Andy Polyakov
|
64214a2183
|
New Montgomery multiplication module, ppc64-mont.pl. Reference, non-optimized
implementation. This is essentially informational commit.
|
2007-12-29 20:26:46 +00:00 |
|
Andy Polyakov
|
ca64056836
|
Engage x86 assembler in Mac OS X build.
|
2007-12-18 17:33:49 +00:00 |
|
Andy Polyakov
|
70ba4ee5d5
|
Commit #16325 fixed one thing but broke DH with certain moduli.
|
2007-11-03 20:09:04 +00:00 |
|
Andy Polyakov
|
0023adb47a
|
Switch to bn-s390x (it's faster on keys longer than 512 bits) and mention
s390x assembler pack in CHANAGES.
|
2007-10-01 07:38:32 +00:00 |
|
Andy Polyakov
|
7722e53f12
|
Yet another ARM update. It appears to be more appropriate to make
developers responsible for -march choice.
|
2007-09-27 16:27:03 +00:00 |
|
Andy Polyakov
|
75a8e30f4f
|
Minimize stack utilization in probable_prime.
|
2007-09-18 20:52:05 +00:00 |
|
Bodo Möller
|
08b229e13f
|
Make sure that BN_from_montgomery keeps the BIGNUMS in proper format
|
2007-09-18 16:35:28 +00:00 |
|
Dr. Stephen Henson
|
710069c19e
|
Fix warnings.
|
2007-08-12 17:44:32 +00:00 |
|
Andy Polyakov
|
35295bdbee
|
bn_mul_recursive doesn't handle all cases correctly, which results in
BN_mul failures at certain key-length mixes.
PR: 1427
|
2007-07-08 18:53:03 +00:00 |
|
Andy Polyakov
|
62aa5dd415
|
Fix build problem on Tru64.
|
2007-06-29 13:11:45 +00:00 |
|
Andy Polyakov
|
673c55a2fe
|
Latest bn_mont.c modification broke ECDSA test. I've got math wrong, which
is fixed now.
|
2007-06-29 13:10:19 +00:00 |
|
Andy Polyakov
|
5b89f78a89
|
Typo in x86_64-mont.pl.
PR: 1549
|
2007-06-21 11:38:52 +00:00 |
|
Andy Polyakov
|
1c7f8707fd
|
bn_asm for s390x.
|
2007-06-20 14:10:16 +00:00 |
|
Andy Polyakov
|
2329694222
|
SPARC Solaris and Linux assemblers treat .align directive differently.
PR: 1547
|
2007-06-20 12:24:22 +00:00 |
|
Dr. Stephen Henson
|
9677bf0f30
|
Update .cvsignore
|
2007-06-18 12:40:24 +00:00 |
|
Andy Polyakov
|
7d9cf7c0bb
|
Eliminate conditional final subtraction in Montgomery assembler modules.
|
2007-06-17 17:10:03 +00:00 |
|
Andy Polyakov
|
55525742f4
|
Privatize BN_*_no_branch.
|
2007-06-11 16:33:03 +00:00 |
|
Andy Polyakov
|
c693b5a55c
|
Commentary updates and minor optimization for bn_mont.c.
|
2007-06-11 08:53:52 +00:00 |
|
Andy Polyakov
|
6b6443dead
|
Eliminate conditional final subtraction in Montgomery multiplication.
|
2007-06-10 19:34:38 +00:00 |
|
Andy Polyakov
|
b900df5258
|
Engage s390x assembler modules.
|
2007-04-30 09:22:27 +00:00 |
|
Andy Polyakov
|
a2a54ffc5f
|
s390x assembler pack.
|
2007-04-30 08:42:54 +00:00 |
|
Bodo Möller
|
24a8c25ab5
|
fix error codes
|
2007-04-19 15:14:21 +00:00 |
|
Bodo Möller
|
d1e7d1d96c
|
don't violate the bn_check_top assertion in BN_mod_inverse_no_branch()
|
2007-04-19 14:45:57 +00:00 |
|
Bodo Möller
|
b002265ee3
|
make BN_FLG_CONSTTIME semantics more fool-proof
|
2007-03-28 18:41:23 +00:00 |
|
Bodo Möller
|
bd31fb2145
|
Change to mitigate branch prediction attacks
Submitted by: Matthew D Wood
Reviewed by: Bodo Moeller
|
2007-03-28 00:15:28 +00:00 |
|
Andy Polyakov
|
8b71d35458
|
nasm fixes.
|
2007-03-20 08:55:58 +00:00 |
|
Andy Polyakov
|
760e353528
|
sparcv9a-mont was modified to handle 32-bit aligned input, but check
for 64-bit alignment was not removed.
|
2007-03-20 08:54:51 +00:00 |
|
Dr. Stephen Henson
|
af32f9fdda
|
Update from fips2 branch.
|
2007-02-03 17:32:49 +00:00 |
|
Dr. Stephen Henson
|
560b79cbff
|
Constify version strings and some structures.
|
2007-01-21 13:07:17 +00:00 |
|
Andy Polyakov
|
64aecc6720
|
Make armv4t-mont module backward binary compatible with armv4 and rename it
accordingly.
|
2007-01-17 20:12:41 +00:00 |
|
Andy Polyakov
|
43b8fe1cd0
|
Montgomery multiplication for ARMv4.
|
2007-01-11 21:43:25 +00:00 |
|
Andy Polyakov
|
8876e58f34
|
Montgomery multiplication for MIPS III/IV. Not engaged.
|
2006-12-29 11:09:33 +00:00 |
|
Andy Polyakov
|
7321a84d4c
|
Minor clean-up in crypto/bn/asm.
|
2006-12-29 11:05:20 +00:00 |
|
Andy Polyakov
|
4cfe3df1f5
|
Minor performance improvements to x86-mont.pl.
|
2006-12-28 12:43:16 +00:00 |
|
Andy Polyakov
|
8f2d60ec26
|
Fix for "strange errors" exposed by ccgost engine. The fix is
two extra insructions in sqradd loop at line #503.
|
2006-12-27 10:59:51 +00:00 |
|
Andy Polyakov
|
1702c8c4bf
|
x86-mont.pl sse2 tune-up and integer-only squaring procedure.
|
2006-12-22 15:28:07 +00:00 |
|
Andy Polyakov
|
87d3af6475
|
Eliminate 64-bit alignment limitation in sparcv9a-mont.
|
2006-12-08 15:18:41 +00:00 |
|
Andy Polyakov
|
98939a05b6
|
alpha-mont.pl: gcc portability fix and make-rule.
|
2006-12-08 14:18:58 +00:00 |
|
Andy Polyakov
|
d28134b8f3
|
Minor, +10%, tune-up for x86_64-mont.pl.
|
2006-12-08 10:13:51 +00:00 |
|
Andy Polyakov
|
8583eba015
|
Montgomery multiplication routine for Alpha.
|
2006-12-08 10:12:56 +00:00 |
|
Andy Polyakov
|
73b979e601
|
Clarify HAL SPARC64 support situation in sparcv9a-mont.pl.
|
2006-11-28 11:07:36 +00:00 |
|
Andy Polyakov
|
ebae8092cb
|
Minor optimizations based on intruction level profiler feedback.
|
2006-11-28 10:34:51 +00:00 |
|
Andy Polyakov
|
2e21922eb6
|
Modulo-schedule loops in sparcv9a-mont.pl. Overall improvement factor
over 0.9.8 is up to 3x on USI&II cores and up to 80% - on USIII&IV.
|
2006-11-28 07:24:26 +00:00 |
|
Andy Polyakov
|
1c3d2b94be
|
This is "informational" commit. Its mere purpose is to expose "modulo
factor" in inner loops.
|
2006-11-28 07:20:36 +00:00 |
|
Andy Polyakov
|
48d2335d73
|
Non-SSE2 path to bn_mul_mont. But it's disabled, because it currently
doesn't give performance improvement.
|
2006-11-27 14:59:35 +00:00 |
|
Dr. Stephen Henson
|
47a9d527ab
|
Update from 0.9.8 stable. Eliminate duplicate error codes.
|
2006-11-21 21:29:44 +00:00 |
|
Andy Polyakov
|
31439046e0
|
bn/asm/ppc.pl to use ppc-xlate.pl.
|
2006-10-17 14:37:07 +00:00 |
|
Andy Polyakov
|
cecfdbf72d
|
VIA-specific Montgomery multiplication routine.
|
2006-10-17 07:04:48 +00:00 |
|
Bodo Möller
|
a53cdc5b08
|
Ensure that the addition mods[i]+delta cannot overflow in probable_prime().
[Problem pointed out by Adam Young <adamy (at) acm.org>]
|
2006-09-18 14:00:49 +00:00 |
|
Andy Polyakov
|
8ea975d070
|
+20% tune-up for Power5.
|
2006-08-09 15:40:30 +00:00 |
|