aboutsummaryrefslogtreecommitdiff
path: root/crypto/rc4
AgeCommit message (Collapse)AuthorFilesLines
2011-05-25rc4-586.pl: optimize unused code path.Andy Polyakov1-22/+37
2011-05-24rc4-586.pl: 50% improvement on Core2 and 80% on Westmere.Andy Polyakov1-8/+129
2011-02-16Include openssl/crypto.h first in several other files so FIPS renamingDr. Stephen Henson1-0/+1
is picked up.
2011-01-26Change AR to ARX to allow exclusion of fips object modulesDr. Stephen Henson1-1/+1
2010-11-29s390x assembler pack: adapt for -m31 build, see commentary in ConfigureAndy Polyakov1-5/+30
for more details.
2010-07-26rc4-s390x.pl: harmonize build rule with other similar rules.Andy Polyakov2-3/+7
2010-05-13rc4-x86_64.pl: "Westmere" optimization.Andy Polyakov1-0/+5
2010-05-05Revert previous Linux-specific/centric commit#19629. If it really has toAndy Polyakov1-1/+0
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).
2010-05-05Non-executable stack in asm.Ben Laurie1-0/+1
2009-12-27Throw in more PA-RISC assembler.Andy Polyakov2-0/+316
2009-04-26Handle push/pop %rbx in epi/prologue (this is Win64 SEH thing).Andy Polyakov1-8/+9
2009-02-12rc4-s390x.pl: allow for older assembler and optimize character loop.Andy Polyakov1-19/+19
2009-02-11RC4 for s390x.Andy Polyakov2-0/+208
2008-12-29Fix "possible loss of data" Win64 compiler warnings.Andy Polyakov1-2/+2
2008-12-19x86_64 assembler pack: add support for Win64 SEH.Andy Polyakov1-12/+152
2008-11-12Update make rules for x86_64 assembler pack.Andy Polyakov1-1/+2
2008-11-12x86_64 assembler pack to comply with updated styling x86_64-xlate.pl rules.Andy Polyakov1-2/+1
2008-10-31size_t-fy AES, Camellia and RC4.Andy Polyakov2-7/+9
2008-04-17Apply mingw patches as supplied by Roumen Petrov an Alon Bar-LevLutz Jänicke1-2/+1
PR: 1552 Submitted by: Roumen Petrov <openssl@roumenpetrov.info>, "Alon Bar-Lev" <alon.barlev@gmail.com>
2008-01-12rc4-x86_64 portability fix.Andy Polyakov1-1/+1
2008-01-11Unify x86 perlasm make rules.Andy Polyakov1-11/+2
2007-12-18Engage x86 assembler in Mac OS X build.Andy Polyakov1-0/+2
2007-12-02Some assembler are allergic to lea reg,BYTE PTR[...].Andy Polyakov1-1/+1
Submitted by: Guenter Knauf
2007-06-18Update .cvsignoreDr. Stephen Henson1-0/+1
2007-04-26Reimplement rc4-586.pl, relicense rc4-x86_64.pl.Andy Polyakov2-202/+154
2007-04-02RC4_set_key for x86_64 and Core2 optimization.Andy Polyakov1-0/+115
PR: 1447
2007-04-01Reserve for assembler implementation of RC4_set_key and implement x86 one.Andy Polyakov2-10/+105
2007-03-20Two extra instructions in RC4 character loop give 80% performanceAndy Polyakov1-0/+2
improvement on Core2. I still need to detect Core2 and choose this path...
2007-01-21Constify version strings and some structures.Dr. Stephen Henson1-1/+1
2006-02-04Update filenames in makefiles.Dr. Stephen Henson1-1/+1
2005-07-26Fix signed/unsigned warnings.Geoff Thorpe1-2/+2
2005-07-20Pedantic polish to rc4-ia64.pl.Andy Polyakov1-2/+2
2005-07-18Retire original rc4-ia64.S.Andy Polyakov1-159/+0
2005-07-18Switch to new RC4 IA-64 module.Andy Polyakov1-3/+6
2005-07-18This update implements following improvements.Andy Polyakov1-87/+54
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.
2005-07-18Unrolled RC4 IA-64 loop gives 40% improvement over current assemblerAndy Polyakov1-0/+788
implementation [as predicted]. Submitted by: David Mosberger Obtained from: http://www.hpl.hp.com/research/linux/crypto/
2005-07-18Fix unwind directives in IA-64 assembler modules. This helps symbolicAndy Polyakov1-3/+2
debugging and doesn't affect functionality. Submitted by: David Mosberger Obtained from: http://www.hpl.hp.com/research/linux/crypto/
2005-06-26Omit padding in RC4_KEY on IA-64. The idea behind padding was to reserveAndy Polyakov5-44/+39
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
2005-05-16Further BUILDENV refinement, further fool-proofing of Makefiles andAndy Polyakov1-4/+17
[most importantly] put back dependencies accidentaly eliminated in check-in #13342.
2005-05-16make updateBodo Möller1-16/+2
2005-05-15+20% performance improvement of P4-specific RC4_CHAR loop.Andy Polyakov1-5/+6
2005-05-15Fool-proofing MakefilesAndy Polyakov1-5/+1
2005-05-04Commentary update motivating code update in 0.9.7.Andy Polyakov1-4/+4
2005-05-03Commentary update.Andy Polyakov1-2/+4
2005-05-03Rename amd64 modules to x86_64 and update RC4 implementation.Andy Polyakov3-161/+239
2005-04-26Add DTLS support.Ben Laurie1-0/+1
2005-04-17Throw in x86_64 AT&T to MASM assembler converter to facilitate developmentAndy Polyakov1-114/+47
of dual-ABI Unix/Win64 modules.
2005-04-11Add emacs cache files to .cvsignore.Richard Levitte2-0/+4
2005-04-06+45% RC4 performance boost on Intel EM64T core. Unrolled loop providingAndy Polyakov1-4/+4
further +35% will follow... Submitted by: Zou Nanhai
2005-04-04Extend Solaris x86 support to amd64.Andy Polyakov1-1/+1