about summary refs log tree commit diff
path: root/sysdeps/aarch64/multiarch/memcpy_thunderx2.S
blob: 09b4ef1ba6f05b6074ceaebe1be7e37251d7c5f5 (plain) (blame)
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
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
/* A Thunderx2 Optimized memcpy implementation for AARCH64.
   Copyright (C) 2018 Free Software Foundation, Inc.

   This file is part of the GNU C Library.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library 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
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <http://www.gnu.org/licenses/>.  */

#include <sysdep.h>

/* Assumptions:
 *
 * ARMv8-a, AArch64, unaligned accesses.
 *
 */

#define dstin	x0
#define src	x1
#define count	x2
#define dst	x3
#define srcend	x4
#define dstend	x5
#define tmp2    x6
#define tmp3    x7
#define tmp3w   w7
#define A_l	x6
#define A_lw	w6
#define A_h	x7
#define A_hw	w7
#define B_l	x8
#define B_lw	w8
#define B_h	x9
#define C_l	x10
#define C_h	x11
#define D_l	x12
#define D_h	x13
#define E_l	src
#define E_h	count
#define F_l	srcend
#define F_h	dst
#define G_l	count
#define G_h	dst
#define tmp1	x14

#define A_q     q0
#define B_q     q1
#define C_q     q2
#define D_q     q3
#define E_q     q4
#define F_q     q5
#define G_q     q6
#define H_q	q7
#define I_q	q16
#define J_q	q17

#define A_v     v0
#define B_v     v1
#define C_v     v2
#define D_v     v3
#define E_v     v4
#define F_v     v5
#define G_v     v6
#define H_v     v7
#define I_v     v16
#define J_v	v17

#ifndef MEMMOVE
# define MEMMOVE memmove
#endif
#ifndef MEMCPY
# define MEMCPY memcpy
#endif

#if IS_IN (libc)

#undef MEMCPY
#undef MEMMOVE
#define MEMCPY __memcpy_thunderx2
#define MEMMOVE __memmove_thunderx2


/* Moves are split into 3 main cases: small copies of up to 16 bytes,
   medium copies of 17..96 bytes which are fully unrolled. Large copies
   of more than 96 bytes align the destination and use an unrolled loop
   processing 64 bytes per iteration.
   Overlapping large forward memmoves use a loop that copies backwards.
*/

ENTRY_ALIGN (MEMMOVE, 6)

	DELOUSE (0)
	DELOUSE (1)
	DELOUSE (2)

	sub	tmp1, dstin, src
	cmp	count, 96
	ccmp	tmp1, count, 2, hi
	b.lo	L(move_long)

	prfm	PLDL1KEEP, [src]
	add	srcend, src, count
	add	dstend, dstin, count
	cmp	count, 16
	b.ls	L(copy16)
	cmp	count, 96
	b.hi	L(copy_long)

	/* Medium copies: 17..96 bytes.  */
	sub	tmp1, count, 1
	ldp	A_l, A_h, [src]
	tbnz	tmp1, 6, L(copy96)
	ldp	D_l, D_h, [srcend, -16]
	tbz	tmp1, 5, 1f
	ldp	B_l, B_h, [src, 16]
	ldp	C_l, C_h, [srcend, -32]
	stp	B_l, B_h, [dstin, 16]
	stp	C_l, C_h, [dstend, -32]
1:
	stp	A_l, A_h, [dstin]
	stp	D_l, D_h, [dstend, -16]
	ret

	.p2align 4
	/* Small copies: 0..16 bytes.  */
L(copy16):
	cmp	count, 8
	b.lo	1f
	ldr	A_l, [src]
	ldr	A_h, [srcend, -8]
	str	A_l, [dstin]
	str	A_h, [dstend, -8]
	ret
	.p2align 4
1:
	tbz	count, 2, 1f
	ldr	A_lw, [src]
	ldr	A_hw, [srcend, -4]
	str	A_lw, [dstin]
	str	A_hw, [dstend, -4]
	ret

	/* Copy 0..3 bytes.  Use a branchless sequence that copies the same
	   byte 3 times if count==1, or the 2nd byte twice if count==2.  */
1:
	cbz	count, 2f
	lsr	tmp1, count, 1
	ldrb	A_lw, [src]
	ldrb	A_hw, [srcend, -1]
	ldrb	B_lw, [src, tmp1]
	strb	A_lw, [dstin]
	strb	B_lw, [dstin, tmp1]
	strb	A_hw, [dstend, -1]
2:	ret

	.p2align 4
	/* Copy 64..96 bytes.  Copy 64 bytes from the start and
	   32 bytes from the end.  */
L(copy96):
	ldp	B_l, B_h, [src, 16]
	ldp	C_l, C_h, [src, 32]
	ldp	D_l, D_h, [src, 48]
	ldp	E_l, E_h, [srcend, -32]
	ldp	F_l, F_h, [srcend, -16]
	stp	A_l, A_h, [dstin]
	stp	B_l, B_h, [dstin, 16]
	stp	C_l, C_h, [dstin, 32]
	stp	D_l, D_h, [dstin, 48]
	stp	E_l, E_h, [dstend, -32]
	stp	F_l, F_h, [dstend, -16]
	ret

	/* Align DST to 16 byte alignment so that we don't cross cache line
	   boundaries on both loads and stores.  There are at least 96 bytes
	   to copy, so copy 16 bytes unaligned and then align.  The loop
	   copies 64 bytes per iteration and prefetches one iteration ahead.  */

	.p2align 4
L(copy_long):
	and	tmp1, dstin, 15
	bic	dst, dstin, 15
	ldp	D_l, D_h, [src]
	sub	src, src, tmp1
	add	count, count, tmp1	/* Count is now 16 too large.  */
	ldp	A_l, A_h, [src, 16]
	stp	D_l, D_h, [dstin]
	ldp	B_l, B_h, [src, 32]
	ldp	C_l, C_h, [src, 48]
	ldp	D_l, D_h, [src, 64]!
	subs	count, count, 128 + 16	/* Test and readjust count.  */
	b.ls	L(last64)
L(loop64):
	stp	A_l, A_h, [dst, 16]
	ldp	A_l, A_h, [src, 16]
	stp	B_l, B_h, [dst, 32]
	ldp	B_l, B_h, [src, 32]
	stp	C_l, C_h, [dst, 48]
	ldp	C_l, C_h, [src, 48]
	stp	D_l, D_h, [dst, 64]!
	ldp	D_l, D_h, [src, 64]!
	subs	count, count, 64
	b.hi	L(loop64)

	/* Write the last full set of 64 bytes.  The remainder is at most 64
	   bytes, so it is safe to always copy 64 bytes from the end even if
	   there is just 1 byte left.  */
L(last64):
	ldp	E_l, E_h, [srcend, -64]
	stp	A_l, A_h, [dst, 16]
	ldp	A_l, A_h, [srcend, -48]
	stp	B_l, B_h, [dst, 32]
	ldp	B_l, B_h, [srcend, -32]
	stp	C_l, C_h, [dst, 48]
	ldp	C_l, C_h, [srcend, -16]
	stp	D_l, D_h, [dst, 64]
	stp	E_l, E_h, [dstend, -64]
	stp	A_l, A_h, [dstend, -48]
	stp	B_l, B_h, [dstend, -32]
	stp	C_l, C_h, [dstend, -16]
	ret

	.p2align 4
L(move_long):
	cbz	tmp1, 3f

	add	srcend, src, count
	add	dstend, dstin, count

	/* Align dstend to 16 byte alignment so that we don't cross cache line
	   boundaries on both loads and stores.  There are at least 96 bytes
	   to copy, so copy 16 bytes unaligned and then align.  The loop
	   copies 64 bytes per iteration and prefetches one iteration ahead.  */

	and	tmp1, dstend, 15
	ldp	D_l, D_h, [srcend, -16]
	sub	srcend, srcend, tmp1
	sub	count, count, tmp1
	ldp	A_l, A_h, [srcend, -16]
	stp	D_l, D_h, [dstend, -16]
	ldp	B_l, B_h, [srcend, -32]
	ldp	C_l, C_h, [srcend, -48]
	ldp	D_l, D_h, [srcend, -64]!
	sub	dstend, dstend, tmp1
	subs	count, count, 128
	b.ls	2f

	nop
1:
	stp	A_l, A_h, [dstend, -16]
	ldp	A_l, A_h, [srcend, -16]
	stp	B_l, B_h, [dstend, -32]
	ldp	B_l, B_h, [srcend, -32]
	stp	C_l, C_h, [dstend, -48]
	ldp	C_l, C_h, [srcend, -48]
	stp	D_l, D_h, [dstend, -64]!
	ldp	D_l, D_h, [srcend, -64]!
	subs	count, count, 64
	b.hi	1b

	/* Write the last full set of 64 bytes.  The remainder is at most 64
	   bytes, so it is safe to always copy 64 bytes from the start even if
	   there is just 1 byte left.  */
2:
	ldp	G_l, G_h, [src, 48]
	stp	A_l, A_h, [dstend, -16]
	ldp	A_l, A_h, [src, 32]
	stp	B_l, B_h, [dstend, -32]
	ldp	B_l, B_h, [src, 16]
	stp	C_l, C_h, [dstend, -48]
	ldp	C_l, C_h, [src]
	stp	D_l, D_h, [dstend, -64]
	stp	G_l, G_h, [dstin, 48]
	stp	A_l, A_h, [dstin, 32]
	stp	B_l, B_h, [dstin, 16]
	stp	C_l, C_h, [dstin]
3:	ret

END (MEMMOVE)
libc_hidden_builtin_def (MEMMOVE)


/* Copies are split into 3 main cases: small copies of up to 16 bytes,
   medium copies of 17..96 bytes which are fully unrolled. Large copies
   of more than 96 bytes align the destination and use load-and-merge
   approach in the case src and dst addresses are unaligned not evenly,
   so that, loads and stores are always aligned.
   Large copies use an unrolled loop processing 64 bytes per iteration.
   The current optimized memcpy implementation is not compatible with
   memmove and is separated from it completely.

   memcpy implementation below is not compatible with memmove
   because of pipelined loads/stores, which are faster, but they
   can't be used in the case of overlapping memmove arrays */

#define MEMCPY_PREFETCH_LDR 640

ENTRY (MEMCPY)
	DELOUSE (0)
	DELOUSE (1)
	DELOUSE (2)

	add     srcend, src, count
	cmp     count, 16
	b.ls    L(memcopy16)
	ldr     A_q, [src], #16
	add     dstend, dstin, count
	and     tmp1, src, 15
	cmp     count, 96
	b.hi    L(memcopy_long)

	/* Medium copies: 17..96 bytes.  */
	ldr     E_q, [srcend, -16]
	cmp     count, 64
	b.gt    L(memcpy_copy96)
	cmp     count, 48
	b.le    L(bytes_17_to_48)
	/* 49..64 bytes */
	ldp     B_q, C_q, [src]
	str     E_q, [dstend, -16]
	stp     A_q, B_q, [dstin]
	str     C_q, [dstin, 32]
	ret

L(bytes_17_to_48):
	/* 17..48 bytes*/
	cmp     count, 32
	b.gt    L(bytes_32_to_48)
	/* 17..32 bytes*/
	str     A_q, [dstin]
	str     E_q, [dstend, -16]
	ret

L(bytes_32_to_48):
	/* 32..48 */
	ldr     B_q, [src]
	str     A_q, [dstin]
	str     E_q, [dstend, -16]
	str     B_q, [dstin, 16]
	ret

	.p2align 4
	/* Small copies: 0..16 bytes.  */
L(memcopy16):
	cmp     count, 8
	b.lo    L(bytes_0_to_8)
	ldr     A_l, [src]
	ldr     A_h, [srcend, -8]
	add     dstend, dstin, count
	str     A_l, [dstin]
	str     A_h, [dstend, -8]
	ret
	.p2align 4

L(bytes_0_to_8):
	tbz     count, 2, L(bytes_0_to_3)
	ldr     A_lw, [src]
	ldr     A_hw, [srcend, -4]
	add     dstend, dstin, count
	str     A_lw, [dstin]
	str     A_hw, [dstend, -4]
	ret

	/* Copy 0..3 bytes.  Use a branchless sequence that copies the same
	   byte 3 times if count==1, or the 2nd byte twice if count==2.  */
L(bytes_0_to_3):
	cbz     count, L(end)
	lsr     tmp1, count, 1
	ldrb    A_lw, [src]
	ldrb    A_hw, [srcend, -1]
	add     dstend, dstin, count
	ldrb    B_lw, [src, tmp1]
	strb    A_lw, [dstin]
	strb    B_lw, [dstin, tmp1]
	strb    A_hw, [dstend, -1]
L(end): ret

	.p2align 4

L(memcpy_copy96):
	/* Copying 65..96 bytes. A_q (first 16 bytes) and
	   E_q(last 16 bytes) are already loaded.

	   The size is large enough to benefit from aligned
	   loads */
	bic     src, src, 15
	ldp     B_q, C_q, [src]
	str     A_q, [dstin]
	/* Loaded 64 bytes, second 16-bytes chunk can be
	   overlapping with the first chunk by tmp1 bytes.
	   Stored 16 bytes. */
	sub     dst, dstin, tmp1
	add     count, count, tmp1
	/* The range of count being [65..96] becomes [65..111]
	   after tmp [0..15] gets added to it,
	   count now is <bytes-left-to-load>+48 */
	cmp     count, 80
	b.gt    L(copy96_medium)
	ldr     D_q, [src, 32]
	stp     B_q, C_q, [dst, 16]
	str     E_q, [dstend, -16]
	str     D_q, [dst, 48]
	ret

	.p2align 4
L(copy96_medium):
	ldp     D_q, A_q, [src, 32]
	str     B_q, [dst, 16]
	cmp     count, 96
	b.gt    L(copy96_large)
	str     E_q, [dstend, -16]
	stp     C_q, D_q, [dst, 32]
	str     A_q, [dst, 64]
	ret

L(copy96_large):
	ldr     F_q, [src, 64]
	stp     C_q, D_q, [dst, 32]
	str     E_q, [dstend, -16]
	stp     A_q, F_q, [dst, 64]
	ret

	.p2align 4
L(memcopy_long):
	bic     src, src, 15
	ldp     B_q, C_q, [src], #32
	str     A_q, [dstin]
	sub     dst, dstin, tmp1
	add     count, count, tmp1
	add     dst, dst, 16
	and	tmp1, dst, 15
	ldp     D_q, E_q, [src], #32
	str     B_q, [dst], #16

	/* Already loaded 64+16 bytes. Check if at
	   least 64 more bytes left */
	subs    count, count, 64+64+16
	b.lt    L(loop128_exit2)
	cmp     count, MEMCPY_PREFETCH_LDR + 64 + 32
	b.lt    L(loop128)
	cbnz	tmp1, L(dst_unaligned)
	sub     count, count, MEMCPY_PREFETCH_LDR + 64 + 32

	.p2align 4

L(loop128_prefetch):
	str     C_q, [dst], #16
	prfm    pldl1strm, [src, MEMCPY_PREFETCH_LDR]
	str     D_q, [dst], #16
	ldp     F_q, G_q, [src], #32
	str	E_q, [dst], #16
	ldp     H_q, A_q, [src], #32
	str     F_q, [dst], #16
	prfm    pldl1strm, [src, MEMCPY_PREFETCH_LDR]
	str     G_q, [dst], #16
	ldp     B_q, C_q, [src], #32
	str	H_q, [dst], #16
	ldp     D_q, E_q, [src], #32
	stp	A_q, B_q, [dst], #32
	subs	count, count, 128
	b.ge    L(loop128_prefetch)

L(preloop128):
	add	count, count, MEMCPY_PREFETCH_LDR + 64 + 32
	.p2align 4
L(loop128):
	ldp     F_q, G_q, [src], #32
	str     C_q, [dst], #16
	ldp     B_q, A_q, [src], #32
	str     D_q, [dst], #16
	stp     E_q, F_q, [dst], #32
	stp     G_q, B_q, [dst], #32
	subs    count, count, 64
	b.lt    L(loop128_exit1)
L(loop128_proceed):
	ldp     B_q, C_q, [src], #32
	str     A_q, [dst], #16
	ldp     D_q, E_q, [src], #32
	str     B_q, [dst], #16
	subs    count, count, 64
	b.ge    L(loop128)

	.p2align 4
L(loop128_exit2):
	stp     C_q, D_q, [dst], #32
	str     E_q, [dst], #16
	b       L(copy_long_check32);

L(loop128_exit1):
	/* A_q is still not stored and 0..63 bytes left,
	   so, count is -64..-1.
	   Check if less than 32 bytes left (count < -32) */
	str     A_q, [dst], #16
L(copy_long_check32):
	cmn     count, 64
	b.eq    L(copy_long_done)
	cmn     count, 32
	b.le    L(copy_long_last32)
	ldp     B_q, C_q, [src]
	stp     B_q, C_q, [dst]

L(copy_long_last32):
	ldp     F_q, G_q, [srcend, -32]
	stp     F_q, G_q, [dstend, -32]

L(copy_long_done):
	ret

L(dst_unaligned):
	/* For the unaligned store case the code loads two
	   aligned chunks and then merges them using ext
	   instruction. This can be up to 30% faster than
	   the the simple unaligned store access.

	   Current state: tmp1 = dst % 16; C_q, D_q, E_q
	   contains data yet to be stored. src and dst points
	   to next-to-be-processed data. A_q, B_q contains
	   data already stored before, count = bytes left to
	   be load decremented by 64.

	   The control is passed here if at least 64 bytes left
	   to be loaded. The code does two aligned loads and then
	   extracts (16-tmp1) bytes from the first register and
	   tmp1 bytes from the next register forming the value
	   for the aligned store.

	   As ext instruction can only have it's index encoded
	   as immediate. 15 code chunks process each possible
	   index value. Computed goto is used to reach the
	   required code. */

	/* Store the 16 bytes to dst and align dst for further
	   operations, several bytes will be stored at this
	   address once more */
	str     C_q, [dst], #16
	ldp     F_q, G_q, [src], #32
	bic	dst, dst, 15
	adrp	tmp2, L(ext_table)
	add	tmp2, tmp2, :lo12:L(ext_table)
	add	tmp2, tmp2, tmp1, LSL #2
	ldr	tmp3w, [tmp2]
	add	tmp2, tmp2, tmp3w, SXTW
	br	tmp2

#define EXT_CHUNK(shft) \
.p2align 4 ;\
L(ext_size_ ## shft):;\
	ext     A_v.16b, C_v.16b, D_v.16b, 16-shft;\
	ext     B_v.16b, D_v.16b, E_v.16b, 16-shft;\
	subs    count, count, 32;\
	b.ge    2f;\
1:;\
	stp     A_q, B_q, [dst], #32;\
	ext     H_v.16b, E_v.16b, F_v.16b, 16-shft;\
	ext     I_v.16b, F_v.16b, G_v.16b, 16-shft;\
	stp     H_q, I_q, [dst], #16;\
	add     dst, dst, tmp1;\
	str     G_q, [dst], #16;\
	b       L(copy_long_check32);\
2:;\
	stp     A_q, B_q, [dst], #32;\
	prfm    pldl1strm, [src, MEMCPY_PREFETCH_LDR];\
	ldp     D_q, J_q, [src], #32;\
	ext     H_v.16b, E_v.16b, F_v.16b, 16-shft;\
	ext     I_v.16b, F_v.16b, G_v.16b, 16-shft;\
	mov     C_v.16b, G_v.16b;\
	stp     H_q, I_q, [dst], #32;\
	ldp     F_q, G_q, [src], #32;\
	ext     A_v.16b, C_v.16b, D_v.16b, 16-shft;\
	ext     B_v.16b, D_v.16b, J_v.16b, 16-shft;\
	mov     E_v.16b, J_v.16b;\
	subs    count, count, 64;\
	b.ge    2b;\
	b	1b;\

EXT_CHUNK(1)
EXT_CHUNK(2)
EXT_CHUNK(3)
EXT_CHUNK(4)
EXT_CHUNK(5)
EXT_CHUNK(6)
EXT_CHUNK(7)
EXT_CHUNK(8)
EXT_CHUNK(9)
EXT_CHUNK(10)
EXT_CHUNK(11)
EXT_CHUNK(12)
EXT_CHUNK(13)
EXT_CHUNK(14)
EXT_CHUNK(15)

END (MEMCPY)
	.section	.rodata
	.p2align	4

L(ext_table):
	/* The first entry is for the alignment of 0 and is never
	   actually used (could be any value).  */
	.word	0
	.word	L(ext_size_1) -.
	.word	L(ext_size_2) -.
	.word	L(ext_size_3) -.
	.word	L(ext_size_4) -.
	.word	L(ext_size_5) -.
	.word	L(ext_size_6) -.
	.word	L(ext_size_7) -.
	.word	L(ext_size_8) -.
	.word	L(ext_size_9) -.
	.word	L(ext_size_10) -.
	.word	L(ext_size_11) -.
	.word	L(ext_size_12) -.
	.word	L(ext_size_13) -.
	.word	L(ext_size_14) -.
	.word	L(ext_size_15) -.

libc_hidden_builtin_def (MEMCPY)
#endif