about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
blob: 9bab1147d57a520ab82d32f80728061945fa731d (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
/* memmove/memcpy/mempcpy with unaligned load/store and rep movsb
   Copyright (C) 2016-2018 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/>.  */

/* memmove/memcpy/mempcpy is implemented as:
   1. Use overlapping load and store to avoid branch.
   2. Load all sources into registers and store them together to avoid
      possible address overlap between source and destination.
   3. If size is 8 * VEC_SIZE or less, load all sources into registers
      and store them together.
   4. If address of destination > address of source, backward copy
      4 * VEC_SIZE at a time with unaligned load and aligned store.
      Load the first 4 * VEC and last VEC before the loop and store
      them after the loop to support overlapping addresses.
   5. Otherwise, forward copy 4 * VEC_SIZE at a time with unaligned
      load and aligned store.  Load the last 4 * VEC and first VEC
      before the loop and store them after the loop to support
      overlapping addresses.
   6. If size >= __x86_shared_non_temporal_threshold and there is no
      overlap between destination and source, use non-temporal store
      instead of aligned store.  */

#include <sysdep.h>

#ifndef MEMCPY_SYMBOL
# define MEMCPY_SYMBOL(p,s)		MEMMOVE_SYMBOL(p, s)
#endif

#ifndef MEMPCPY_SYMBOL
# define MEMPCPY_SYMBOL(p,s)		MEMMOVE_SYMBOL(p, s)
#endif

#ifndef MEMMOVE_CHK_SYMBOL
# define MEMMOVE_CHK_SYMBOL(p,s)	MEMMOVE_SYMBOL(p, s)
#endif

#ifndef VZEROUPPER
# if VEC_SIZE > 16
#  define VZEROUPPER vzeroupper
# else
#  define VZEROUPPER
# endif
#endif

/* Threshold to use Enhanced REP MOVSB.  Since there is overhead to set
   up REP MOVSB operation, REP MOVSB isn't faster on short data.  The
   memcpy micro benchmark in glibc shows that 2KB is the approximate
   value above which REP MOVSB becomes faster than SSE2 optimization
   on processors with Enhanced REP MOVSB.  Since larger register size
   can move more data with a single load and store, the threshold is
   higher with larger register size.  */
#ifndef REP_MOVSB_THRESHOLD
# define REP_MOVSB_THRESHOLD	(2048 * (VEC_SIZE / 16))
#endif

#ifndef PREFETCH
# define PREFETCH(addr) prefetcht0 addr
#endif

/* Assume 64-byte prefetch size.  */
#ifndef PREFETCH_SIZE
# define PREFETCH_SIZE 64
#endif

#define PREFETCHED_LOAD_SIZE (VEC_SIZE * 4)

#if PREFETCH_SIZE == 64
# if PREFETCHED_LOAD_SIZE == PREFETCH_SIZE
#  define PREFETCH_ONE_SET(dir, base, offset) \
	PREFETCH ((offset)base)
# elif PREFETCHED_LOAD_SIZE == 2 * PREFETCH_SIZE
#  define PREFETCH_ONE_SET(dir, base, offset) \
	PREFETCH ((offset)base); \
	PREFETCH ((offset + dir * PREFETCH_SIZE)base)
# elif PREFETCHED_LOAD_SIZE == 4 * PREFETCH_SIZE
#  define PREFETCH_ONE_SET(dir, base, offset) \
	PREFETCH ((offset)base); \
	PREFETCH ((offset + dir * PREFETCH_SIZE)base); \
	PREFETCH ((offset + dir * PREFETCH_SIZE * 2)base); \
	PREFETCH ((offset + dir * PREFETCH_SIZE * 3)base)
# else
#   error Unsupported PREFETCHED_LOAD_SIZE!
# endif
#else
# error Unsupported PREFETCH_SIZE!
#endif

#ifndef SECTION
# error SECTION is not defined!
#endif

	.section SECTION(.text),"ax",@progbits
#if defined SHARED && IS_IN (libc)
ENTRY (MEMMOVE_CHK_SYMBOL (__mempcpy_chk, unaligned))
	cmp	%RDX_LP, %RCX_LP
	jb	HIDDEN_JUMPTARGET (__chk_fail)
END (MEMMOVE_CHK_SYMBOL (__mempcpy_chk, unaligned))
#endif

ENTRY (MEMPCPY_SYMBOL (__mempcpy, unaligned))
	mov	%RDI_LP, %RAX_LP
	add	%RDX_LP, %RAX_LP
	jmp	L(start)
END (MEMPCPY_SYMBOL (__mempcpy, unaligned))

#if defined SHARED && IS_IN (libc)
ENTRY (MEMMOVE_CHK_SYMBOL (__memmove_chk, unaligned))
	cmp	%RDX_LP, %RCX_LP
	jb	HIDDEN_JUMPTARGET (__chk_fail)
END (MEMMOVE_CHK_SYMBOL (__memmove_chk, unaligned))
#endif

ENTRY (MEMMOVE_SYMBOL (__memmove, unaligned))
	movq	%rdi, %rax
L(start):
# ifdef __ILP32__
	/* Clear the upper 32 bits.  */
	movl	%edx, %edx
# endif
	cmp	$VEC_SIZE, %RDX_LP
	jb	L(less_vec)
	cmp	$(VEC_SIZE * 2), %RDX_LP
	ja	L(more_2x_vec)
#if !defined USE_MULTIARCH || !IS_IN (libc)
L(last_2x_vec):
#endif
	/* From VEC and to 2 * VEC.  No branch when size == VEC_SIZE.  */
	VMOVU	(%rsi), %VEC(0)
	VMOVU	-VEC_SIZE(%rsi,%rdx), %VEC(1)
	VMOVU	%VEC(0), (%rdi)
	VMOVU	%VEC(1), -VEC_SIZE(%rdi,%rdx)
	VZEROUPPER
#if !defined USE_MULTIARCH || !IS_IN (libc)
L(nop):
#endif
	ret
#if defined USE_MULTIARCH && IS_IN (libc)
END (MEMMOVE_SYMBOL (__memmove, unaligned))

# if VEC_SIZE == 16
ENTRY (__mempcpy_chk_erms)
	cmp	%RDX_LP, %RCX_LP
	jb	HIDDEN_JUMPTARGET (__chk_fail)
END (__mempcpy_chk_erms)

/* Only used to measure performance of REP MOVSB.  */
ENTRY (__mempcpy_erms)
	mov	%RDI_LP, %RAX_LP
	/* Skip zero length.  */
	test	%RDX_LP, %RDX_LP
	jz	2f
	add	%RDX_LP, %RAX_LP
	jmp	L(start_movsb)
END (__mempcpy_erms)

ENTRY (__memmove_chk_erms)
	cmp	%RDX_LP, %RCX_LP
	jb	HIDDEN_JUMPTARGET (__chk_fail)
END (__memmove_chk_erms)

ENTRY (__memmove_erms)
	movq	%rdi, %rax
	/* Skip zero length.  */
	test	%RDX_LP, %RDX_LP
	jz	2f
L(start_movsb):
	mov	%RDX_LP, %RCX_LP
	cmp	%RSI_LP, %RDI_LP
	jb	1f
	/* Source == destination is less common.  */
	je	2f
	lea	(%rsi,%rcx), %RDX_LP
	cmp	%RDX_LP, %RDI_LP
	jb	L(movsb_backward)
1:
	rep movsb
2:
	ret
L(movsb_backward):
	leaq	-1(%rdi,%rcx), %rdi
	leaq	-1(%rsi,%rcx), %rsi
	std
	rep movsb
	cld
	ret
END (__memmove_erms)
strong_alias (__memmove_erms, __memcpy_erms)
strong_alias (__memmove_chk_erms, __memcpy_chk_erms)
# endif

# ifdef SHARED
ENTRY (MEMMOVE_CHK_SYMBOL (__mempcpy_chk, unaligned_erms))
	cmp	%RDX_LP, %RCX_LP
	jb	HIDDEN_JUMPTARGET (__chk_fail)
END (MEMMOVE_CHK_SYMBOL (__mempcpy_chk, unaligned_erms))
# endif

ENTRY (MEMMOVE_SYMBOL (__mempcpy, unaligned_erms))
	mov	%RDI_LP, %RAX_LP
	add	%RDX_LP, %RAX_LP
	jmp	L(start_erms)
END (MEMMOVE_SYMBOL (__mempcpy, unaligned_erms))

# ifdef SHARED
ENTRY (MEMMOVE_CHK_SYMBOL (__memmove_chk, unaligned_erms))
	cmp	%RDX_LP, %RCX_LP
	jb	HIDDEN_JUMPTARGET (__chk_fail)
END (MEMMOVE_CHK_SYMBOL (__memmove_chk, unaligned_erms))
# endif

ENTRY (MEMMOVE_SYMBOL (__memmove, unaligned_erms))
	movq	%rdi, %rax
L(start_erms):
# ifdef __ILP32__
	/* Clear the upper 32 bits.  */
	movl	%edx, %edx
# endif
	cmp	$VEC_SIZE, %RDX_LP
	jb	L(less_vec)
	cmp	$(VEC_SIZE * 2), %RDX_LP
	ja	L(movsb_more_2x_vec)
L(last_2x_vec):
	/* From VEC and to 2 * VEC.  No branch when size == VEC_SIZE. */
	VMOVU	(%rsi), %VEC(0)
	VMOVU	-VEC_SIZE(%rsi,%rdx), %VEC(1)
	VMOVU	%VEC(0), (%rdi)
	VMOVU	%VEC(1), -VEC_SIZE(%rdi,%rdx)
L(return):
	VZEROUPPER
	ret

L(movsb):
	cmpq	__x86_shared_non_temporal_threshold(%rip), %rdx
	jae	L(more_8x_vec)
	cmpq	%rsi, %rdi
	jb	1f
	/* Source == destination is less common.  */
	je	L(nop)
	leaq	(%rsi,%rdx), %r9
	cmpq	%r9, %rdi
	/* Avoid slow backward REP MOVSB.  */
# if REP_MOVSB_THRESHOLD <= (VEC_SIZE * 8)
#  error Unsupported REP_MOVSB_THRESHOLD and VEC_SIZE!
# endif
	jb	L(more_8x_vec_backward)
1:
	mov	%RDX_LP, %RCX_LP
	rep movsb
L(nop):
	ret
#endif

L(less_vec):
	/* Less than 1 VEC.  */
#if VEC_SIZE != 16 && VEC_SIZE != 32 && VEC_SIZE != 64
# error Unsupported VEC_SIZE!
#endif
#if VEC_SIZE > 32
	cmpb	$32, %dl
	jae	L(between_32_63)
#endif
#if VEC_SIZE > 16
	cmpb	$16, %dl
	jae	L(between_16_31)
#endif
	cmpb	$8, %dl
	jae	L(between_8_15)
	cmpb	$4, %dl
	jae	L(between_4_7)
	cmpb	$1, %dl
	ja	L(between_2_3)
	jb	1f
	movzbl	(%rsi), %ecx
	movb	%cl, (%rdi)
1:
	ret
#if VEC_SIZE > 32
L(between_32_63):
	/* From 32 to 63.  No branch when size == 32.  */
	vmovdqu	(%rsi), %ymm0
	vmovdqu	-32(%rsi,%rdx), %ymm1
	vmovdqu	%ymm0, (%rdi)
	vmovdqu	%ymm1, -32(%rdi,%rdx)
	VZEROUPPER
	ret
#endif
#if VEC_SIZE > 16
	/* From 16 to 31.  No branch when size == 16.  */
L(between_16_31):
	vmovdqu	(%rsi), %xmm0
	vmovdqu	-16(%rsi,%rdx), %xmm1
	vmovdqu	%xmm0, (%rdi)
	vmovdqu	%xmm1, -16(%rdi,%rdx)
	ret
#endif
L(between_8_15):
	/* From 8 to 15.  No branch when size == 8.  */
	movq	-8(%rsi,%rdx), %rcx
	movq	(%rsi), %rsi
	movq	%rcx, -8(%rdi,%rdx)
	movq	%rsi, (%rdi)
	ret
L(between_4_7):
	/* From 4 to 7.  No branch when size == 4.  */
	movl	-4(%rsi,%rdx), %ecx
	movl	(%rsi), %esi
	movl	%ecx, -4(%rdi,%rdx)
	movl	%esi, (%rdi)
	ret
L(between_2_3):
	/* From 2 to 3.  No branch when size == 2.  */
	movzwl	-2(%rsi,%rdx), %ecx
	movzwl	(%rsi), %esi
	movw	%cx, -2(%rdi,%rdx)
	movw	%si, (%rdi)
	ret

#if defined USE_MULTIARCH && IS_IN (libc)
L(movsb_more_2x_vec):
	cmpq	$REP_MOVSB_THRESHOLD, %rdx
	ja	L(movsb)
#endif
L(more_2x_vec):
	/* More than 2 * VEC and there may be overlap between destination
	   and source.  */
	cmpq	$(VEC_SIZE * 8), %rdx
	ja	L(more_8x_vec)
	cmpq	$(VEC_SIZE * 4), %rdx
	jb	L(last_4x_vec)
	/* Copy from 4 * VEC to 8 * VEC, inclusively. */
	VMOVU	(%rsi), %VEC(0)
	VMOVU	VEC_SIZE(%rsi), %VEC(1)
	VMOVU	(VEC_SIZE * 2)(%rsi), %VEC(2)
	VMOVU	(VEC_SIZE * 3)(%rsi), %VEC(3)
	VMOVU	-VEC_SIZE(%rsi,%rdx), %VEC(4)
	VMOVU	-(VEC_SIZE * 2)(%rsi,%rdx), %VEC(5)
	VMOVU	-(VEC_SIZE * 3)(%rsi,%rdx), %VEC(6)
	VMOVU	-(VEC_SIZE * 4)(%rsi,%rdx), %VEC(7)
	VMOVU	%VEC(0), (%rdi)
	VMOVU	%VEC(1), VEC_SIZE(%rdi)
	VMOVU	%VEC(2), (VEC_SIZE * 2)(%rdi)
	VMOVU	%VEC(3), (VEC_SIZE * 3)(%rdi)
	VMOVU	%VEC(4), -VEC_SIZE(%rdi,%rdx)
	VMOVU	%VEC(5), -(VEC_SIZE * 2)(%rdi,%rdx)
	VMOVU	%VEC(6), -(VEC_SIZE * 3)(%rdi,%rdx)
	VMOVU	%VEC(7), -(VEC_SIZE * 4)(%rdi,%rdx)
	VZEROUPPER
	ret
L(last_4x_vec):
	/* Copy from 2 * VEC to 4 * VEC. */
	VMOVU	(%rsi), %VEC(0)
	VMOVU	VEC_SIZE(%rsi), %VEC(1)
	VMOVU	-VEC_SIZE(%rsi,%rdx), %VEC(2)
	VMOVU	-(VEC_SIZE * 2)(%rsi,%rdx), %VEC(3)
	VMOVU	%VEC(0), (%rdi)
	VMOVU	%VEC(1), VEC_SIZE(%rdi)
	VMOVU	%VEC(2), -VEC_SIZE(%rdi,%rdx)
	VMOVU	%VEC(3), -(VEC_SIZE * 2)(%rdi,%rdx)
	VZEROUPPER
	ret

L(more_8x_vec):
	cmpq	%rsi, %rdi
	ja	L(more_8x_vec_backward)
	/* Source == destination is less common.  */
	je	L(nop)
	/* Load the first VEC and last 4 * VEC to support overlapping
	   addresses.  */
	VMOVU	(%rsi), %VEC(4)
	VMOVU	-VEC_SIZE(%rsi, %rdx), %VEC(5)
	VMOVU	-(VEC_SIZE * 2)(%rsi, %rdx), %VEC(6)
	VMOVU	-(VEC_SIZE * 3)(%rsi, %rdx), %VEC(7)
	VMOVU	-(VEC_SIZE * 4)(%rsi, %rdx), %VEC(8)
	/* Save start and stop of the destination buffer.  */
	movq	%rdi, %r11
	leaq	-VEC_SIZE(%rdi, %rdx), %rcx
	/* Align destination for aligned stores in the loop.  Compute
	   how much destination is misaligned.  */
	movq	%rdi, %r8
	andq	$(VEC_SIZE - 1), %r8
	/* Get the negative of offset for alignment.  */
	subq	$VEC_SIZE, %r8
	/* Adjust source.  */
	subq	%r8, %rsi
	/* Adjust destination which should be aligned now.  */
	subq	%r8, %rdi
	/* Adjust length.  */
	addq	%r8, %rdx
#if (defined USE_MULTIARCH || VEC_SIZE == 16) && IS_IN (libc)
	/* Check non-temporal store threshold.  */
	cmpq	__x86_shared_non_temporal_threshold(%rip), %rdx
	ja	L(large_forward)
#endif
L(loop_4x_vec_forward):
	/* Copy 4 * VEC a time forward.  */
	VMOVU	(%rsi), %VEC(0)
	VMOVU	VEC_SIZE(%rsi), %VEC(1)
	VMOVU	(VEC_SIZE * 2)(%rsi), %VEC(2)
	VMOVU	(VEC_SIZE * 3)(%rsi), %VEC(3)
	addq	$(VEC_SIZE * 4), %rsi
	subq	$(VEC_SIZE * 4), %rdx
	VMOVA	%VEC(0), (%rdi)
	VMOVA	%VEC(1), VEC_SIZE(%rdi)
	VMOVA	%VEC(2), (VEC_SIZE * 2)(%rdi)
	VMOVA	%VEC(3), (VEC_SIZE * 3)(%rdi)
	addq	$(VEC_SIZE * 4), %rdi
	cmpq	$(VEC_SIZE * 4), %rdx
	ja	L(loop_4x_vec_forward)
	/* Store the last 4 * VEC.  */
	VMOVU	%VEC(5), (%rcx)
	VMOVU	%VEC(6), -VEC_SIZE(%rcx)
	VMOVU	%VEC(7), -(VEC_SIZE * 2)(%rcx)
	VMOVU	%VEC(8), -(VEC_SIZE * 3)(%rcx)
	/* Store the first VEC.  */
	VMOVU	%VEC(4), (%r11)
	VZEROUPPER
	ret

L(more_8x_vec_backward):
	/* Load the first 4 * VEC and last VEC to support overlapping
	   addresses.  */
	VMOVU	(%rsi), %VEC(4)
	VMOVU	VEC_SIZE(%rsi), %VEC(5)
	VMOVU	(VEC_SIZE * 2)(%rsi), %VEC(6)
	VMOVU	(VEC_SIZE * 3)(%rsi), %VEC(7)
	VMOVU	-VEC_SIZE(%rsi,%rdx), %VEC(8)
	/* Save stop of the destination buffer.  */
	leaq	-VEC_SIZE(%rdi, %rdx), %r11
	/* Align destination end for aligned stores in the loop.  Compute
	   how much destination end is misaligned.  */
	leaq	-VEC_SIZE(%rsi, %rdx), %rcx
	movq	%r11, %r9
	movq	%r11, %r8
	andq	$(VEC_SIZE - 1), %r8
	/* Adjust source.  */
	subq	%r8, %rcx
	/* Adjust the end of destination which should be aligned now.  */
	subq	%r8, %r9
	/* Adjust length.  */
	subq	%r8, %rdx
#if (defined USE_MULTIARCH || VEC_SIZE == 16) && IS_IN (libc)
	/* Check non-temporal store threshold.  */
	cmpq	__x86_shared_non_temporal_threshold(%rip), %rdx
	ja	L(large_backward)
#endif
L(loop_4x_vec_backward):
	/* Copy 4 * VEC a time backward.  */
	VMOVU	(%rcx), %VEC(0)
	VMOVU	-VEC_SIZE(%rcx), %VEC(1)
	VMOVU	-(VEC_SIZE * 2)(%rcx), %VEC(2)
	VMOVU	-(VEC_SIZE * 3)(%rcx), %VEC(3)
	subq	$(VEC_SIZE * 4), %rcx
	subq	$(VEC_SIZE * 4), %rdx
	VMOVA	%VEC(0), (%r9)
	VMOVA	%VEC(1), -VEC_SIZE(%r9)
	VMOVA	%VEC(2), -(VEC_SIZE * 2)(%r9)
	VMOVA	%VEC(3), -(VEC_SIZE * 3)(%r9)
	subq	$(VEC_SIZE * 4), %r9
	cmpq	$(VEC_SIZE * 4), %rdx
	ja	L(loop_4x_vec_backward)
	/* Store the first 4 * VEC.  */
	VMOVU	%VEC(4), (%rdi)
	VMOVU	%VEC(5), VEC_SIZE(%rdi)
	VMOVU	%VEC(6), (VEC_SIZE * 2)(%rdi)
	VMOVU	%VEC(7), (VEC_SIZE * 3)(%rdi)
	/* Store the last VEC.  */
	VMOVU	%VEC(8), (%r11)
	VZEROUPPER
	ret

#if (defined USE_MULTIARCH || VEC_SIZE == 16) && IS_IN (libc)
L(large_forward):
	/* Don't use non-temporal store if there is overlap between
	   destination and source since destination may be in cache
	   when source is loaded.  */
	leaq    (%rdi, %rdx), %r10
	cmpq    %r10, %rsi
	jb	L(loop_4x_vec_forward)
L(loop_large_forward):
	/* Copy 4 * VEC a time forward with non-temporal stores.  */
	PREFETCH_ONE_SET (1, (%rsi), PREFETCHED_LOAD_SIZE * 2)
	PREFETCH_ONE_SET (1, (%rsi), PREFETCHED_LOAD_SIZE * 3)
	VMOVU	(%rsi), %VEC(0)
	VMOVU	VEC_SIZE(%rsi), %VEC(1)
	VMOVU	(VEC_SIZE * 2)(%rsi), %VEC(2)
	VMOVU	(VEC_SIZE * 3)(%rsi), %VEC(3)
	addq	$PREFETCHED_LOAD_SIZE, %rsi
	subq	$PREFETCHED_LOAD_SIZE, %rdx
	VMOVNT	%VEC(0), (%rdi)
	VMOVNT	%VEC(1), VEC_SIZE(%rdi)
	VMOVNT	%VEC(2), (VEC_SIZE * 2)(%rdi)
	VMOVNT	%VEC(3), (VEC_SIZE * 3)(%rdi)
	addq	$PREFETCHED_LOAD_SIZE, %rdi
	cmpq	$PREFETCHED_LOAD_SIZE, %rdx
	ja	L(loop_large_forward)
	sfence
	/* Store the last 4 * VEC.  */
	VMOVU	%VEC(5), (%rcx)
	VMOVU	%VEC(6), -VEC_SIZE(%rcx)
	VMOVU	%VEC(7), -(VEC_SIZE * 2)(%rcx)
	VMOVU	%VEC(8), -(VEC_SIZE * 3)(%rcx)
	/* Store the first VEC.  */
	VMOVU	%VEC(4), (%r11)
	VZEROUPPER
	ret

L(large_backward):
	/* Don't use non-temporal store if there is overlap between
	   destination and source since destination may be in cache
	   when source is loaded.  */
	leaq    (%rcx, %rdx), %r10
	cmpq    %r10, %r9
	jb	L(loop_4x_vec_backward)
L(loop_large_backward):
	/* Copy 4 * VEC a time backward with non-temporal stores.  */
	PREFETCH_ONE_SET (-1, (%rcx), -PREFETCHED_LOAD_SIZE * 2)
	PREFETCH_ONE_SET (-1, (%rcx), -PREFETCHED_LOAD_SIZE * 3)
	VMOVU	(%rcx), %VEC(0)
	VMOVU	-VEC_SIZE(%rcx), %VEC(1)
	VMOVU	-(VEC_SIZE * 2)(%rcx), %VEC(2)
	VMOVU	-(VEC_SIZE * 3)(%rcx), %VEC(3)
	subq	$PREFETCHED_LOAD_SIZE, %rcx
	subq	$PREFETCHED_LOAD_SIZE, %rdx
	VMOVNT	%VEC(0), (%r9)
	VMOVNT	%VEC(1), -VEC_SIZE(%r9)
	VMOVNT	%VEC(2), -(VEC_SIZE * 2)(%r9)
	VMOVNT	%VEC(3), -(VEC_SIZE * 3)(%r9)
	subq	$PREFETCHED_LOAD_SIZE, %r9
	cmpq	$PREFETCHED_LOAD_SIZE, %rdx
	ja	L(loop_large_backward)
	sfence
	/* Store the first 4 * VEC.  */
	VMOVU	%VEC(4), (%rdi)
	VMOVU	%VEC(5), VEC_SIZE(%rdi)
	VMOVU	%VEC(6), (VEC_SIZE * 2)(%rdi)
	VMOVU	%VEC(7), (VEC_SIZE * 3)(%rdi)
	/* Store the last VEC.  */
	VMOVU	%VEC(8), (%r11)
	VZEROUPPER
	ret
#endif
END (MEMMOVE_SYMBOL (__memmove, unaligned_erms))

#if IS_IN (libc)
# ifdef USE_MULTIARCH
strong_alias (MEMMOVE_SYMBOL (__memmove, unaligned_erms),
	      MEMMOVE_SYMBOL (__memcpy, unaligned_erms))
#  ifdef SHARED
strong_alias (MEMMOVE_SYMBOL (__memmove_chk, unaligned_erms),
	      MEMMOVE_SYMBOL (__memcpy_chk, unaligned_erms))
#  endif
# endif
# ifdef SHARED
strong_alias (MEMMOVE_CHK_SYMBOL (__memmove_chk, unaligned),
	      MEMMOVE_CHK_SYMBOL (__memcpy_chk, unaligned))
# endif
#endif
strong_alias (MEMMOVE_SYMBOL (__memmove, unaligned),
	      MEMCPY_SYMBOL (__memcpy, unaligned))