jsteube
9390be8594
Use real registers for salt, high-end maxwells didn't like it with global memory access
2016-05-09 23:07:23 +02:00
jsteube
373d2b9882
Remove barrier from DCC1, high-end maxwells didn't like it
2016-05-09 21:51:36 +02:00
jsteube
c79bed3b7d
Prepare for a more dynamic #pragma unroll use
2016-05-09 21:32:12 +02:00
jsteube
34c3557d50
Fix compiler warnings
2016-05-09 19:23:37 +02:00
Jens Steube
67d5bb4b81
Merge pull request #330 from RolfHashcat/patch-1
...
Update hashcat_tuning.hctab
2016-05-09 12:36:54 +02:00
Rolf
d33360e3f5
Update hashcat_tuning.hctab
...
Requested optimisation of opencl vector width values for GTX Titan Mk I.
2016-05-09 11:31:02 +01:00
jsteube
7709ffbe52
Add some missing hash-modes to hashcat_tuning.hctab
2016-05-09 11:25:51 +02:00
Jens Steube
941e016378
Fix -m 9000 performance for AMD
2016-05-09 09:40:57 +02:00
jsteube
a0221cd368
Fix broken -m 1500 and -m 3000
2016-05-09 09:17:59 +02:00
jsteube
6dac6b409e
Add compiler kernel hints for algorithms with fixed workgroup size
2016-05-09 00:58:04 +02:00
jsteube
71c31fca59
Rewrote sha256crypt from scratch
2016-05-08 22:56:36 +02:00
jsteube
fd77a098c5
Another some unroll to reduce register pressure
2016-05-08 18:57:44 +02:00
jsteube
bd1f555c9c
Remove some unroll to reduce register pressure
2016-05-08 18:29:54 +02:00
jsteube
303cfcae15
Enable unrolling of SHA512 with HMAC on NV
2016-05-08 16:07:40 +02:00
Jens Steube
7f04a89f77
Optimize out the swap32() of sha256 in 7zip
2016-05-08 15:33:32 +02:00
jsteube
16af77af18
Extended password length up to 32 for 7zip
2016-05-08 14:39:44 +02:00
jsteube
ab193c4162
Rename ALIAS_pre_maxwell and ALIAS_maxwell_budget to ALIAS_nv_use_simd
2016-05-08 13:45:49 +02:00
jsteube
b877c84486
Run a few device compatibility checks on startup
2016-05-08 13:37:58 +02:00
jsteube
b91506c1c7
Check if device is little endian device
2016-05-08 12:58:43 +02:00
jsteube
6d027e77f2
Optimize some macros
...
Use rotate() instead of inline asm; breaks Titan speed
2016-05-08 11:09:44 +02:00
jsteube
41e2d7247a
Update autotune, respect kernel_loops_max
2016-05-08 01:56:32 +02:00
jsteube
5bb8d17784
Merge branch 'master' of https://github.com/hashcat/oclHashcat
2016-05-07 23:51:50 +02:00
jsteube
89dcaeb76d
Replace SHL+ADD with MAD
2016-05-07 23:51:37 +02:00
Jens Steube
74dd96fa5b
Merge pull request #329 from jfoug/master
...
generated and generated2. Changed xNM command to ONM
2016-05-07 21:02:56 +02:00
jsteube
1d15ee40be
Add maxwell budget to hashcat_tuning.hctab
2016-05-07 20:59:35 +02:00
jsteube
8141c7fb60
Little bit inline assembly for the older nvidia cards
2016-05-07 20:45:16 +02:00
jfoug
298340ba47
generated and generated2. Changed xNM command to ONM
2016-05-07 12:58:10 -05:00
Jens Steube
f3a7b088a3
Merge pull request #328 from jfoug/master
...
d3adone.rule: removed duplicates.
2016-05-07 19:52:57 +02:00
jsteube
da4090cca3
Fix pocl version string
2016-05-07 19:51:23 +02:00
jsteube
78dd258200
Add missing pre-maxwell cards
2016-05-07 19:44:02 +02:00
jfoug
e04443c5c7
d3adone.rule: removed duplicates.
2016-05-07 12:34:25 -05:00
jsteube
504aad0dbb
Update hashcat_tuning.hctab to match best settings with new autotuner
2016-05-07 15:50:18 +02:00
jsteube
4f6c3cf818
Merge branch 'master' of https://github.com/hashcat/oclHashcat
2016-05-07 13:21:59 +02:00
jsteube
006f5252b7
Optimize a few modes for hashcat_tuning.hctab for budget NV cards
...
Little experiment with MD4 based optimizations on -m 900 -m 1000 and -m 1100
Fix benchmark in case user fixes -u and -n values
2016-05-07 13:15:21 +02:00
Jens Steube
7a5852ed85
Merge pull request #327 from jfoug/master
...
d3ad0ne rules. Converted all xNM commands into ONM
2016-05-07 11:14:20 +02:00
Jens Steube
01f566451c
Check both kernel_accel and kernel_loops for some minimum value
2016-05-06 14:38:08 +02:00
jfoug
e4eb385d34
d3ad0ne rules. Converted all xNM commands into ONM
2016-05-06 05:27:40 -05:00
Jens Steube
50a7638e7b
Aim for -n 64 in autotune
2016-05-06 11:52:19 +02:00
Jens Steube
c40bf412e5
Fix -m 8500: volatile no longer required
2016-05-06 11:44:28 +02:00
Jens Steube
a7886f02f4
Merge pull request #325 from jfoug/master
...
dive.rule: duplicates found by running data have been removed.
2016-05-06 09:15:59 +02:00
Jens Steube
72e3821a4c
Simplify auto-tuning and benchmark routines
...
Decrease the time it takes to run a benchmark
Removed --benchmark-repeat, it creates no advantage
Fix some wording related to drivers
Dropped special 64-bit rotate() handling for NV
Cleanup SHA384
Cleanup try_run()
2016-05-05 23:21:15 +02:00
jfoug
7c7836acdd
dive.rule: duplicates found by running data have been removed.
2016-05-04 17:17:06 -05:00
Jens Steube
fc89a04737
Update to better scrypt tmto defaults
2016-05-04 11:55:10 +02:00
Jens Steube
29a0eab0b3
Remove pocl warning, add catalyst warning
2016-05-04 11:40:42 +02:00
Jens Steube
3d508f9122
Fix test.sh
2016-05-04 11:21:20 +02:00
jsteube
cd08fa5f8c
Limit kernel_threads on CPU
2016-05-04 10:32:54 +02:00
jsteube
241a8c8485
Fix scrypt handling
2016-05-04 02:06:31 +02:00
Jens Steube
8316210233
Unlock kernel_threads > 64
2016-05-04 00:52:53 +02:00
jsteube
54df10b36d
improved autotune engine
2016-05-03 12:37:43 +02:00
jsteube
dbe2d96618
Fix -m 1500 multihash and benchmark
...
Fix -m 3000 multihash and benchmark
Fix -m 3100 multihash and benchmark
Fix -m 7700 multihash and benchmark
Fix -m 8500 multihash and benchmark
Fix -m 11500 multihash and benchmark
2016-05-03 10:57:23 +02:00
