
671 xor $1,$3,$3 \n\
672 stq $27,48($17) \n\
673 subq $16,1,$16 \n\
674 \n\
675 stq $3,56($17) \n\
676 addq $20,64,$20 \n\
677 addq $19,64,$19 \n\
678 addq $18,64,$18 \n\
679 \n\
680 addq $17,64,$17 \n\
681 bgt $16,4b \n\
682 ret \n\
683 .end xor_alpha_prefetch_4 \n\
684 \n\
685 .align 3 \n\
686 .ent xor_alpha_prefetch_5 \n\
687 xor_alpha_prefetch_5: \n\
688 .prologue 0 \n\
689 srl $16, 6, $16 \n\
690 \n\
691 ldq $31, 0($17) \n\
692 ldq $31, 0($18) \n\
693 ldq $31, 0($19) \n\
694 ldq $31, 0($20) \n\
695 ldq $31, 0($21) \n\
696 \n\
697 ldq $31, 64($17) \n\
698 ldq $31, 64($18) \n\
699 ldq $31, 64($19) \n\
700 ldq $31, 64($20) \n\
701 ldq $31, 64($21) \n\
702 \n\
703 ldq $31, 128($17) \n\
704 ldq $31, 128($18) \n\
705 ldq $31, 128($19) \n\
706 ldq $31, 128($20) \n\
707 ldq $31, 128($21) \n\
708 \n\
709 ldq $31, 192($17) \n\
710 ldq $31, 192($18) \n\
711 ldq $31, 192($19) \n\
712 ldq $31, 192($20) \n\
713 ldq $31, 192($21) \n\
714 .align 4 \n\
715 5: \n\
716 ldq $0,0($17) \n\
717 ldq $1,0($18) \n\
718 ldq $2,0($19) \n\
719 ldq $3,0($20) \n\
720 \n\
721 ldq $4,0($21) \n\
722 ldq $5,8($17) \n\
723 ldq $6,8($18) \n\
724 ldq $7,8($19) \n\
725 \n\
726 ldq $22,8($20) \n\
727 ldq $23,8($21) \n\
728 ldq $24,16($17) \n\
729 ldq $25,16($18) \n\
730 \n\
731 ldq $27,16($19) \n\
732 xor $0,$1,$1 # 6 cycles from $1 load \n\
733 ldq $28,16($20) \n\
734 xor $2,$3,$3 # 6 cycles from $3 load \n\
735 \n\
736 ldq $0,16($21) \n\
737 xor $1,$3,$3 \n\
738 ldq $1,24($17) \n\
739 xor $3,$4,$4 # 7 cycles from $4 load \n\
740 \n\
741 stq $4,0($17) \n\
742 xor $5,$6,$6 # 7 cycles from $6 load \n\
743 xor $7,$22,$22 # 7 cycles from $22 load \n\
744 xor $6,$23,$23 # 7 cycles from $23 load \n\
745 \n\
746 ldq $2,24($18) \n\
747 xor $22,$23,$23 \n\
748 ldq $3,24($19) \n\
749 xor $24,$25,$25 # 8 cycles from $25 load \n\
750 \n\
751 stq $23,8($17) \n\
752 xor $25,$27,$27 # 8 cycles from $27 load \n\
753 ldq $4,24($20) \n\
754 xor $28,$0,$0 # 7 cycles from $0 load \n\
755 \n\
756 ldq $5,24($21) \n\
757 xor $27,$0,$0 \n\
758 ldq $6,32($17) \n\
759 ldq $7,32($18) \n\
760 \n\
761 stq $0,16($17) \n\
762 xor $1,$2,$2 # 6 cycles from $2 load \n\
763 ldq $22,32($19) \n\
764 xor $3,$4,$4 # 4 cycles from $4 load \n\
765 \n\
766 ldq $23,32($20) \n\
767 xor $2,$4,$4 \n\
768 ldq $24,32($21) \n\
769 ldq $25,40($17) \n\
770 \n\
771 ldq $27,40($18) \n\
772 ldq $28,40($19) \n\
773 ldq $0,40($20) \n\
774 xor $4,$5,$5 # 7 cycles from $5 load \n\
775 \n\
776 stq $5,24($17) \n\
777 xor $6,$7,$7 # 7 cycles from $7 load \n\
778 ldq $1,40($21) \n\
779 ldq $2,48($17) \n\
780 \n\
781 ldq $3,48($18) \n\
782 xor $7,$22,$22 # 7 cycles from $22 load \n\
783 ldq $4,48($19) \n\
784 xor $23,$24,$24 # 6 cycles from $24 load \n\
785 \n\
786 ldq $5,48($20) \n\
787 xor $22,$24,$24 \n\
788 ldq $6,48($21) \n\
789 xor $25,$27,$27 # 7 cycles from $27 load \n\
790 \n\
791 stq $24,32($17) \n\
792 xor $27,$28,$28 # 8 cycles from $28 load \n\
793 ldq $7,56($17) \n\
794 xor $0,$1,$1 # 6 cycles from $1 load \n\
795 \n\
796 ldq $22,56($18) \n\
797 ldq $23,56($19) \n\
798 ldq $24,56($20) \n\
799 ldq $25,56($21) \n\
800 \n\
801 ldq $31,256($17) \n\
802 xor $28,$1,$1 \n\
803 ldq $31,256($18) \n\
804 xor $2,$3,$3 # 9 cycles from $3 load \n\
805 \n\
806 ldq $31,256($19) \n\
807 xor $3,$4,$4 # 9 cycles from $4 load \n\
808 ldq $31,256($20) \n\
809 xor $5,$6,$6 # 8 cycles from $6 load \n\
810 \n\
811 stq $1,40($17) \n\
812 xor $4,$6,$6 \n\
813 xor $7,$22,$22 # 7 cycles from $22 load \n\
814 xor $23,$24,$24 # 6 cycles from $24 load \n\
815 \n\
816 stq $6,48($17) \n\
817 xor $22,$24,$24 \n\
818 ldq $31,256($21) \n\
819 xor $24,$25,$25 # 8 cycles from $25 load \n\
820 \n\
821 stq $25,56($17) \n\
822 subq $16,1,$16 \n\
823 addq $21,64,$21 \n\
824 addq $20,64,$20 \n\
825 \n\
826 addq $19,64,$19 \n\
827 addq $18,64,$18 \n\
828 addq $17,64,$17 \n\
829 bgt $16,5b \n\
830 \n\
831 ret \n\
832 .end xor_alpha_prefetch_5 \n\
833 ");
834
835 static struct xor_block_template xor_block_alpha = {
836 .name = "alpha",
837 .do_2 = xor_alpha_2,
838 .do_3 = xor_alpha_3,
839 .do_4 = xor_alpha_4,
840 .do_5 = xor_alpha_5,
841 };
842
843 static struct xor_block_template xor_block_alpha_prefetch = {
844 .name = "alpha prefetch",
845 .do_2 = xor_alpha_prefetch_2,
846 .do_3 = xor_alpha_prefetch_3,
847 .do_4 = xor_alpha_prefetch_4,
848 .do_5 = xor_alpha_prefetch_5,
849 };
850
851 /* For grins, also test the generic routines. */
852 #include <asm-generic/xor.h>
853
854 #undef XOR_TRY_TEMPLATES
855 #define XOR_TRY_TEMPLATES \
856 do { \
857 xor_speed(&xor_block_8regs); \
858 xor_speed(&xor_block_32regs); \
859 xor_speed(&xor_block_alpha); \
860 xor_speed(&xor_block_alpha_prefetch); \
861 } while (0)
862
863 /* Force the use of alpha_prefetch if EV6, as it is significantly
864 faster in the cold cache case. */
865 #define XOR_SELECT_TEMPLATE(FASTEST) \
866 (implver() == IMPLVER_EV6 ? &xor_block_alpha_prefetch : FASTEST)
867
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.