x86_64-gf2m.S@ 87083

Last change on this file since 87083 was 83531, checked in by vboxsync, 5 years ago
setting svn:sync-process=export for openssl-1.1.1f, all files except tests
File size: 6.5 KB

Line
1	default rel
2	%define XMMWORD
3	%define YMMWORD
4	%define ZMMWORD
5	section .text code align=64
6
7
8
9	ALIGN 16
10	_mul_1x1:
11
12	sub rsp,128+8
13
14	mov r9,-1
15	lea rsi,[rax*1+rax]
16	shr r9,3
17	lea rdi,[rax*4]
18	and r9,rax
19	lea r12,[rax*8]
20	sar rax,63
21	lea r10,[r9*1+r9]
22	sar rsi,63
23	lea r11,[r9*4]
24	and rax,rbp
25	sar rdi,63
26	mov rdx,rax
27	shl rax,63
28	and rsi,rbp
29	shr rdx,1
30	mov rcx,rsi
31	shl rsi,62
32	and rdi,rbp
33	shr rcx,2
34	xor rax,rsi
35	mov rbx,rdi
36	shl rdi,61
37	xor rdx,rcx
38	shr rbx,3
39	xor rax,rdi
40	xor rdx,rbx
41
42	mov r13,r9
43	mov QWORD[rsp],0
44	xor r13,r10
45	mov QWORD[8+rsp],r9
46	mov r14,r11
47	mov QWORD[16+rsp],r10
48	xor r14,r12
49	mov QWORD[24+rsp],r13
50
51	xor r9,r11
52	mov QWORD[32+rsp],r11
53	xor r10,r11
54	mov QWORD[40+rsp],r9
55	xor r13,r11
56	mov QWORD[48+rsp],r10
57	xor r9,r14
58	mov QWORD[56+rsp],r13
59	xor r10,r14
60
61	mov QWORD[64+rsp],r12
62	xor r13,r14
63	mov QWORD[72+rsp],r9
64	xor r9,r11
65	mov QWORD[80+rsp],r10
66	xor r10,r11
67	mov QWORD[88+rsp],r13
68
69	xor r13,r11
70	mov QWORD[96+rsp],r14
71	mov rsi,r8
72	mov QWORD[104+rsp],r9
73	and rsi,rbp
74	mov QWORD[112+rsp],r10
75	shr rbp,4
76	mov QWORD[120+rsp],r13
77	mov rdi,r8
78	and rdi,rbp
79	shr rbp,4
80
81	movq xmm0,QWORD[rsi*8+rsp]
82	mov rsi,r8
83	and rsi,rbp
84	shr rbp,4
85	mov rcx,QWORD[rdi*8+rsp]
86	mov rdi,r8
87	mov rbx,rcx
88	shl rcx,4
89	and rdi,rbp
90	movq xmm1,QWORD[rsi*8+rsp]
91	shr rbx,60
92	xor rax,rcx
93	pslldq xmm1,1
94	mov rsi,r8
95	shr rbp,4
96	xor rdx,rbx
97	and rsi,rbp
98	shr rbp,4
99	pxor xmm0,xmm1
100	mov rcx,QWORD[rdi*8+rsp]
101	mov rdi,r8
102	mov rbx,rcx
103	shl rcx,12
104	and rdi,rbp
105	movq xmm1,QWORD[rsi*8+rsp]
106	shr rbx,52
107	xor rax,rcx
108	pslldq xmm1,2
109	mov rsi,r8
110	shr rbp,4
111	xor rdx,rbx
112	and rsi,rbp
113	shr rbp,4
114	pxor xmm0,xmm1
115	mov rcx,QWORD[rdi*8+rsp]
116	mov rdi,r8
117	mov rbx,rcx
118	shl rcx,20
119	and rdi,rbp
120	movq xmm1,QWORD[rsi*8+rsp]
121	shr rbx,44
122	xor rax,rcx
123	pslldq xmm1,3
124	mov rsi,r8
125	shr rbp,4
126	xor rdx,rbx
127	and rsi,rbp
128	shr rbp,4
129	pxor xmm0,xmm1
130	mov rcx,QWORD[rdi*8+rsp]
131	mov rdi,r8
132	mov rbx,rcx
133	shl rcx,28
134	and rdi,rbp
135	movq xmm1,QWORD[rsi*8+rsp]
136	shr rbx,36
137	xor rax,rcx
138	pslldq xmm1,4
139	mov rsi,r8
140	shr rbp,4
141	xor rdx,rbx
142	and rsi,rbp
143	shr rbp,4
144	pxor xmm0,xmm1
145	mov rcx,QWORD[rdi*8+rsp]
146	mov rdi,r8
147	mov rbx,rcx
148	shl rcx,36
149	and rdi,rbp
150	movq xmm1,QWORD[rsi*8+rsp]
151	shr rbx,28
152	xor rax,rcx
153	pslldq xmm1,5
154	mov rsi,r8
155	shr rbp,4
156	xor rdx,rbx
157	and rsi,rbp
158	shr rbp,4
159	pxor xmm0,xmm1
160	mov rcx,QWORD[rdi*8+rsp]
161	mov rdi,r8
162	mov rbx,rcx
163	shl rcx,44
164	and rdi,rbp
165	movq xmm1,QWORD[rsi*8+rsp]
166	shr rbx,20
167	xor rax,rcx
168	pslldq xmm1,6
169	mov rsi,r8
170	shr rbp,4
171	xor rdx,rbx
172	and rsi,rbp
173	shr rbp,4
174	pxor xmm0,xmm1
175	mov rcx,QWORD[rdi*8+rsp]
176	mov rdi,r8
177	mov rbx,rcx
178	shl rcx,52
179	and rdi,rbp
180	movq xmm1,QWORD[rsi*8+rsp]
181	shr rbx,12
182	xor rax,rcx
183	pslldq xmm1,7
184	mov rsi,r8
185	shr rbp,4
186	xor rdx,rbx
187	and rsi,rbp
188	shr rbp,4
189	pxor xmm0,xmm1
190	mov rcx,QWORD[rdi*8+rsp]
191	mov rbx,rcx
192	shl rcx,60
193	DB 102,72,15,126,198
194	shr rbx,4
195	xor rax,rcx
196	psrldq xmm0,8
197	xor rdx,rbx
198	DB 102,72,15,126,199
199	xor rax,rsi
200	xor rdx,rdi
201
202	add rsp,128+8
203
204	DB 0F3h,0C3h ;repret
205	$L$end_mul_1x1:
206
207
208	EXTERN OPENSSL_ia32cap_P
209	global bn_GF2m_mul_2x2
210
211	ALIGN 16
212	bn_GF2m_mul_2x2:
213
214	mov rax,rsp
215	mov r10,QWORD[OPENSSL_ia32cap_P]
216	bt r10,33
217	jnc NEAR $L$vanilla_mul_2x2
218
219	DB 102,72,15,110,194
220	DB 102,73,15,110,201
221	DB 102,73,15,110,208
222	movq xmm3,QWORD[40+rsp]
223	movdqa xmm4,xmm0
224	movdqa xmm5,xmm1
225	DB 102,15,58,68,193,0
226	pxor xmm4,xmm2
227	pxor xmm5,xmm3
228	DB 102,15,58,68,211,0
229	DB 102,15,58,68,229,0
230	xorps xmm4,xmm0
231	xorps xmm4,xmm2
232	movdqa xmm5,xmm4
233	pslldq xmm4,8
234	psrldq xmm5,8
235	pxor xmm2,xmm4
236	pxor xmm0,xmm5
237	movdqu XMMWORD[rcx],xmm2
238	movdqu XMMWORD[16+rcx],xmm0
239	DB 0F3h,0C3h ;repret
240
241	ALIGN 16
242	$L$vanilla_mul_2x2:
243	lea rsp,[((-136))+rsp]
244
245	mov r10,QWORD[176+rsp]
246	mov QWORD[120+rsp],rdi
247	mov QWORD[128+rsp],rsi
248	mov QWORD[80+rsp],r14
249
250	mov QWORD[88+rsp],r13
251
252	mov QWORD[96+rsp],r12
253
254	mov QWORD[104+rsp],rbp
255
256	mov QWORD[112+rsp],rbx
257
258	$L$body_mul_2x2:
259	mov QWORD[32+rsp],rcx
260	mov QWORD[40+rsp],rdx
261	mov QWORD[48+rsp],r8
262	mov QWORD[56+rsp],r9
263	mov QWORD[64+rsp],r10
264
265	mov r8,0xf
266	mov rax,rdx
267	mov rbp,r9
268	call _mul_1x1
269	mov QWORD[16+rsp],rax
270	mov QWORD[24+rsp],rdx
271
272	mov rax,QWORD[48+rsp]
273	mov rbp,QWORD[64+rsp]
274	call _mul_1x1
275	mov QWORD[rsp],rax
276	mov QWORD[8+rsp],rdx
277
278	mov rax,QWORD[40+rsp]
279	mov rbp,QWORD[56+rsp]
280	xor rax,QWORD[48+rsp]
281	xor rbp,QWORD[64+rsp]
282	call _mul_1x1
283	mov rbx,QWORD[rsp]
284	mov rcx,QWORD[8+rsp]
285	mov rdi,QWORD[16+rsp]
286	mov rsi,QWORD[24+rsp]
287	mov rbp,QWORD[32+rsp]
288
289	xor rax,rdx
290	xor rdx,rcx
291	xor rax,rbx
292	mov QWORD[rbp],rbx
293	xor rdx,rdi
294	mov QWORD[24+rbp],rsi
295	xor rax,rsi
296	xor rdx,rsi
297	xor rax,rdx
298	mov QWORD[16+rbp],rdx
299	mov QWORD[8+rbp],rax
300
301	mov r14,QWORD[80+rsp]
302
303	mov r13,QWORD[88+rsp]
304
305	mov r12,QWORD[96+rsp]
306
307	mov rbp,QWORD[104+rsp]
308
309	mov rbx,QWORD[112+rsp]
310
311	mov rdi,QWORD[120+rsp]
312	mov rsi,QWORD[128+rsp]
313	lea rsp,[136+rsp]
314
315	$L$epilogue_mul_2x2:
316	DB 0F3h,0C3h ;repret
317	$L$end_mul_2x2:
318
319
320	DB 71,70,40,50,94,109,41,32,77,117,108,116,105,112,108,105
321	DB 99,97,116,105,111,110,32,102,111,114,32,120,56,54,95,54
322	DB 52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121
323	DB 32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46
324	DB 111,114,103,62,0
325	ALIGN 16
326	EXTERN __imp_RtlVirtualUnwind
327
328
329	ALIGN 16
330	se_handler:
331	push rsi
332	push rdi
333	push rbx
334	push rbp
335	push r12
336	push r13
337	push r14
338	push r15
339	pushfq
340	sub rsp,64
341
342	mov rax,QWORD[120+r8]
343	mov rbx,QWORD[248+r8]
344
345	lea r10,[$L$body_mul_2x2]
346	cmp rbx,r10
347	jb NEAR $L$in_prologue
348
349	mov rax,QWORD[152+r8]
350
351	lea r10,[$L$epilogue_mul_2x2]
352	cmp rbx,r10
353	jae NEAR $L$in_prologue
354
355	mov r14,QWORD[80+rax]
356	mov r13,QWORD[88+rax]
357	mov r12,QWORD[96+rax]
358	mov rbp,QWORD[104+rax]
359	mov rbx,QWORD[112+rax]
360	mov rdi,QWORD[120+rax]
361	mov rsi,QWORD[128+rax]
362
363	mov QWORD[144+r8],rbx
364	mov QWORD[160+r8],rbp
365	mov QWORD[168+r8],rsi
366	mov QWORD[176+r8],rdi
367	mov QWORD[216+r8],r12
368	mov QWORD[224+r8],r13
369	mov QWORD[232+r8],r14
370
371	lea rax,[136+rax]
372
373	$L$in_prologue:
374	mov QWORD[152+r8],rax
375
376	mov rdi,QWORD[40+r9]
377	mov rsi,r8
378	mov ecx,154
379	DD 0xa548f3fc
380
381	mov rsi,r9
382	xor rcx,rcx
383	mov rdx,QWORD[8+rsi]
384	mov r8,QWORD[rsi]
385	mov r9,QWORD[16+rsi]
386	mov r10,QWORD[40+rsi]
387	lea r11,[56+rsi]
388	lea r12,[24+rsi]
389	mov QWORD[32+rsp],r10
390	mov QWORD[40+rsp],r11
391	mov QWORD[48+rsp],r12
392	mov QWORD[56+rsp],rcx
393	call QWORD[__imp_RtlVirtualUnwind]
394
395	mov eax,1
396	add rsp,64
397	popfq
398	pop r15
399	pop r14
400	pop r13
401	pop r12
402	pop rbp
403	pop rbx
404	pop rdi
405	pop rsi
406	DB 0F3h,0C3h ;repret
407
408
409	section .pdata rdata align=4
410	ALIGN 4
411	DD _mul_1x1 wrt ..imagebase
412	DD $L$end_mul_1x1 wrt ..imagebase
413	DD $L$SEH_info_1x1 wrt ..imagebase
414
415	DD $L$vanilla_mul_2x2 wrt ..imagebase
416	DD $L$end_mul_2x2 wrt ..imagebase
417	DD $L$SEH_info_2x2 wrt ..imagebase
418	section .xdata rdata align=8
419	ALIGN 8
420	$L$SEH_info_1x1:
421	DB 0x01,0x07,0x02,0x00
422	DB 0x07,0x01,0x11,0x00
423	$L$SEH_info_2x2:
424	DB 9,0,0,0
425	DD se_handler wrt ..imagebase

Note: See TracBrowser for help on using the repository browser.

Download in other formats:

Original Format