Commit graph

263 commits

Author SHA1 Message Date
FdaSilvaYY
0d4fb84390 GH601: Various spelling fixes.
Signed-off-by: Rich Salz <rsalz@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
2016-02-05 15:25:50 -05:00
Andy Polyakov
b974943234 x86_64 assembly pack: tune clang version detection even further.
RT#4171

Reviewed-by: Kurt Roeckx <kurt@openssl.org>
2015-12-13 22:18:18 +01:00
Andy Polyakov
bd30091c97 x86[_64] assembly pack: add optimized AES-NI OCB subroutines.
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-12-10 13:11:26 +01:00
Andy Polyakov
a285992763 ARMv4 assembly pack: allow Thumb2 even in iOS build,
and engage it in most modules.

Reviewed-by: Tim Hudson <tjh@openssl.org>
2015-12-07 12:06:06 +01:00
Andy Polyakov
76eba0d94b x86_64 assembly pack: tune clang version detection.
RT#4142

Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-11-23 16:00:06 +01:00
Andy Polyakov
ce24d2ed23 aes/asm/vpaes-ppc.pl: eliminate overhung stores in misaligned cases.
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-11-18 11:56:21 +01:00
Andy Polyakov
a5fd24d19b aesni-sha256-x86_64.pl: fix crash on AMD Jaguar.
It was also found that stich performs suboptimally on AMD Jaguar, hence
execution is limited to XOP-capable and Intel processors.

Reviewed-by: Kurt Roeckx <kurt@openssl.org>
2015-11-16 13:06:10 +01:00
Alessandro Ghedini
d900a015b5 Fix typos
Reviewed-by: Rich Salz <rsalz@openssl.org>
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-10-23 19:52:08 +02:00
Andy Polyakov
b7f5503fa6 Skylake performance results.
Reviewed-by: Matt Caswell <matt@openssl.org>
2015-09-26 19:50:11 +02:00
Andy Polyakov
11208dcfb9 ARMv4 assembly pack: implement support for Thumb2.
As some of ARM processors, more specifically Cortex-Mx series, are
Thumb2-only, we need to support Thumb2-only builds even in assembly.

Reviewed-by: Tim Hudson <tjh@openssl.org>
2015-09-25 13:34:02 +02:00
Richard Levitte
053fa39af6 Conversion to UTF-8 where needed
This leaves behind files with names ending with '.iso-8859-1'.  These
should be safe to remove.  If something went wrong when re-encoding,
there will be some files with names ending with '.utf8' left behind.

Reviewed-by: Rich Salz <rsalz@openssl.org>
2015-07-14 01:10:01 +02:00
Andy Polyakov
c4cd831606 aes/asm/bsaes-armv7.pl: fix compilation with Xcode 6.3.
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-05-13 17:11:00 +02:00
Andy Polyakov
82c4a07939 aes/asm/aesni-sha256-x86_64.pl: fix Windows compilation failure with old assembler.
Reviewed-by: Matt Caswell <matt@openssl.org>
2015-05-13 16:58:37 +02:00
Andy Polyakov
7be6bc68c6 aes/asm/aesni-x86.pl: fix typo affecting Windows build.
Reviewed-by: Matt Caswell <matt@openssl.org>
2015-04-20 18:39:56 +02:00
Andy Polyakov
23f6eec71d aes/asm/aesni-x86[_64].pl update.
This addresses

- request for improvement for faster key setup in RT#3576;
- clearing registers and stack in RT#3554 (this is more of a gesture to
see if there will be some traction from compiler side);
- more commentary around input parameters handling and stack layout
(desired when RT#3553 was reviewed);
- minor size and single block performance optimization (was lying around);

Reviewed-by: Matt Caswell <matt@openssl.org>
2015-04-20 15:43:05 +02:00
Andy Polyakov
313e6ec11f Add assembly support for 32-bit iOS.
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-04-20 15:06:22 +02:00
Andy Polyakov
35141544e2 aes/asm/vpaes-armv8.pl: make it compile on iOS.
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-04-20 14:30:50 +02:00
Andy Polyakov
94376cccb4 aes/asm/aesv8-armx.pl: optimize for Cortex-A5x.
ARM has optimized Cortex-A5x pipeline to favour pairs of complementary
AES instructions. While modified code improves performance of post-r0p0
Cortex-A53 performance by >40% (for CBC decrypt and CTR), it hurts
original r0p0. We favour later revisions, because one can't prevent
future from coming. Improvement on post-r0p0 Cortex-A57 exceeds 50%,
while new code is not slower on r0p0, or Apple A7 for that matter.

[Update even SHA results for latest Cortex-A53.]

Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-04-02 09:47:56 +02:00
Andy Polyakov
2779c08436 Add vpaes-amrv8.pl module.
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-03-28 15:41:50 +01:00
Andy Polyakov
e620e5ae37 aes/asm/bsaes-armv7: fix kernel-side XTS and harmonize with Linux.
XTS bug spotted and fix suggested by Adrian Kotelba.

Reviewed-by: Tim Hudson <tjh@openssl.org>
2015-02-24 10:08:57 +01:00
Andy Polyakov
9b05cbc33e Add assembly support to ios64-cross.
Fix typos in ios64-cross config line.

Reviewed-by: Tim Hudson <tjh@openssl.org>
2015-01-23 15:38:41 +01:00
Andy Polyakov
c462a6817b Fix macosx-ppc build (and typos in unwind info).
Reviewed-by: Tim Hudson <tjh@openssl.org>
2015-01-22 12:13:57 +01:00
Andy Polyakov
e464403d0b Fix irix-cc build.
Reviewed-by: Matt Caswell <matt@openssl.org>
2015-01-07 18:39:39 +01:00
Andy Polyakov
c1669e1c20 Remove inconsistency in ARM support.
This facilitates "universal" builds, ones that target multiple
architectures, e.g. ARMv5 through ARMv7. See commentary in
Configure for details.

Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
2015-01-04 23:45:08 +01:00
Andy Polyakov
69d5747f90 aesni-x86_64.pl: make ECB subroutine Windows ABI compliant.
RT: 3553
Reviewed-by: Emilia Kasper <emilia@openssl.org>
2014-10-15 11:10:08 +02:00
Andy Polyakov
b59f92e75d x86[_64] assembly pack: add Silvermont performance data.
Reviewed-by: Rich Salz <rsalz@openssl.org>
2014-08-30 19:13:49 +02:00
Andy Polyakov
1b0fe79f3e x86_64 assembly pack: improve masm support. 2014-07-09 20:08:01 +02:00
Andy Polyakov
a356e488ad x86_64 assembly pack: refine clang detection. 2014-06-28 17:23:21 +02:00
Andy Polyakov
052ecf91d2 aesp8-ppc.pl: rigid input verification in key setup. 2014-06-25 22:13:17 +02:00
Andy Polyakov
7b8c8c4d79 aesv8-armx.pl: rigid input verification in key setup. 2014-06-25 22:10:45 +02:00
Andy Polyakov
7eb0488280 x86_64 assembly pack: addendum to last clang commit. 2014-06-24 08:37:05 +02:00
Andy Polyakov
ac171925ab x86_64 assembly pack: allow clang to compile AVX code. 2014-06-24 08:24:25 +02:00
Andy Polyakov
015364baf3 aesv8-armx.pl: inclrease interleave factor.
This is to compensate for higher aes* instruction latency on Cortex-A57.
2014-06-24 08:08:58 +02:00
Andy Polyakov
9024b84b7c aesni-sha[1|256]-x86_64.pl: fix logical error and MacOS X build. 2014-06-16 10:11:45 +02:00
Andy Polyakov
764fe518da aesp8-ppc.pl: add CTR mode. 2014-06-16 08:05:19 +02:00
Andy Polyakov
91a6bf80f8 aesni-sha256-x86_64.pl: add missing rex in shaext.
PR: 3405
2014-06-14 16:03:06 +02:00
Andy Polyakov
977f32e852 Facilitate back-porting of AESNI and SHA modules.
Fix SEH and stack handling in Win64 build.
2014-06-12 21:45:41 +02:00
Andy Polyakov
619b94667c Add support for Intel SHA extension. 2014-06-11 10:27:45 +02:00
Andy Polyakov
e2eabed110 aesni-mb-x86_64.pl: add Win64 SEH. 2014-06-10 23:08:06 +02:00
Andy Polyakov
5dcf70a1c5 ARM assembly pack: get ARMv7 instruction endianness right.
Pointer out and suggested by: Ard Biesheuvel.
2014-06-06 21:27:18 +02:00
Andy Polyakov
65cad34b10 aesv8-armx.pl update:
- fix 32-bit build (submitted by Ard Biesheuvel);
- fix performance issue in CTR;
2014-06-06 12:18:51 +02:00
Andy Polyakov
d86689e1d9 aesp8-ppc.pl: fix typos. 2014-06-04 08:34:18 +02:00
Andy Polyakov
de51e830a6 Engage POWER8 AES support. 2014-06-01 23:38:11 +02:00
Andy Polyakov
ddacb8f27b Engage ARMv8 AES support. 2014-06-01 22:20:37 +02:00
Andy Polyakov
e09ea622bb aesv8-armx.pl: add CTR implementation.
Submitted by: Ard Biesheuvel.
2014-05-29 22:45:35 +02:00
Andy Polyakov
7cbdb975c2 aesp8-ppc.pl: optimize CBC decrypt even further.
10-19% improvement depending on key length and endianness.
2014-05-29 15:10:12 +02:00
Andy Polyakov
fda29b6db0 aesp8-ppc.pl: add optimized CBC decrypt. 2014-05-23 20:15:06 +02:00
Andy Polyakov
b83d09f552 vpaes-ppc.pl: comply with ABI. 2014-05-23 20:14:38 +02:00
Andy Polyakov
3e68273326 aesv8-armx.pl: fix typo. 2014-05-20 23:32:12 +02:00
Andy Polyakov
a0a17fcb75 aesv8-armx.pl: optimize by adding 128-bit code paths. 2014-05-20 22:50:28 +02:00