about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/strchr-evex.S
blob: f62cd9d1445d994e5b27fbb486f840a57c536f83 (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
/* strchr/strchrnul optimized with 256-bit EVEX instructions.
   Copyright (C) 2021-2022 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/>.  */

#if IS_IN (libc)

# include <sysdep.h>

# ifndef STRCHR
#  define STRCHR	__strchr_evex
# endif

# define VMOVU		vmovdqu64
# define VMOVA		vmovdqa64

# ifdef USE_AS_WCSCHR
#  define VPBROADCAST	vpbroadcastd
#  define VPCMP		vpcmpd
#  define VPMINU	vpminud
#  define CHAR_REG	esi
#  define SHIFT_REG	ecx
#  define CHAR_SIZE	4
# else
#  define VPBROADCAST	vpbroadcastb
#  define VPCMP		vpcmpb
#  define VPMINU	vpminub
#  define CHAR_REG	sil
#  define SHIFT_REG	edx
#  define CHAR_SIZE	1
# endif

# define XMMZERO	xmm16

# define YMMZERO	ymm16
# define YMM0		ymm17
# define YMM1		ymm18
# define YMM2		ymm19
# define YMM3		ymm20
# define YMM4		ymm21
# define YMM5		ymm22
# define YMM6		ymm23
# define YMM7		ymm24
# define YMM8		ymm25

# define VEC_SIZE 32
# define PAGE_SIZE 4096
# define CHAR_PER_VEC (VEC_SIZE / CHAR_SIZE)

	.section .text.evex,"ax",@progbits
ENTRY (STRCHR)
	/* Broadcast CHAR to YMM0.	*/
	VPBROADCAST	%esi, %YMM0
	movl	%edi, %eax
	andl	$(PAGE_SIZE - 1), %eax
	vpxorq	%XMMZERO, %XMMZERO, %XMMZERO

	/* Check if we cross page boundary with one vector load.
	   Otherwise it is safe to use an unaligned load.  */
	cmpl	$(PAGE_SIZE - VEC_SIZE), %eax
	ja	L(cross_page_boundary)

	/* Check the first VEC_SIZE bytes. Search for both CHAR and the
	   null bytes.  */
	VMOVU	(%rdi), %YMM1

	/* Leaves only CHARS matching esi as 0.  */
	vpxorq	%YMM1, %YMM0, %YMM2
	VPMINU	%YMM2, %YMM1, %YMM2
	/* Each bit in K0 represents a CHAR or a null byte in YMM1.  */
	VPCMP	$0, %YMMZERO, %YMM2, %k0
	kmovd	%k0, %eax
	testl	%eax, %eax
	jz	L(aligned_more)
	tzcntl	%eax, %eax
# ifdef USE_AS_WCSCHR
	/* NB: Multiply wchar_t count by 4 to get the number of bytes.
	 */
	leaq	(%rdi, %rax, CHAR_SIZE), %rax
# else
	addq	%rdi, %rax
# endif
# ifndef USE_AS_STRCHRNUL
	/* Found CHAR or the null byte.	 */
	cmp	(%rax), %CHAR_REG
	jne	L(zero)
# endif
	ret

	/* .p2align 5 helps keep performance more consistent if ENTRY()
	   alignment % 32 was either 16 or 0. As well this makes the
	   alignment % 32 of the loop_4x_vec fixed which makes tuning it
	   easier.  */
	.p2align 5
L(first_vec_x3):
	tzcntl	%eax, %eax
# ifndef USE_AS_STRCHRNUL
	/* Found CHAR or the null byte.	 */
	cmp	(VEC_SIZE * 3)(%rdi, %rax, CHAR_SIZE), %CHAR_REG
	jne	L(zero)
# endif
	/* NB: Multiply sizeof char type (1 or 4) to get the number of
	   bytes.  */
	leaq	(VEC_SIZE * 3)(%rdi, %rax, CHAR_SIZE), %rax
	ret

# ifndef USE_AS_STRCHRNUL
L(zero):
	xorl	%eax, %eax
	ret
# endif

	.p2align 4
L(first_vec_x4):
# ifndef USE_AS_STRCHRNUL
	/* Check to see if first match was CHAR (k0) or null (k1).  */
	kmovd	%k0, %eax
	tzcntl	%eax, %eax
	kmovd	%k1, %ecx
	/* bzhil will not be 0 if first match was null.  */
	bzhil	%eax, %ecx, %ecx
	jne	L(zero)
# else
	/* Combine CHAR and null matches.  */
	kord	%k0, %k1, %k0
	kmovd	%k0, %eax
	tzcntl	%eax, %eax
# endif
	/* NB: Multiply sizeof char type (1 or 4) to get the number of
	   bytes.  */
	leaq	(VEC_SIZE * 4)(%rdi, %rax, CHAR_SIZE), %rax
	ret

	.p2align 4
L(first_vec_x1):
	tzcntl	%eax, %eax
# ifndef USE_AS_STRCHRNUL
	/* Found CHAR or the null byte.	 */
	cmp	(VEC_SIZE)(%rdi, %rax, CHAR_SIZE), %CHAR_REG
	jne	L(zero)

# endif
	/* NB: Multiply sizeof char type (1 or 4) to get the number of
	   bytes.  */
	leaq	(VEC_SIZE)(%rdi, %rax, CHAR_SIZE), %rax
	ret

	.p2align 4
L(first_vec_x2):
# ifndef USE_AS_STRCHRNUL
	/* Check to see if first match was CHAR (k0) or null (k1).  */
	kmovd	%k0, %eax
	tzcntl	%eax, %eax
	kmovd	%k1, %ecx
	/* bzhil will not be 0 if first match was null.  */
	bzhil	%eax, %ecx, %ecx
	jne	L(zero)
# else
	/* Combine CHAR and null matches.  */
	kord	%k0, %k1, %k0
	kmovd	%k0, %eax
	tzcntl	%eax, %eax
# endif
	/* NB: Multiply sizeof char type (1 or 4) to get the number of
	   bytes.  */
	leaq	(VEC_SIZE * 2)(%rdi, %rax, CHAR_SIZE), %rax
	ret

	.p2align 4
L(aligned_more):
	/* Align data to VEC_SIZE.  */
	andq	$-VEC_SIZE, %rdi
L(cross_page_continue):
	/* Check the next 4 * VEC_SIZE. Only one VEC_SIZE at a time since
	   data is only aligned to VEC_SIZE. Use two alternating methods
	   for checking VEC to balance latency and port contention.  */

	/* This method has higher latency but has better port
	   distribution.  */
	VMOVA	(VEC_SIZE)(%rdi), %YMM1
	/* Leaves only CHARS matching esi as 0.  */
	vpxorq	%YMM1, %YMM0, %YMM2
	VPMINU	%YMM2, %YMM1, %YMM2
	/* Each bit in K0 represents a CHAR or a null byte in YMM1.  */
	VPCMP	$0, %YMMZERO, %YMM2, %k0
	kmovd	%k0, %eax
	testl	%eax, %eax
	jnz	L(first_vec_x1)

	/* This method has higher latency but has better port
	   distribution.  */
	VMOVA	(VEC_SIZE * 2)(%rdi), %YMM1
	/* Each bit in K0 represents a CHAR in YMM1.  */
	VPCMP	$0, %YMM1, %YMM0, %k0
	/* Each bit in K1 represents a CHAR in YMM1.  */
	VPCMP	$0, %YMM1, %YMMZERO, %k1
	kortestd	%k0, %k1
	jnz	L(first_vec_x2)

	VMOVA	(VEC_SIZE * 3)(%rdi), %YMM1
	/* Leaves only CHARS matching esi as 0.  */
	vpxorq	%YMM1, %YMM0, %YMM2
	VPMINU	%YMM2, %YMM1, %YMM2
	/* Each bit in K0 represents a CHAR or a null byte in YMM1.  */
	VPCMP	$0, %YMMZERO, %YMM2, %k0
	kmovd	%k0, %eax
	testl	%eax, %eax
	jnz	L(first_vec_x3)

	VMOVA	(VEC_SIZE * 4)(%rdi), %YMM1
	/* Each bit in K0 represents a CHAR in YMM1.  */
	VPCMP	$0, %YMM1, %YMM0, %k0
	/* Each bit in K1 represents a CHAR in YMM1.  */
	VPCMP	$0, %YMM1, %YMMZERO, %k1
	kortestd	%k0, %k1
	jnz	L(first_vec_x4)

	/* Align data to VEC_SIZE * 4 for the loop.  */
	addq	$VEC_SIZE, %rdi
	andq	$-(VEC_SIZE * 4), %rdi

	.p2align 4
L(loop_4x_vec):
	/* Check 4x VEC at a time. No penalty to imm32 offset with evex
	   encoding.  */
	VMOVA	(VEC_SIZE * 4)(%rdi), %YMM1
	VMOVA	(VEC_SIZE * 5)(%rdi), %YMM2
	VMOVA	(VEC_SIZE * 6)(%rdi), %YMM3
	VMOVA	(VEC_SIZE * 7)(%rdi), %YMM4

	/* For YMM1 and YMM3 use xor to set the CHARs matching esi to
	   zero.  */
	vpxorq	%YMM1, %YMM0, %YMM5
	/* For YMM2 and YMM4 cmp not equals to CHAR and store result in
	   k register. Its possible to save either 1 or 2 instructions
	   using cmp no equals method for either YMM1 or YMM1 and YMM3
	   respectively but bottleneck on p5 makes it not worth it.  */
	VPCMP	$4, %YMM0, %YMM2, %k2
	vpxorq	%YMM3, %YMM0, %YMM7
	VPCMP	$4, %YMM0, %YMM4, %k4

	/* Use min to select all zeros from either xor or end of string).
	 */
	VPMINU	%YMM1, %YMM5, %YMM1
	VPMINU	%YMM3, %YMM7, %YMM3

	/* Use min + zeromask to select for zeros. Since k2 and k4 will
	   have 0 as positions that matched with CHAR which will set
	   zero in the corresponding destination bytes in YMM2 / YMM4.
	 */
	VPMINU	%YMM1, %YMM2, %YMM2{%k2}{z}
	VPMINU	%YMM3, %YMM4, %YMM4
	VPMINU	%YMM2, %YMM4, %YMM4{%k4}{z}

	VPCMP	$0, %YMMZERO, %YMM4, %k1
	kmovd	%k1, %ecx
	subq	$-(VEC_SIZE * 4), %rdi
	testl	%ecx, %ecx
	jz	L(loop_4x_vec)

	VPCMP	$0, %YMMZERO, %YMM1, %k0
	kmovd	%k0, %eax
	testl	%eax, %eax
	jnz	L(last_vec_x1)

	VPCMP	$0, %YMMZERO, %YMM2, %k0
	kmovd	%k0, %eax
	testl	%eax, %eax
	jnz	L(last_vec_x2)

	VPCMP	$0, %YMMZERO, %YMM3, %k0
	kmovd	%k0, %eax
	/* Combine YMM3 matches (eax) with YMM4 matches (ecx).  */
# ifdef USE_AS_WCSCHR
	sall	$8, %ecx
	orl	%ecx, %eax
	tzcntl	%eax, %eax
# else
	salq	$32, %rcx
	orq	%rcx, %rax
	tzcntq	%rax, %rax
# endif
# ifndef USE_AS_STRCHRNUL
	/* Check if match was CHAR or null.  */
	cmp	(VEC_SIZE * 2)(%rdi, %rax, CHAR_SIZE), %CHAR_REG
	jne	L(zero_end)
# endif
	/* NB: Multiply sizeof char type (1 or 4) to get the number of
	   bytes.  */
	leaq	(VEC_SIZE * 2)(%rdi, %rax, CHAR_SIZE), %rax
	ret

# ifndef USE_AS_STRCHRNUL
L(zero_end):
	xorl	%eax, %eax
	ret
# endif

	.p2align 4
L(last_vec_x1):
	tzcntl	%eax, %eax
# ifndef USE_AS_STRCHRNUL
	/* Check if match was null.  */
	cmp	(%rdi, %rax, CHAR_SIZE), %CHAR_REG
	jne	L(zero_end)
# endif
	/* NB: Multiply sizeof char type (1 or 4) to get the number of
	   bytes.  */
	leaq	(%rdi, %rax, CHAR_SIZE), %rax
	ret

	.p2align 4
L(last_vec_x2):
	tzcntl	%eax, %eax
# ifndef USE_AS_STRCHRNUL
	/* Check if match was null.  */
	cmp	(VEC_SIZE)(%rdi, %rax, CHAR_SIZE), %CHAR_REG
	jne	L(zero_end)
# endif
	/* NB: Multiply sizeof char type (1 or 4) to get the number of
	   bytes.  */
	leaq	(VEC_SIZE)(%rdi, %rax, CHAR_SIZE), %rax
	ret

	/* Cold case for crossing page with first load.	 */
	.p2align 4
L(cross_page_boundary):
	movq	%rdi, %rdx
	/* Align rdi.  */
	andq	$-VEC_SIZE, %rdi
	VMOVA	(%rdi), %YMM1
	/* Leaves only CHARS matching esi as 0.  */
	vpxorq	%YMM1, %YMM0, %YMM2
	VPMINU	%YMM2, %YMM1, %YMM2
	/* Each bit in K0 represents a CHAR or a null byte in YMM1.  */
	VPCMP	$0, %YMMZERO, %YMM2, %k0
	kmovd	%k0, %eax
	/* Remove the leading bits.	 */
# ifdef USE_AS_WCSCHR
	movl	%edx, %SHIFT_REG
	/* NB: Divide shift count by 4 since each bit in K1 represent 4
	   bytes.  */
	sarl	$2, %SHIFT_REG
	andl	$(CHAR_PER_VEC - 1), %SHIFT_REG
# endif
	sarxl	%SHIFT_REG, %eax, %eax
	/* If eax is zero continue.  */
	testl	%eax, %eax
	jz	L(cross_page_continue)
	tzcntl	%eax, %eax
# ifndef USE_AS_STRCHRNUL
	/* Check to see if match was CHAR or null.  */
	cmp	(%rdx, %rax, CHAR_SIZE), %CHAR_REG
	jne	L(zero_end)
# endif
# ifdef USE_AS_WCSCHR
	/* NB: Multiply wchar_t count by 4 to get the number of
	   bytes.  */
	leaq	(%rdx, %rax, CHAR_SIZE), %rax
# else
	addq	%rdx, %rax
# endif
	ret

END (STRCHR)
# endif