about summary refs log tree commit diff
path: root/sysdeps/sparc/sparc64/multiarch/memcpy-niagara4.S
blob: 098ad2df1a7fd965ecc60b839b9783748f1690cd (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
/* Copy SIZE bytes from SRC to DEST.  For SUN4V Niagara-4.
   Copyright (C) 2012-2023 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
   <https://www.gnu.org/licenses/>.  */

#include <sysdep.h>

#define ASI_BLK_INIT_QUAD_LDD_P	0xe2

#define FPRS_FEF		0x04

/* On T4 it is very expensive to access ASRs like %fprs and
 * %asi, avoiding a read or a write can save ~50 cycles.
 */
#define FPU_ENTER			\
	rd	%fprs, %o5;		\
	andcc	%o5, FPRS_FEF, %g0;	\
	be,a,pn	%icc, 999f;		\
	 wr	%g0, FPRS_FEF, %fprs;	\
	999:

#define VISEntryHalf FPU_ENTER
#define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs

#define GLOBAL_SPARE	%g5

#define STORE_ASI	ASI_BLK_INIT_QUAD_LDD_P
#define EX_LD(x)	x
#define EX_ST(x)	x
#define EX_RETVAL(x)	x
#define LOAD(type,addr,dest)	type [addr], dest
#define STORE(type,src,addr)	type src, [addr]
#define STORE_INIT(src,addr)	stxa src, [addr] STORE_ASI

#if IS_IN (libc)

	.register	%g2,#scratch
	.register	%g3,#scratch
	.register	%g6,#scratch

	.text

ENTRY(__mempcpy_niagara4)
	ba,pt		%icc, 101f
	 add		%o0, %o2, %o3
END(__mempcpy_niagara4)

	.align		32
ENTRY(__memcpy_niagara4)
100:	/* %o0=dst, %o1=src, %o2=len */
	mov		%o0, %o3
101:
#ifndef __arch64__
	srl		%o2, 0, %o2
#endif
	brz,pn		%o2, .Lexit
	 cmp		%o2, 3
	ble,pn		%icc, .Ltiny
	 cmp		%o2, 19
	ble,pn		%icc, .Lsmall
	 or		%o0, %o1, %g2
	cmp		%o2, 128
	bl,pn		%icc, .Lmedium
	 nop

.Llarge:/* len >= 0x80 */
	/* First get dest 8 byte aligned.  */
	sub		%g0, %o0, %g1
	and		%g1, 0x7, %g1
	brz,pt		%g1, 51f
	 sub		%o2, %g1, %o2

1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
	add		%o1, 1, %o1
	subcc		%g1, 1, %g1
	add		%o0, 1, %o0
	bne,pt		%icc, 1b
	 EX_ST(STORE(stb, %g2, %o0 - 0x01))

51:	LOAD(prefetch, %o1 + 0x040, #n_reads_strong)
	LOAD(prefetch, %o1 + 0x080, #n_reads_strong)
	LOAD(prefetch, %o1 + 0x0c0, #n_reads_strong)
	LOAD(prefetch, %o1 + 0x100, #n_reads_strong)
	LOAD(prefetch, %o1 + 0x140, #n_reads_strong)
	LOAD(prefetch, %o1 + 0x180, #n_reads_strong)
	LOAD(prefetch, %o1 + 0x1c0, #n_reads_strong)
	LOAD(prefetch, %o1 + 0x200, #n_reads_strong)

	/* Check if we can use the straight fully aligned
	 * loop, or we require the alignaddr/faligndata variant.
	 */
	andcc		%o1, 0x7, %o5
	bne,pn		%icc, .Llarge_src_unaligned
	 sub		%g0, %o0, %g1

	/* Legitimize the use of initializing stores by getting dest
	 * to be 64-byte aligned.
	 */
	and		%g1, 0x3f, %g1
	brz,pt		%g1, .Llarge_aligned
	 sub		%o2, %g1, %o2

1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g2))
	add		%o1, 8, %o1
	subcc		%g1, 8, %g1
	add		%o0, 8, %o0
	bne,pt		%icc, 1b
	 EX_ST(STORE(stx, %g2, %o0 - 0x08))

.Llarge_aligned:
	/* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */
	andn		%o2, 0x3f, %o4
	sub		%o2, %o4, %o2

1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
	add		%o1, 0x40, %o1
	EX_LD(LOAD(ldx, %o1 - 0x38, %g2))
	subcc		%o4, 0x40, %o4
	EX_LD(LOAD(ldx, %o1 - 0x30, %g3))
	EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE))
	EX_LD(LOAD(ldx, %o1 - 0x20, %o5))
	EX_ST(STORE_INIT(%g1, %o0))
	add		%o0, 0x08, %o0
	EX_ST(STORE_INIT(%g2, %o0))
	add		%o0, 0x08, %o0
	EX_LD(LOAD(ldx, %o1 - 0x18, %g2))
	EX_ST(STORE_INIT(%g3, %o0))
	add		%o0, 0x08, %o0
	EX_LD(LOAD(ldx, %o1 - 0x10, %g3))
	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
	add		%o0, 0x08, %o0
	EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE))
	EX_ST(STORE_INIT(%o5, %o0))
	add		%o0, 0x08, %o0
	EX_ST(STORE_INIT(%g2, %o0))
	add		%o0, 0x08, %o0
	EX_ST(STORE_INIT(%g3, %o0))
	add		%o0, 0x08, %o0
	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
	add		%o0, 0x08, %o0
	bne,pt		%icc, 1b
	 LOAD(prefetch, %o1 + 0x200, #n_reads_strong)

	membar		#StoreLoad | #StoreStore

	brz,pn		%o2, .Lexit
	 cmp		%o2, 19
	ble,pn		%icc, .Lsmall_unaligned
	 nop
	ba,a,pt		%icc, .Lmedium_noprefetch

.Lexit:	retl
	 mov		EX_RETVAL(%o3), %o0

.Llarge_src_unaligned:
	andn		%o2, 0x3f, %o4
	sub		%o2, %o4, %o2
	VISEntryHalf
	alignaddr	%o1, %g0, %g1
	add		%o1, %o4, %o1
	EX_LD(LOAD(ldd, %g1 + 0x00, %f0))
1:	EX_LD(LOAD(ldd, %g1 + 0x08, %f2))
	subcc		%o4, 0x40, %o4
	EX_LD(LOAD(ldd, %g1 + 0x10, %f4))
	EX_LD(LOAD(ldd, %g1 + 0x18, %f6))
	EX_LD(LOAD(ldd, %g1 + 0x20, %f8))
	EX_LD(LOAD(ldd, %g1 + 0x28, %f10))
	EX_LD(LOAD(ldd, %g1 + 0x30, %f12))
	EX_LD(LOAD(ldd, %g1 + 0x38, %f14))
	faligndata	%f0, %f2, %f16
	EX_LD(LOAD(ldd, %g1 + 0x40, %f0))
	faligndata	%f2, %f4, %f18
	add		%g1, 0x40, %g1
	faligndata	%f4, %f6, %f20
	faligndata	%f6, %f8, %f22
	faligndata	%f8, %f10, %f24
	faligndata	%f10, %f12, %f26
	faligndata	%f12, %f14, %f28
	faligndata	%f14, %f0, %f30
	EX_ST(STORE(std, %f16, %o0 + 0x00))
	EX_ST(STORE(std, %f18, %o0 + 0x08))
	EX_ST(STORE(std, %f20, %o0 + 0x10))
	EX_ST(STORE(std, %f22, %o0 + 0x18))
	EX_ST(STORE(std, %f24, %o0 + 0x20))
	EX_ST(STORE(std, %f26, %o0 + 0x28))
	EX_ST(STORE(std, %f28, %o0 + 0x30))
	EX_ST(STORE(std, %f30, %o0 + 0x38))
	add		%o0, 0x40, %o0
	bne,pt		%icc, 1b
	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
	VISExitHalf

	brz,pn		%o2, .Lexit
	 cmp		%o2, 19
	ble,pn		%icc, .Lsmall_unaligned
	 nop
	ba,a,pt		%icc, .Lmedium_unaligned

.Lmedium:
	LOAD(prefetch, %o1 + 0x40, #n_reads_strong)
	andcc		%g2, 0x7, %g0
	bne,pn		%icc, .Lmedium_unaligned
	 nop
.Lmedium_noprefetch:
	andncc		%o2, 0x20 - 1, %o5
	be,pn		%icc, 2f
	 sub		%o2, %o5, %o2
1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
	EX_LD(LOAD(ldx, %o1 + 0x08, %g2))
	EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE))
	EX_LD(LOAD(ldx, %o1 + 0x18, %o4))
	add		%o1, 0x20, %o1
	subcc		%o5, 0x20, %o5
	EX_ST(STORE(stx, %g1, %o0 + 0x00))
	EX_ST(STORE(stx, %g2, %o0 + 0x08))
	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10))
	EX_ST(STORE(stx, %o4, %o0 + 0x18))
	bne,pt		%icc, 1b
	 add		%o0, 0x20, %o0
2:	andcc		%o2, 0x18, %o5
	be,pt		%icc, 3f
	 sub		%o2, %o5, %o2
1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
	add		%o1, 0x08, %o1
	add		%o0, 0x08, %o0
	subcc		%o5, 0x08, %o5
	bne,pt		%icc, 1b
	 EX_ST(STORE(stx, %g1, %o0 - 0x08))
3:	brz,pt		%o2, .Lexit
	 cmp		%o2, 0x04
	bl,pn		%icc, .Ltiny
	 nop
	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
	add		%o1, 0x04, %o1
	add		%o0, 0x04, %o0
	subcc		%o2, 0x04, %o2
	bne,pn		%icc, .Ltiny
	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
	ba,a,pt		%icc, .Lexit
.Lmedium_unaligned:
	/* First get dest 8 byte aligned.  */
	sub		%g0, %o0, %g1
	and		%g1, 0x7, %g1
	brz,pt		%g1, 2f
	 sub		%o2, %g1, %o2

1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
	add		%o1, 1, %o1
	subcc		%g1, 1, %g1
	add		%o0, 1, %o0
	bne,pt		%icc, 1b
	 EX_ST(STORE(stb, %g2, %o0 - 0x01))
2:
	and		%o1, 0x7, %g1
	brz,pn		%g1, .Lmedium_noprefetch
	 sll		%g1, 3, %g1
	mov		64, %g2
	sub		%g2, %g1, %g2
	andn		%o1, 0x7, %o1
	EX_LD(LOAD(ldx, %o1 + 0x00, %o4))
	sllx		%o4, %g1, %o4
	andn		%o2, 0x08 - 1, %o5
	sub		%o2, %o5, %o2
1:	EX_LD(LOAD(ldx, %o1 + 0x08, %g3))
	add		%o1, 0x08, %o1
	subcc		%o5, 0x08, %o5
	srlx		%g3, %g2, GLOBAL_SPARE
	or		GLOBAL_SPARE, %o4, GLOBAL_SPARE
	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00))
	add		%o0, 0x08, %o0
	bne,pt		%icc, 1b
	 sllx		%g3, %g1, %o4
	srl		%g1, 3, %g1
	add		%o1, %g1, %o1
	brz,pn		%o2, .Lexit
	 nop
	ba,pt		%icc, .Lsmall_unaligned

.Ltiny:
	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
	subcc		%o2, 1, %o2
	be,pn		%icc, .Lexit
	 EX_ST(STORE(stb, %g1, %o0 + 0x00))
	EX_LD(LOAD(ldub, %o1 + 0x01, %g1))
	subcc		%o2, 1, %o2
	be,pn		%icc, .Lexit
	 EX_ST(STORE(stb, %g1, %o0 + 0x01))
	EX_LD(LOAD(ldub, %o1 + 0x02, %g1))
	ba,pt		%icc, .Lexit
	 EX_ST(STORE(stb, %g1, %o0 + 0x02))

.Lsmall:
	andcc		%g2, 0x3, %g0
	bne,pn		%icc, .Lsmall_unaligned
	 andn		%o2, 0x4 - 1, %o5
	sub		%o2, %o5, %o2
1:
	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
	add		%o1, 0x04, %o1
	subcc		%o5, 0x04, %o5
	add		%o0, 0x04, %o0
	bne,pt		%icc, 1b
	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
	brz,pt		%o2, .Lexit
	 nop
	ba,a,pt		%icc, .Ltiny

.Lsmall_unaligned:
1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
	add		%o1, 1, %o1
	add		%o0, 1, %o0
	subcc		%o2, 1, %o2
	bne,pt		%icc, 1b
	 EX_ST(STORE(stb, %g1, %o0 - 0x01))
	ba,a,pt		%icc, .Lexit
END(__memcpy_niagara4)

#endif