Jens Steube
cace799187
Move more no unrolling exceptions from inc_vendor.cl to specific modules
2019-03-07 18:57:04 +00:00
jsteube
dc9279c95c
New Strategy: Instead of using volatile, mark the mode as unstable. Remove all volatiles
2019-03-03 19:18:56 +01:00
jsteube
7c1120b784
Migrate unroll handling for -m 15900 from OpenCL/inc_vendor.cl to module_jit_build_options()
2019-03-03 13:44:25 +01:00
jsteube
1714382daa
Migrate unroll handling for -m 14100 from OpenCL/inc_vendor.cl to module_jit_build_options()
2019-03-03 11:55:42 +01:00
jsteube
b0a83b28d1
Migrate unroll handling for -m 12300 from OpenCL/inc_vendor.cl to module_jit_build_options()
2019-03-03 11:47:33 +01:00
jsteube
1937b67595
Migrate unroll handling for -m 8200 from OpenCL/inc_vendor.cl to module_jit_build_options()
2019-03-03 11:43:47 +01:00
jsteube
fee37ac4c3
Migrate unroll handling for -m 8000 from OpenCL/inc_vendor.cl to module_jit_build_options()
2019-03-03 11:39:18 +01:00
jsteube
88a051629c
Support module specific JiT compiler build options
2019-03-02 11:12:13 +01:00
jsteube
4359418918
OpenCL Runtime: Not using amd_bytealign (amd_bitalign is fine) on AMDGPU driver drastically reduces JiT segfaults
2019-03-01 15:34:49 +01:00
jsteube
540b405e3a
Replace IS_ROCM with HAS_VPERM and HAS_VADD3
2019-02-24 10:12:48 +01:00
Jens Steube
ae577410d0
OpenCL Device: Do a real query on OpenCL local memory type instead of just assuming it
2018-11-20 10:06:34 +01:00
jsteube
6469357c74
Remove SCR_TYPE macro from OpenCL code
...
Disable REAL_SHM access to AMD platform devices
2018-08-13 12:10:03 +02:00
jsteube
dad05d9f69
Testing: Workaround some AMD OpenCL runtime segmentation faults
2018-08-09 13:03:22 +02:00
Jens Steube
a43d3ad176
Rename some hashcat specific OpenCL functions to avoid conflicts with existing OpenCL functions from OpenCL runtime
2018-07-22 12:20:20 +02:00
jsteube
c1622d6593
Fixed detection of AMD_GCN version in case the rocm driver is used
2018-07-21 11:52:54 +02:00
Jens Steube
ad50883080
Allow unroll for DES based algorithms but not bitsliced versions
2018-02-18 11:28:25 +01:00
Jens Steube
aa82d8d34d
Re-enable CPU optimizations and some CPU case in thread management
2018-02-16 18:56:21 +01:00
Jens Steube
2a19f19904
Drop -m 6800 from no-unroll list in inc_vendor.cl
2018-02-13 17:08:29 +01:00
jsteube
d5153539e2
Some syntax error
2018-02-08 09:49:59 +01:00
jsteube
786384664e
DECLSPEC for CPU
2018-02-08 09:42:59 +01:00
jsteube
e4e1c1d515
We can't mix inline functions with static constants
2018-02-07 14:16:27 +01:00
Jens Steube
8273bb8376
NV JiT doesn't like static inline keywords
2018-02-06 22:05:15 +01:00
jsteube
3e08750900
OpenCL Kernels: Add general function declaration keyword (static inline)
2018-02-06 19:12:24 +01:00
jsteube
00abb849e1
Update inc_vector.cl for ideal performance with reference GTX1080 for NV and Vega64 for AMD
2017-10-26 13:41:47 +02:00
Fist0urs
a6294537fd
Splitted DPAPI kernel in 2 to increase performances
2017-09-21 12:23:33 +02:00
jsteube
1963b12fdc
According to AMD docs, GCN 3 and 4 are the same
2017-09-08 12:46:00 +02:00
jsteube
ac9f1da747
Add fine-tuned AMD GCN control macros
2017-09-07 20:33:43 +02:00
Jens Steube
b58aa445b4
Do not use __local memory for -m 7500 if running on a device without physical shared memory
2017-09-05 17:37:20 +02:00
Jens Steube
63f6ca5114
Do not use __local memory for whirlpool if running on a device without physical shared memory
2017-09-05 16:45:20 +02:00
jsteube
00e38cc2c6
Add VEGA specific inline assembly to improve all MD4, MD5, SHA1 and SHA256 based kernels
2017-08-27 19:36:07 +02:00
jsteube
51372438fe
Allow OpenCL kernel inline assembly if ROCm drivers was detected
2017-08-22 18:47:53 +02:00
jsteube
bf299fe043
Optimized 3DES for rocm
2017-08-17 14:03:55 +02:00
jsteube
9ee5da40e0
Workaround rocm compiler error for -m 15300
2017-08-17 11:25:34 +02:00
jsteube
772441448a
Optimized -m 8000 for ROCm
2017-07-24 13:13:35 +02:00
jsteube
3125a756d9
Remove some AMD _unroll restrictions no longer required with ROCm
2017-07-23 14:44:20 +02:00
jsteube
5e34ec348e
Optimize kernels for ROCm 1.6
...
- Remove inline keywords
- Remove volatile keywords where it causes ROCm to slow down
- Replace DES functions (looks like bitselect somehow is no longer mapped to BFI_INT)
2017-07-22 18:05:18 +02:00
jsteube
cefd2ddb94
Tune AMD unroll settings for AMD-GPU-PRO 17.40
2017-06-29 15:50:46 +02:00
jsteube
8257883ec1
Added hash-mode 14600 = LUKS
2017-01-21 15:37:44 +01:00
jsteube
899413f88b
Allow unroll of Android FDE (Samsung DEK) on NV
2016-11-25 22:24:14 +01:00
jsteube
ac02c60b3f
Do not allow unroll of Drupal7, but for NV only
2016-11-25 22:12:54 +01:00
jsteube
ee2e8ba598
Do not allow unroll of Drupal7, increases performance on CL1.2
2016-11-25 22:09:19 +01:00
jsteube
0de908905f
Allow unroll of PBKDF2-HMAC-SHA256 on NV
2016-11-25 22:04:24 +01:00
jsteube
0206142a69
Bcrypt on NVIDIA works better when unrolled
2016-11-19 18:17:38 +01:00
Gabriele Gristina
246336c49c
Fix CL_BUILD_PROGRAM_FAILURE on OSX ( #412 )
2016-11-14 19:28:07 +01:00
jsteube
91a69fa635
Experiment to fix https://github.com/hashcat/hashcat/issues/412
2016-11-14 10:50:47 +01:00
jsteube
92f7a560a7
Optimize DES/LM cracking speed boost on AMD
2016-11-14 00:56:35 +01:00
jsteube
31a616e00e
Add a shared section in inc_vendor.cl
2016-11-13 20:58:28 +01:00
jsteube
306fc8a59a
Optimize unrolling for AMD based on AMDGPU-Pro 16.40
2016-11-12 21:20:03 +01:00
jsteube
ac44087c83
Optimize unrolling for AMD based on AMDGPU-Pro 16.40
2016-11-12 20:23:15 +01:00
jsteube
f58c9baade
Do not unroll -m 6800 based algorithm on NV, latest windows driver can't compile them otherwise
2016-10-21 10:14:15 +02:00
