Jens Steube
245301c9b4
Started optimizing some of the OpenCL kernel for latest AMD Catalyst 15.12:
...
- Replaced SBOX for DES:
replaced JtR's * Bitslice DES S-boxes making use of a vector conditional select operation (e.g., vsel on PowerPC with AltiVec).
with JtR's * Bitslice DES S-boxes for x86 with MMX/SSE2/AVX and for typical RISC architectures.
Performance increased for DEScrypt from 355MH/s to 405MH/s and for LM from 11100MH/s to 12000MH/s
BTW, the same effect can be seen with non-maxwell GPU's
- Remove some volatile keywords no longer needed thanks to fixed catalyst bugs
- Fix weak-hash-check parameter for use with tools/test.sh
2016-01-14 19:44:47 +01:00
philsmd
cbe6be9246
set default iteration count for -m 2100 = DCC2 to 10240
2016-01-14 00:14:43 +01:00
Jens Steube
49d0767aa8
Run weak-hash checks only in straight-attack mode, this greatly reduces code complexity
2016-01-13 22:22:46 +01:00
Jens Steube
52d71de0d4
Added support to utilize multiple different OpenCL platforms in parallel, ex: AMD + NV
2016-01-13 17:10:40 +01:00
Jens Steube
730044e26e
Added option --opencl-device-types to filter for specific OpenCL device types
2016-01-12 00:44:28 +01:00
jsteube
f0a84a2410
Added new hash mode -m 13000 = RAR5
2016-01-09 20:34:12 +01:00
jsteube
332b3c35e5
Added new hash mode -m 12900 = Android FDE (Samsung DEK)
2016-01-09 00:49:54 +01:00
philsmd
4d6d056709
updated MIT license year
2016-01-05 19:31:35 +01:00
jsteube
2b706f909e
Update README.txt with new release version number and new driver recommendation
2016-01-05 16:50:57 +01:00
jsteube
16294fe94e
Next release version will be v2.10
2016-01-05 08:30:18 +01:00
jsteube
331188167c
Replace the substring GPU to a more appropriate "device" or "kernel" substring depending on the context
2016-01-05 08:26:44 +01:00
philsmd
00d8789346
Merge remote-tracking branch 'upstream/master'
2016-01-03 19:56:23 +01:00
jsteube
0428514f61
Extended support from 14 to 255 functions calls per rule on GPU
2016-01-03 19:49:47 +01:00
philsmd
483833d06d
added note about how to fix the 'cannot find -lOpenCL' error to BUILD.md
2016-01-03 19:47:55 +01:00
philsmd
1774f73601
updated BUILD.md with the notes about OpenCL-Headers + removed some target that do not exist anymore
2016-01-03 19:25:37 +01:00
Jens Steube
dc13c2fc71
Switched to Khronos OSS OpenCL reference implementation for building
...
For detailed information see: https://github.com/hashcat/oclHashcat/issues/40
2016-01-03 13:17:14 +01:00
jsteube
2be8f5f982
- Added Makefile target for native compilation
...
- Moved rules_optimize tool to hashcat-utils
2016-01-02 17:42:47 +01:00
Jens Steube
5fa4d9918b
Update BUILD.md
2016-01-01 22:22:04 +01:00
philsmd
fc65b6fd44
issue #38 : NVIDIA SDK is not needed anymore, the lib is dynamically loaded on NVidia systems
2016-01-01 17:41:03 +01:00
Jens Steube
0f906dcfeb
Fix a bug in the implementation of GOST R 34.11-94, zero length passwords were not cracked
2015-12-26 17:10:03 +01:00
jsteube
f1cdf15540
Added option --gpu-platform to select a single OpenCL platform in case multiple OpenCL platforms are present
2015-12-23 18:02:01 +01:00
jsteube
4e3ec5802e
Update changes to inform people about the good results with ForceWare 358.09
2015-12-21 22:02:52 +01:00
jsteube
83008460fc
We do not depend on CUDA any longer, so get rid of it :)
2015-12-21 12:31:23 +01:00
Gabriele 'Matrix' Gristina
35f740386d
Update for BUILD.md
...
Make the build documentation like hashcat
2015-12-21 12:29:40 +01:00
jsteube
e2412c9b10
We do not depend on CUDA any longer, so get rid of it :)
2015-12-21 12:20:08 +01:00
jsteube
88284108b3
More cleanup
2015-12-15 13:23:32 +01:00
jsteube
0bf4e3c34a
- Dropped all vector code since new GPU's are all scalar, makes the code much easier
...
- Some performance on low-end GPU may drop because of that, but only for a few hash-modes
- Dropped scalar code (aka warp) since we do not have any vector datatypes anymore
- Renamed C++ overloading functions memcat32_9 -> memcat_c32_w4x4_a3x4
- Still need to fix kernels to new function names, needs to be done manually
- Temperature Management needs to be rewritten partially because of conflicting datatypes names
- Added code to create different codepaths for NV on AMD in runtime in host (see data.vendor_id)
- Added code to create different codepaths for NV on AMD in runtime in kernels (see IS_NV and IS_AMD)
- First tests working for -m 0, for example
- Great performance increases in general for NV so far
- Tested amp_* and markov_* kernel
- Migrated special NV optimizations for rule processor
2015-12-15 12:04:22 +01:00
Jens Steube
586441fa25
Revert "Fixed a bug where oclHashcat rejected to load a rule which calls 15 functions although it is supported"
...
This reverts commit f230ed73dc
.
Some kernel require too much constant memory and do not compile anymore
2015-12-13 18:46:21 +01:00
Jens Steube
f230ed73dc
Fixed a bug where oclHashcat rejected to load a rule which calls 15 functions although it is supported
2015-12-13 14:54:39 +01:00
Jens Steube
c460b554d0
- Fixed a bug related to --restore if the User
...
- Updated readme, we actually need catalyst 15.7 (for the binary package) because of OpenCL 2.0
2015-12-11 19:27:07 +01:00
magnum
fc1c7d07af
BUILD.md incorrectly referred to docs/deps.sh as opposed to tools/deps.sh.
2015-12-10 19:23:30 +01:00
philsmd
c15f0d6146
issue #16 : use just "deps" instead of "hashcat-deps" as directory name
2015-12-09 15:55:06 +01:00
philsmd
29547c4f9b
issue #14 : move /opt/hashcat-deps/ to [git_clone_dir]/hascat-deps/
2015-12-09 13:33:21 +01:00
philsmd
32a21150fb
minor: docs/changes.txt updated
2015-12-08 00:15:33 +01:00
Jens Steube
490ff03fe1
It's important to release a fixed version of v2.00 because of the issue #1 even if AMD is not affected
2015-12-05 13:42:02 +01:00
philsmd
9684d8793a
fixes issue #1 : cuMemsetD8() 1 error (nvidia only, problem did not affect mask attacks)
2015-12-05 08:48:00 +01:00
Jens Steube
5065474b4e
Initial commit
2015-12-04 15:47:52 +01:00