Andy Polyakov
d49135e7ea
sha/asm/sha256-586.pl: don't try to compile SIMD with no-sse2.
2014-02-26 10:22:13 +01:00
Andy Polyakov
147cca8f53
sha/asm/sha512-x86_64.pl: fix compilation error on Solaris.
2014-02-26 09:30:03 +01:00
Andy Polyakov
3847d15d6b
[aesni|sha*]-mb-x86_64.pl: add data prefetching.
2014-02-05 14:03:35 +01:00
Andy Polyakov
b217ca63b1
crypto/sha/asm/sha1-x86_64.pl update:
...
+5% on Atom Silvermont, up to +8% improvement of legacy code.
Harmonize sha1-586.pl and aesni-sha1-x86_86.p with sha1-x86_64.pl.
2014-02-01 21:07:16 +01:00
Andy Polyakov
5dc52b919b
PPC assembly pack: relax 64-bit requirement for little-endian support.
2014-01-07 22:44:21 +01:00
Andy Polyakov
ad0d2579cf
sha/asm/sha256-armv4.pl: add NEON code path.
...
(and shave off cycle even from integer-only code)
2014-01-04 18:04:53 +01:00
Andy Polyakov
25f7117f0e
aesni-sha1-x86_64.pl: refine Atom-specific optimization.
...
(and update performance data, and fix typo)
2014-01-04 17:13:57 +01:00
Andy Polyakov
2218c296b4
ARM assembly pack: make it work with older toolchain.
2013-12-28 12:17:08 +01:00
Andy Polyakov
fc0503a25c
sha1-x86_64.pl: harmonize Win64 SE handlers for SIMD code pathes.
...
(and ensure stack alignment in the process)
2013-12-18 22:12:08 +01:00
Andy Polyakov
cdd1acd788
sha512.c: fullfull implicit API contract in SHA512_Transform.
...
SHA512_Transform was initially added rather as tribute to tradition
than for practucal reasons. But use was recently found in ssl/s3_cbc.c
and it turned to be problematic on platforms that don't tolerate
misasligned references to memory and lack assembly subroutine.
2013-12-18 21:27:35 +01:00
Andy Polyakov
d1cf23ac86
Make Makefiles OSF-make-friendly.
...
PR: 3165
2013-11-12 21:51:37 +01:00
Andy Polyakov
fb65e65e28
sha/asm/sha512-ppc.pl: fix typo.
...
Submitted by: Marcelo Cerri
2013-10-31 20:21:54 +01:00
Andy Polyakov
8ff8a829b0
perlasm/ppc-xlate.pl: add .quad directive
...
sha/asm/sha512-ppc.pl: add little-endian support.
Submitted by: Marcelo Cerri
2013-10-31 11:08:51 +01:00
Andy Polyakov
3f9562a669
sha/asm/sha1-ppc.pl: add little-endian support.
...
Submitted by: Marcelo Cerri
2013-10-31 11:07:38 +01:00
Andy Polyakov
76c15d790e
PPC assembly pack: make new .size directives profiler-friendly.
...
Suggested by: Anton Blanchard
2013-10-15 23:40:12 +02:00
Andy Polyakov
d6019e1654
PPC assembly pack: add .size directives.
2013-10-15 00:14:39 +02:00
Andy Polyakov
039081b809
Initial aarch64 bits.
2013-10-13 19:15:15 +02:00
Andy Polyakov
0c2adb0a9b
MIPS assembly pack: get rid of deprecated instructions.
...
Latest MIPS ISA specification declared 'branch likely' instructions
obsolete. To makes code future-proof replace them with equivalent.
2013-10-13 13:14:52 +02:00
Andy Polyakov
61ba602af5
sha/asm/sha*-mb-x86_64.pl: commentary update.
2013-10-08 23:36:55 +02:00
Andy Polyakov
6bcb68da41
Configire: take multi-block modules into build loop.
2013-10-03 00:21:10 +02:00
Andy Polyakov
b783858654
x86_64 assembly pack: add multi-block AES-NI, SHA1 and SHA256.
2013-10-03 00:18:58 +02:00
Veres Lajos
478b50cf67
misspellings fixes by https://github.com/vlajos/misspell_fixer
2013-09-05 21:39:42 +01:00
Andy Polyakov
006784378d
crypto/sha/asm/sha*-x86_64.pl: comply with Win64 ABI.
2013-07-31 23:50:15 +02:00
Andy Polyakov
241fba4ea9
sha512-586.pl: fix typo.
...
Submitted by: Gisle Vanem
2013-07-10 09:59:25 +02:00
Andy Polyakov
02450ec69d
PA-RISC assembler pack: switch to bve in 64-bit builds.
...
PR: 3074
2013-06-18 10:37:00 +02:00
Andy Polyakov
cd8d7335af
sha1-x86_64.pl: add AVX2+BMI code path.
2013-06-10 22:30:34 +02:00
Andy Polyakov
c7f690c243
sha512-x86_64.pl: upcoming-Atom-specific optimization.
2013-06-10 22:29:01 +02:00
Andy Polyakov
32213d8d77
sha[256|512]-586.pl: add more SIMD code paths.
2013-06-10 22:26:53 +02:00
Andy Polyakov
504bbcf3cd
sha512-x86_64.pl: +16% optimization for Atom.
...
(and pending AVX2 changes).
2013-05-25 19:02:57 +02:00
Andy Polyakov
47edeb9f59
sha256-586.pl: code refresh.
2013-02-15 11:23:06 +01:00
Andy Polyakov
35c77b7303
sha1-586.pl: code refresh.
2013-02-14 22:20:17 +01:00
Andy Polyakov
7c9e81be40
[aesni-]sha1-x86_64.pl: code refresh.
2013-02-14 16:14:02 +01:00
Andy Polyakov
c4558efbf3
sha512-x86_64.pl: add AVX2 code path.
2013-02-14 15:39:42 +01:00
Andy Polyakov
46bf83f07a
x86_64 assembly pack: make Windows build more robust.
...
PR: 2963 and a number of others
2013-01-22 22:27:28 +01:00
Andy Polyakov
1598af9ac9
sha512-ppc.pl: minimize stack frame.
2013-01-22 21:09:14 +01:00
Andy Polyakov
d4571f43e8
sha512-ppc.pl: add PPC32 code, >2x improvement on in-order cores.
2013-01-19 17:22:05 +01:00
Ben Laurie
08e5536445
Fix some clang warnings.
2013-01-13 21:04:39 +00:00
Andy Polyakov
904732f68b
C64x+ assembly pack: improve EABI support.
2012-11-28 13:19:10 +00:00
Andy Polyakov
1efd583085
SPARCv9 assembly pack: harmonize ABI handling (so that it's handled in one
...
place at a time, by pre-processor in .S case and perl - in .s).
2012-10-25 12:07:32 +00:00
Andy Polyakov
aea4126e4e
[md5|sha1|sha512]-sparcv9.pl: "cooperative" optimizations based on
...
suggestions from David Miller.
2012-10-14 14:46:56 +00:00
Andy Polyakov
3ed6e22771
sha[1|512]-sparcv9.pl: add hardware SPARC T4 support.
...
Submitted by: David Miller
2012-09-28 09:35:39 +00:00
Andy Polyakov
5cc2159526
MIPS assembly pack: add support for SmartMIPS ASE.
2012-09-18 12:52:23 +00:00
Andy Polyakov
8df5518bd9
MIPS assembly pack: add MIPS[32|64]R2 code.
2012-09-15 11:18:20 +00:00
Andy Polyakov
17e820aec3
sha512-sparcv9.pl: fix binutils compilation error.
...
Submitted by: David Miller
2012-09-15 08:53:25 +00:00
Andy Polyakov
f26328c2f3
sha512-armv4.pl: optimize for Snapdragon S4.
2012-09-04 08:25:37 +00:00
Andy Polyakov
1a9d60d2e3
sha1-armv4-large.pl: comply with ABI.
2012-08-17 19:57:04 +00:00
Andy Polyakov
1a002d88ad
MIPS assembly pack: assign default value to $flavour.
2012-08-17 09:10:31 +00:00
Andy Polyakov
f6ff1aa8e0
sha512-x86_64.pl: revert previous change and solve the problem through
...
perlasm/x86_64-xlate.pl instead.
2012-08-13 12:34:36 +00:00
Andy Polyakov
3a5485a9f8
sha512-x86_64.pl: minimum gas requirement for AMD XOP.
2012-08-13 11:01:44 +00:00
Andy Polyakov
69f45c520c
sha1-[586|x86_64].pl: shave off one instruction from body_40_59, it's
...
2% less instructions in SIMD code paths, so 2% improvement in average:-)
2012-07-15 20:33:30 +00:00