wbrawner/openssl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
11101 commits 20 branches 302 tags 153 MiB
Commit graph

57 commits

Author SHA1 Message Date
Andy Polyakov
6251989eb6 x86_64 assembly pack: make it possible to compile with Perl located on 
path with spaces.

PR: 2835
 2012-06-27 10:08:23 +00:00
Andy Polyakov
d2e1803197 x86[_64] assembly pack: update benchmark results. 2012-06-12 14:18:21 +00:00
Andy Polyakov
c608171d9c Add RC4-MD5 and AESNI-SHA1 "stitched" implementations. 2011-08-23 20:51:38 +00:00
Andy Polyakov
a908b711ac rc4-586.pl: add Atom performance results. 2011-06-28 12:36:10 +00:00
Andy Polyakov
0772f3b4f6 rc4-x86_64.pl: commentary update. 2011-06-27 09:46:16 +00:00
Andy Polyakov
fe9a5107be Various mingw64 fixes. 2011-05-29 13:51:14 +00:00
Andy Polyakov
f44cb15fab rc4-x86_64.pl: fix due credit. 2011-05-27 18:58:37 +00:00
Andy Polyakov
986289604e rc4-x86_64.pl: RC4_options fix-up. 2011-05-27 16:15:12 +00:00
Andy Polyakov
4bb90087d7 x86[_64]cpuid.pl: harmonize usage of reserved bits #20 and #30. 2011-05-27 15:32:43 +00:00
Andy Polyakov
0ca9a483af rc4-x86_64.pl: major optimization for contemporary Intel CPUs. 2011-05-27 09:51:09 +00:00
Andy Polyakov
0dff8ba248 rc4-586.pl: optimize even further... 2011-05-27 09:46:19 +00:00
Andy Polyakov
6a99984b57 rc4-586.pl: optimize unused code path. 2011-05-25 09:36:13 +00:00
Andy Polyakov
760d2551fb rc4-586.pl: 50% improvement on Core2 and 80% on Westmere. 2011-05-24 13:07:29 +00:00
Andy Polyakov
e822c756b6 s390x assembler pack: adapt for -m31 build, see commentary in Configure 
for more details.
 2010-11-29 20:52:43 +00:00
Andy Polyakov
6219d2c294 rc4-s390x.pl: harmonize build rule with other similar rules. 2010-07-26 21:56:16 +00:00
Andy Polyakov
629fd3aa91 rc4-x86_64.pl: "Westmere" optimization. 2010-05-13 21:01:24 +00:00
Andy Polyakov
3efe51a407 Revert previous Linux-specific/centric commit#19629. If it really has to 
be done, it's definitely not the way to do it. So far answer to the
question was to ./config -Wa,--noexecstack (adopted by RedHat).
 2010-05-05 22:05:39 +00:00
Ben Laurie
0e3ef596e5 Non-executable stack in asm. 2010-05-05 15:50:13 +00:00
Andy Polyakov
cb3b9b1323 Throw in more PA-RISC assembler. 2009-12-27 20:49:40 +00:00
Andy Polyakov
75d448dde4 Handle push/pop %rbx in epi/prologue (this is Win64 SEH thing). 2009-04-26 17:58:01 +00:00
Andy Polyakov
c558c99fd8 rc4-s390x.pl: allow for older assembler and optimize character loop. 2009-02-12 14:48:49 +00:00
Andy Polyakov
13c3a1defa RC4 for s390x. 2009-02-11 10:01:36 +00:00
Andy Polyakov
be01f79d3d x86_64 assembler pack: add support for Win64 SEH. 2008-12-19 11:17:29 +00:00
Andy Polyakov
aa8f38e49b x86_64 assembler pack to comply with updated styling x86_64-xlate.pl rules. 2008-11-12 08:15:52 +00:00
Andy Polyakov
a078befcbe rc4-x86_64 portability fix. 2008-01-12 11:29:45 +00:00
Andy Polyakov
544b82e493 Some assembler are allergic to lea reg,BYTE PTR[...]. 
Submitted by: Guenter Knauf
 2007-12-02 21:32:03 +00:00
Andy Polyakov
20c04a13e6 Reimplement rc4-586.pl, relicense rc4-x86_64.pl. 2007-04-26 20:48:38 +00:00
Andy Polyakov
9babf3929b RC4_set_key for x86_64 and Core2 optimization. 
PR: 1447
 2007-04-02 09:50:14 +00:00
Andy Polyakov
2875462425 Reserve for assembler implementation of RC4_set_key and implement x86 one. 2007-04-01 17:01:12 +00:00
Andy Polyakov
de50494505 Two extra instructions in RC4 character loop give 80% performance 
improvement on Core2. I still need to detect Core2 and choose this
path...
 2007-03-20 09:13:07 +00:00
Andy Polyakov
2802ec65c2 Pedantic polish to rc4-ia64.pl. 2005-07-20 11:47:47 +00:00
Andy Polyakov
26c07054a1 Retire original rc4-ia64.S. 2005-07-18 18:59:21 +00:00
Andy Polyakov
4ac210c16a This update implements following improvements. 
1. Original submission required minor modification to RC4_set_key, which
   we don't want to tolerate and therefore we fix assembler instead.
2. Eliminate remaining byte-order dependence [look for RC4_BIG_ENDIAN].
3. Eliminate logical error [when key->x is referred prior key is verified].
4. HP-UX assembler puked on MODSCHED_RC4 macro with "syntax error,"
   macro has to be splitted in two.
5. Deploy parallel compare in function prologue.
6. Eliminate redundant instuctions and nops.
7. Eliminate assembler warnings.
 2005-07-18 17:11:13 +00:00
Andy Polyakov
02703c74a4 Unrolled RC4 IA-64 loop gives 40% improvement over current assembler 
implementation [as predicted].

Submitted by: David Mosberger

Obtained from: http://www.hpl.hp.com/research/linux/crypto/
 2005-07-18 16:55:52 +00:00
Andy Polyakov
ef428d5681 Fix unwind directives in IA-64 assembler modules. This helps symbolic 
debugging and doesn't affect functionality.

Submitted by: David Mosberger

Obtained from: http://www.hpl.hp.com/research/linux/crypto/
 2005-07-18 09:54:14 +00:00
Andy Polyakov
a4022932ee Omit padding in RC4_KEY on IA-64. The idea behind padding was to reserve 
room for aligning of the key schedule itself [specific alignment is
required for future performance improvements], but OpenSSH "abuses"
our API by making copies and restoring RC4_KEY, thus ruining the
alignment and making it impossible to recover the key schedule.
PR: 1114
 2005-06-26 16:09:29 +00:00
Andy Polyakov
804515425a +20% performance improvement of P4-specific RC4_CHAR loop. 2005-05-15 22:43:00 +00:00
Andy Polyakov
0ee883650d Commentary update motivating code update in 0.9.7. 2005-05-04 14:51:38 +00:00
Andy Polyakov
647907918d Commentary update. 2005-05-03 21:16:42 +00:00
Andy Polyakov
5f1841cdca Rename amd64 modules to x86_64 and update RC4 implementation. 2005-05-03 15:42:05 +00:00
Andy Polyakov
1cfd258ed6 Throw in x86_64 AT&T to MASM assembler converter to facilitate development 
of dual-ABI Unix/Win64 modules.
 2005-04-17 21:05:57 +00:00
Richard Levitte
4bb61becbb Add emacs cache files to .cvsignore. 2005-04-11 14:17:07 +00:00
Andy Polyakov
81ee80ab88 +45% RC4 performance boost on Intel EM64T core. Unrolled loop providing 
further +35% will follow...

Submitted by: Zou Nanhai
 2005-04-06 09:45:42 +00:00
Andy Polyakov
f774accdbf Fix rc4-ia64.S to pass more exhaustive regression tests. 2004-12-02 10:07:55 +00:00
Andy Polyakov
7c69478064 I've introduced a bug to i386 RC4 assembler, which would emerge with 
certain mix of calls to RC4 routine not covered by rc4test.c.
It's fixed now. In addition this patch inadvertently fixes minor
performance problem: in 0.9.7 context P4 was performing 12% slower
than the original implementation...
 2004-12-01 15:28:18 +00:00
Andy Polyakov
b7b46c9a87 Add 0.9.7 specific comments to RC4 assembler modules. 2004-11-30 15:46:46 +00:00
Andy Polyakov
7a3240e319 Final touches to rc4/asm/rc4-596.pl, +52% better performance on AMD core. 2004-11-29 21:12:58 +00:00
Andy Polyakov
d675c74d14 RC4 IA-64 assembler implementation. 2004-11-26 15:07:50 +00:00
Andy Polyakov
376729e130 RC4 tune-up for Intel P4 core, both 32- and 64-bit ones. As it's 
apparently impossible to compose blended code with would perform
satisfactory on all x86 and x86_64 cores, an extra RC4_CHAR
code-path is introduced and P4 core is detected at run-time. This
way we keep original performance on non-P4 implementations and
turbo-charge P4 performance by factor of 2.8x (on 32-bit core).
 2004-11-21 10:36:25 +00:00
Andy Polyakov
68d9e764cb As was shown by Marc Bevand reordering of couple of load operations 
results in even higher performance gain of 3.3x:-) At least on
Opteron...
 2004-11-09 17:23:26 +00:00