Age | Commit message (Collapse) | Author | |
---|---|---|---|
2017-03-13 | crypto/x86*cpuid.pl: move extended feature detection. | Andy Polyakov | |
Exteneded feature flags were not pulled on AMD processors, as result a number of extensions were effectively masked on Ryzen. Original fix for x86_64cpuid.pl addressed this problem, but messed up processor vendor detection. This fix moves extended feature detection past basic feature detection where it belongs. 32-bit counterpart is harmonized too. Reviewed-by: Rich Salz <rsalz@openssl.org> Reviewed-by: Richard Levitte <levitte@openssl.org> (cherry picked from commit 1aed5e1ac28790cc915ad03e86e2d5e896a4ea13) | |||
2014-02-14 | x86[_64]cpuid.pl: add low-level RDSEED. | Andy Polyakov | |
(cherry picked from commit f4d456408d9d7bca31f34765d1a05fbd9fa55826) | |||
2013-09-15 | Extend OPENSSL_ia32cap_P (backport from HEAD). | Andy Polyakov | |
2013-09-09 | Revert "x86cpuid.pl: fix extended feature flags detection." | Andy Polyakov | |
This reverts commit 514f1a783515e9beb73b759a483c078813cf8ba0. | |||
2013-06-10 | x86cpuid.pl: fix extended feature flags detection. | Andy Polyakov | |
(cherry picked from commit 1bc0b68d7b8c7620487310ed84fa273ba0d9f428) | |||
2013-03-18 | x86cpuid.pl: make it work with older CPUs. | Andy Polyakov | |
PR: 3005 (cherry picked from commit 5702e965d759dde8a098d8108660721ba2b93a7d) | |||
2012-08-29 | x86cpuid.pl: hide symbols [backport from x86_64, from HEAD]. | Andy Polyakov | |
2012-06-03 | Reduce version skew: trivia (I hope). | Ben Laurie | |
2012-02-28 | x86cpuid.pl: fix processor capability detection on pre-586 [from HEAD]. | Andy Polyakov | |
2011-11-08 | x86cpuid.pl: compensate for imaginary virtual machines [from HEAD]. | Andy Polyakov | |
PR: 2633 | |||
2011-11-05 | x86cpuid.pl: don't punish "last-year" OSes on "this-year" CPUs. | Andy Polyakov | |
PR: 2633 | |||
2011-08-10 | Add provisory support for RDRAND [from HEAD]. | Andy Polyakov | |
2011-06-28 | x86[_64]cpuid.pl: harmonize OPENSSL_ia32_cpuid [from HEAD]. | Andy Polyakov | |
2010-02-12 | Make assembly language versions of OPENSSL_cleanse() accept zero length | Dr. Stephen Henson | |
parameter. Backport from HEAD, orginal by appro. | |||
2009-05-14 | x86[_64]cpuid.pl: update from HEAD. | Andy Polyakov | |
2008-01-05 | Update perl asm scripts include paths for perlasm. | Dr. Stephen Henson | |
2007-07-21 | x86*cpuid update. | Andy Polyakov | |
2007-05-19 | x86cpuid fixes. | Andy Polyakov | |
PR: 1526 | |||
2007-05-14 | Profiling revealed that OPENSSL_cleanse consumes *more* CPU time than | Andy Polyakov | |
sha1_block_data_order when hashing short messages. Move OPENSSL_cleanse to "cpuid" assembler module and gain 2x. | |||
2007-04-01 | Update x86cpuid.pl to correctly detect shared cache and to support new | Andy Polyakov | |
RC4_set_key. | |||
2005-12-06 | Support for indirect calls in x86 assembler modules. | Andy Polyakov | |
2005-12-03 | x86cpuid.pl update. | Andy Polyakov | |
2005-06-24 | Replace emms with finit in x86cpuid. | Andy Polyakov | |
2005-05-18 | Don't emit SSE2 instructions unless were asked to. | Andy Polyakov | |
PR: 1073 | |||
2005-05-03 | Cpuid modules updates. | Andy Polyakov | |
2004-09-09 | x86 assembler updates: more instructions, new OPENSSL_instrument_halt | Andy Polyakov | |
[for DJGPP]... | |||
2004-08-29 | OPENSSL_ia32cap final touches. Note that OPENSSL_ia32cap is no longer a | Andy Polyakov | |
symbol, but a macro expanded as (*(OPENSSL_ia32cap_loc())). The latter is the only one to be exported to application. | |||
2004-07-26 | Add framework for yet another assembler module dubbed "cpuid." Idea | Andy Polyakov | |
is to have a placeholder to small routines, which can be written only in assembler. In IA-32 case this includes processor capability identification and access to Time-Stamp Counter. As discussed earlier OPENSSL_ia32cap is introduced to control recently added SSE2 code pathes (see docs/crypto/OPENSSL_ia32cap.pod). For the moment the code is operational on ELF platforms only. I haven't checked it yet, but I have all reasons to believe that Windows build should fail to link too. I'll be looking into it shortly... |