Gabriele Gristina
490702fcfa
Backends: added Metal host-code
3 years ago
Gabriele Gristina
6175459b0a
Merge branch 'hashcat:master' into autotune_error_handling
3 years ago
Gabriele Gristina
7650894e02
fixed bug in benchmark engine, updated negative status code
3 years ago
Gabriele Gristina
607d314ff2
Merge branch 'master' into autotune_error_handling
3 years ago
Jens Steube
668d2179cd
Kernels: Refactored standard kernel declaration to use a structure holding u32/u64 attributes to reduce the number of attributes
3 years ago
Gabriele Gristina
3802adff7e
Autotune: Added error handling. By default skipping device on error, with --force using accel/loops/threads min values instead
3 years ago
Jens Steube
534bfd3172
Fixed out-of-boundary reads in attack mode 9 that were caused by a missing work item limit in the refactored autotune engine
3 years ago
Jens Steube
9254603960
Fixed out-of-boundary read in PKZIP masterkey kernel if the password candidate has length zero.
...
Now that kernel threads are no longer fixed over the entire session, hardware_power and hardware_power_all
needs to be updated the same way as kernel_power and kernel_power_all for each call to inner2_loop().
3 years ago
Jukka Ojanen
3d7ce7162b
Merge branch 'master' of https://github.com/hashcat/hashcat
3 years ago
Jens Steube
d4997d1255
Added support for auto-tuning --kernel-threads (-T) on startup
3 years ago
Jukka Ojanen
8d51fca192
No need to synchronize after run_kernel()
3 years ago
Jukka Ojanen
c48e6a25a8
Enqueue several commands before clFlush()
3 years ago
Jukka Ojanen
e889cf98a9
Few cleanups in autotune
3 years ago
Jukka Ojanen
a86b44a750
Allow async execution of autotune() and prepare try_run() for async kernel execution
3 years ago
Jukka Ojanen
f07ff6f03d
Use kernel_bzero instead of kernel_memset when value is zero
3 years ago
Jukka Ojanen
4c0f6dd263
Merge branch 'hashcat:master' into master
3 years ago
Jens Steube
7d43b6e1eb
Clear tmps memory region after autotune use
3 years ago
Jens Steube
0504498e86
Merge pull request #2886 from pellekuiters/issue-2876
...
Auto-tuning outside kernel can cause unpredictable behavior for tmp_t structs on CUDA
3 years ago
pelle
ac3ccfcc51
Run init() and loop_prepare() during autotune to prevent possible corruptions during loop().
3 years ago
Jukka Ojanen
72a418932c
HIP: Use kernel_bzero instead of kernel_memset when value is zero
3 years ago
Jukka Ojanen
8066a47ac5
Merge branch 'hashcat:master' into master
3 years ago
Jukka Ojanen
43b5a138d4
Use kernel_bzero instead of kernel_memset when value is zero
3 years ago
Jens Steube
23c3c178bf
Limit max threads per block to 64 to enable offline compiler to make better use if available registers
...
Fix double free() for hip_event1/hip_event2 and hip_stream causes segfault
Replace hc_cuCtxSetCurrent() with hc_cuCtxPushCurrent() in order to align changes with HIP
Add vector datatype operators (if we decide to use them - currently unused)
3 years ago
Jens Steube
1b84a9e53b
Add missing backports from code base v6.2.2
...
Fix context to thread management
Fix missing code in selftest.c, autotune.c, hashes.c, dispatch.c and backend.c
Use IS_HIP depending code makes it easier for future optimization related to inline assembly calls - instead of using IS_CUDA || IS_HIP
See TODO markers for more optimizations / next steps
3 years ago
Jens Steube
04d5e5a119
New Attack-Mode: Association Attack. Like JtR's single mode. Very early
...
stage. See hashcat Forum for detailed writeup.
4 years ago
Jens Steube
9b64a405d1
Fixed cleanup of password candidate buffers on GPU set from autotune in case -n was used
4 years ago
Rosen Penev
bd6c0e57e4
Change 0/1 to true/false
...
Found with clang-tidy
5 years ago
Rosen Penev
98e17d5774
Run through clang-tidy's readability-uppercase-literal-suffix
...
1 and l are visually similar and can be confused. This also changes u to U
for consistency.
5 years ago
Jens Steube
1943c35e4a
Improve kernel-loops detection for slow hashes
5 years ago
Jens Steube
fa9d073f9a
Manually unroll sha2 hashes
5 years ago
Jens Steube
a6bc1d3cc0
Experimental kernel-thread autotuner
5 years ago
Jens Steube
08dc1acc02
More CUDA rewrites
5 years ago
Jens Steube
ec9925f3b1
Warnings self-check and autotune with CUDA
5 years ago
Jens Steube
f2948460c9
Some first kernel invocations
5 years ago
Jens Steube
50a6e720ca
More OpenCL variables rename
5 years ago
Jens Steube
af8e317cf4
Begin renaming some OpenCL only variables
5 years ago
Jens Steube
4b986de5fb
Prepare native CUDA hybrid integration
6 years ago
jsteube
4548d15dde
Fix spin_damp datatype
6 years ago
jsteube
708a86fb59
Move old ascii_digest() to hashes.c and rename it to hash_encode(), also remove some unused includes
6 years ago
jsteube
1537fc4e5d
Improve handling of temporary skipped devices (due to JiT build failure or unstable_warning)
6 years ago
jsteube
3c37daf94b
Get rid of hash_mode in autotune.c
6 years ago
Jens Steube
e770449702
OpenCL Runtime: Use our own yielding technique for synchronizing rather than vendor specific
...
Parameter: Rename --nvidia-spin-damp to --spin-damp (now accessible for all devices)
6 years ago
Rosen Penev
77daf05dd0
Add HC_API_CALL to a few functions
...
On 32-bit MinGW, clang was throwing errors about this.
64-bit MinGW and regular MSYS does not throw warnings after the change.
6 years ago
jsteube
52c52836e3
Add new option --slow-candidates which allows hashcat to generate passwords on-host
6 years ago
jsteube
fe4413797e
OpenCL Kernels: Use three separate comparison kernels (depending on keyver) for WPA instead of one
7 years ago
jsteube
c4f30220a0
OpenCL Kernels: Refactored kernel thread management from native to maximum per kernel
7 years ago
jsteube
05a01d3843
fix some datatypes
7 years ago
jsteube
a3a16f676f
OpenCL Kernels: Add a decompressing kernel and a compressing host code in order to reduce PCIe transfer time
...
For details see https://hashcat.net/forum/thread-7267.html
7 years ago
Jens Steube
665a514977
Use a more conservative mechanic in the last step of the autotune
7 years ago
Jens Steube
fb00b528c4
Improve autotune and synchronize results on same OpenCL devices
7 years ago