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
|
/*
* Poly1305 authenticator algorithm, RFC7539, x64 SSE2 functions
*
* Copyright (C) 2015 Martin Willi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#include <linux/linkage.h>
.data
.align 16
ANMASK: .octa 0x0000000003ffffff0000000003ffffff
.text
#define h0 0x00(%rdi)
#define h1 0x04(%rdi)
#define h2 0x08(%rdi)
#define h3 0x0c(%rdi)
#define h4 0x10(%rdi)
#define r0 0x00(%rdx)
#define r1 0x04(%rdx)
#define r2 0x08(%rdx)
#define r3 0x0c(%rdx)
#define r4 0x10(%rdx)
#define s1 0x00(%rsp)
#define s2 0x04(%rsp)
#define s3 0x08(%rsp)
#define s4 0x0c(%rsp)
#define m %rsi
#define h01 %xmm0
#define h23 %xmm1
#define h44 %xmm2
#define t1 %xmm3
#define t2 %xmm4
#define t3 %xmm5
#define t4 %xmm6
#define mask %xmm7
#define d0 %r8
#define d1 %r9
#define d2 %r10
#define d3 %r11
#define d4 %r12
ENTRY(poly1305_block_sse2)
# %rdi: Accumulator h[5]
# %rsi: 16 byte input block m
# %rdx: Poly1305 key r[5]
# %rcx: Block count
# This single block variant tries to improve performance by doing two
# multiplications in parallel using SSE instructions. There is quite
# some quardword packing involved, hence the speedup is marginal.
push %rbx
push %r12
sub $0x10,%rsp
# s1..s4 = r1..r4 * 5
mov r1,%eax
lea (%eax,%eax,4),%eax
mov %eax,s1
mov r2,%eax
lea (%eax,%eax,4),%eax
mov %eax,s2
mov r3,%eax
lea (%eax,%eax,4),%eax
mov %eax,s3
mov r4,%eax
lea (%eax,%eax,4),%eax
mov %eax,s4
movdqa ANMASK(%rip),mask
.Ldoblock:
# h01 = [0, h1, 0, h0]
# h23 = [0, h3, 0, h2]
# h44 = [0, h4, 0, h4]
movd h0,h01
movd h1,t1
movd h2,h23
movd h3,t2
movd h4,h44
punpcklqdq t1,h01
punpcklqdq t2,h23
punpcklqdq h44,h44
# h01 += [ (m[3-6] >> 2) & 0x3ffffff, m[0-3] & 0x3ffffff ]
movd 0x00(m),t1
movd 0x03(m),t2
psrld $2,t2
punpcklqdq t2,t1
pand mask,t1
paddd t1,h01
# h23 += [ (m[9-12] >> 6) & 0x3ffffff, (m[6-9] >> 4) & 0x3ffffff ]
movd 0x06(m),t1
movd 0x09(m),t2
psrld $4,t1
psrld $6,t2
punpcklqdq t2,t1
pand mask,t1
paddd t1,h23
# h44 += [ (m[12-15] >> 8) | (1 << 24), (m[12-15] >> 8) | (1 << 24) ]
mov 0x0c(m),%eax
shr $8,%eax
or $0x01000000,%eax
movd %eax,t1
pshufd $0xc4,t1,t1
paddd t1,h44
# t1[0] = h0 * r0 + h2 * s3
# t1[1] = h1 * s4 + h3 * s2
movd r0,t1
movd s4,t2
punpcklqdq t2,t1
pmuludq h01,t1
movd s3,t2
movd s2,t3
punpcklqdq t3,t2
pmuludq h23,t2
paddq t2,t1
# t2[0] = h0 * r1 + h2 * s4
# t2[1] = h1 * r0 + h3 * s3
movd r1,t2
movd r0,t3
punpcklqdq t3,t2
pmuludq h01,t2
movd s4,t3
movd s3,t4
punpcklqdq t4,t3
pmuludq h23,t3
paddq t3,t2
# t3[0] = h4 * s1
# t3[1] = h4 * s2
movd s1,t3
movd s2,t4
punpcklqdq t4,t3
pmuludq h44,t3
# d0 = t1[0] + t1[1] + t3[0]
# d1 = t2[0] + t2[1] + t3[1]
movdqa t1,t4
punpcklqdq t2,t4
punpckhqdq t2,t1
paddq t4,t1
paddq t3,t1
movq t1,d0
psrldq $8,t1
movq t1,d1
# t1[0] = h0 * r2 + h2 * r0
# t1[1] = h1 * r1 + h3 * s4
movd r2,t1
movd r1,t2
punpcklqdq t2,t1
pmuludq h01,t1
movd r0,t2
movd s4,t3
punpcklqdq t3,t2
pmuludq h23,t2
paddq t2,t1
# t2[0] = h0 * r3 + h2 * r1
# t2[1] = h1 * r2 + h3 * r0
movd r3,t2
movd r2,t3
punpcklqdq t3,t2
pmuludq h01,t2
movd r1,t3
movd r0,t4
punpcklqdq t4,t3
pmuludq h23,t3
paddq t3,t2
# t3[0] = h4 * s3
# t3[1] = h4 * s4
movd s3,t3
movd s4,t4
punpcklqdq t4,t3
pmuludq h44,t3
# d2 = t1[0] + t1[1] + t3[0]
# d3 = t2[0] + t2[1] + t3[1]
movdqa t1,t4
punpcklqdq t2,t4
punpckhqdq t2,t1
paddq t4,t1
paddq t3,t1
movq t1,d2
psrldq $8,t1
movq t1,d3
# t1[0] = h0 * r4 + h2 * r2
# t1[1] = h1 * r3 + h3 * r1
movd r4,t1
movd r3,t2
punpcklqdq t2,t1
pmuludq h01,t1
movd r2,t2
movd r1,t3
punpcklqdq t3,t2
pmuludq h23,t2
paddq t2,t1
# t3[0] = h4 * r0
movd r0,t3
pmuludq h44,t3
# d4 = t1[0] + t1[1] + t3[0]
movdqa t1,t4
psrldq $8,t4
paddq t4,t1
paddq t3,t1
movq t1,d4
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
add %rax,d1
# h0 = d0 & 0x3ffffff
mov d0,%rbx
and $0x3ffffff,%ebx
# d2 += d1 >> 26
mov d1,%rax
shr $26,%rax
add %rax,d2
# h1 = d1 & 0x3ffffff
mov d1,%rax
and $0x3ffffff,%eax
mov %eax,h1
# d3 += d2 >> 26
mov d2,%rax
shr $26,%rax
add %rax,d3
# h2 = d2 & 0x3ffffff
mov d2,%rax
and $0x3ffffff,%eax
mov %eax,h2
# d4 += d3 >> 26
mov d3,%rax
shr $26,%rax
add %rax,d4
# h3 = d3 & 0x3ffffff
mov d3,%rax
and $0x3ffffff,%eax
mov %eax,h3
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
lea (%eax,%eax,4),%eax
add %eax,%ebx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
mov %ebx,%eax
shr $26,%eax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
mov %ebx,h0
add $0x10,m
dec %rcx
jnz .Ldoblock
add $0x10,%rsp
pop %r12
pop %rbx
ret
ENDPROC(poly1305_block_sse2)
|
