b169653b8f
Fix missing return value in rule_op_mangle_toggle_at()
jsteube2017-09-08 22:49:49 +02:00
55f653f374
Get rid of volatile in TrueCrypt kernels
jsteube2017-09-08 19:47:56 +02:00
16e33b20fc
Fix out of boundary access in -m 4700
jsteube2017-09-08 19:42:34 +02:00
51dd982b12
Bring back some volatile for AMD
jsteube2017-09-08 14:08:21 +02:00
9125062ffc
Move volatiles for AMD closer to the problem
jsteube2017-09-08 13:32:19 +02:00
1963b12fdc
According to AMD docs, GCN 3 and 4 are the same
jsteube2017-09-08 12:46:00 +02:00
2b4be5d093
Move AMD ROCm driver check out of a --force condition
jsteube2017-09-08 12:44:06 +02:00
ac9f1da747
Add fine-tuned AMD GCN control macros
jsteube2017-09-07 20:33:43 +02:00
3b89153c2d
Fix use of --hex-salt with SALT_TYPE_GENERIC
jsteube2017-09-06 22:14:06 +02:00
d05f40ab98
Remove OpenCL build option -O2 fixed for ROCm and AMDGPU-PRO using AMD_OCL_BUILD_OPTIONS_APPEND, no longer needed with latest ROCm
jsteube2017-09-06 16:38:55 +02:00
a910aea9e0
Do not use __local memory for -m 13100 if running on a device without physical shared memory
Jens Steube2017-09-05 17:41:55 +02:00
b58aa445b4
Do not use __local memory for -m 7500 if running on a device without physical shared memory
Jens Steube2017-09-05 17:37:20 +02:00
3e597f4c7b
Revert use of zero-copy for main password buffer using CL_MEM_ALLOC_HOST_PTR and hc_clEnqueueMapBuffer() Caused problems with WPA cracking performance on NVidia when not using rules
Jens Steube2017-09-05 17:19:49 +02:00
63f6ca5114
Do not use __local memory for whirlpool if running on a device without physical shared memory
Jens Steube2017-09-05 16:45:20 +02:00
0a0522cf76
Reset salt length limit in test.pl for mode 4520 to not run into errors in case the user specifies the -O mode
jsteube2017-09-04 15:57:57 +02:00
0dfe015301
Fixed a parser error in multiple modes not checking for return code, resulting in negative memory index writes
jsteube2017-09-04 15:53:13 +02:00
8b0e7087c7
Fixed an invalid optimization code in kernel 7700 depending on the input hash, causing the kernel to loop forever
jsteube2017-09-03 13:36:14 +02:00
151dbc5349
Fix replace value in inc_hash_ripemd160.cl
jsteube2017-09-01 16:35:08 +02:00
f859f466ef
Fix -m 8300 in -a 0 mode
jsteube2017-09-01 16:10:29 +02:00
f5e04254dc
Fix -m 10800 in -a 0 mode
jsteube2017-09-01 16:06:42 +02:00
8ee75141ea
OpenCL Runtime: Set OpenCL build option -O2 fixed for ROCm and AMDGPU-PRO using AMD_OCL_BUILD_OPTIONS_APPEND
jsteube2017-08-31 15:25:19 +02:00
d3b9febb30
Fix some double variable declarations
jsteube2017-08-30 16:29:25 +02:00
40b57677cd
OpenCL Kernels: Reactivate Dalibors XOR optimization on MD5_H on all MD5 based algorithms
jsteube2017-08-30 15:32:09 +02:00
6d112aeb39
OpenCL Kernels: Rewritten Keccak kernel to run fully on registers and partially reversed last round
jsteube2017-08-30 13:27:04 +02:00
8fb583f0a7
Simplify kernel thread calculation for SCRYPT based algorithms
Jens Steube2017-08-29 22:43:26 +02:00
fcd20fbacb
OpenCL Runtime: Fall back to 64 threads default (from 256) on AMD GPU to prevent creating too many workitems
Jens Steube2017-08-29 17:36:50 +02:00
a378abee66
Add missing NEW_SIMD_CODE in -m 6600
jsteube2017-08-29 12:01:43 +02:00
918578bee1
Improve some NVidia specific inline assembly
jsteube2017-08-28 14:15:47 +02:00
9de1e557bb
More VEGA specific inline assembly to improve SHA1 based kernels
jsteube2017-08-28 09:24:06 +02:00
a0be36d7b8
Fix compile error caused by __add3()
jsteube2017-08-27 19:46:17 +02:00
00e38cc2c6
Add VEGA specific inline assembly to improve all MD4, MD5, SHA1 and SHA256 based kernels
jsteube2017-08-27 19:36:07 +02:00
7cebc936fd
Add a note on improved rule engine performance to changes.txt
jsteube2017-08-27 17:16:35 +02:00
7bfd343ec9
Optimized rule_op_mangle_dupechar_last(), rule_op_mangle_rotate_right(), rule_op_mangle_rotate_left() and append_block1() in rule engine
jsteube2017-08-27 16:47:21 +02:00
52a97fee75
Improve rule engine performance by improving append_0x80_xxx() performance by using precomputed values from constant memory
jsteube2017-08-27 14:22:20 +02:00
3260000357
Fix whirlpool pure kernel in -a 0 mode
jsteube2017-08-26 19:51:37 +02:00
e3810d054b
Fix some use of pw_t tmp variable
jsteube2017-08-26 19:48:38 +02:00
5e01ff4c53
Refactor some u32x to u32 where u32x is not needed
jsteube2017-08-26 18:31:50 +02:00
35a24df55e
Fixed an integer overflow in hash buffer size calculation
jsteube2017-08-26 16:29:59 +02:00
f6fe5657a3
Fixed an integer overflow in masks not skipped when loaded from file
jsteube2017-08-26 14:40:53 +02:00
2bc2137203
Remove some debugging statement
jsteube2017-08-25 20:54:21 +02:00
688a580d6c
Fixed an integer overflow in innerloop_step and innerloop_cnt variables
jsteube2017-08-25 20:52:13 +02:00
1aa76eac15
Refactor use of __constant to match up with the user selected attack mode
jsteube2017-08-25 17:52:55 +02:00
938c281ee0
Resurrect some volatile variables in order to correctly compile pure kernels on AMD drivers
jsteube2017-08-25 17:06:07 +02:00
48fbe81a09
Add more inline assembly for AMD ROCm
jsteube2017-08-25 16:33:00 +02:00
6c619155c3
Workaround ROCm compiler error in aes256_ExpandKey()
jsteube2017-08-25 12:10:36 +02:00
8c9c36ee2a
Fix out-of-bound access in aesXXX_InvertKey()
jsteube2017-08-25 11:52:07 +02:00
a08f65b50e
flip the logic in terminal.c for readability
Royce Williams2017-08-22 06:53:18 -08:00
7b71fb803b
Add hash-mode to --example-hashes and use $HEX[] in case the password is in binary
jsteube2017-08-22 15:52:41 +02:00
18c8de3428
Use zero-copy for main password buffer using CL_MEM_ALLOC_HOST_PTR and hc_clEnqueueMapBuffer()
jsteube2017-08-22 15:19:25 +02:00
12d95fd22c
Added option --example-hashes to show an example hash for each hash-mode
jsteube2017-08-22 11:09:46 +02:00
a8f3392344
Startup: Show some attack-specific optimizer constraints on start, eg: minimum and maximum support password- and salt-length
jsteube2017-08-22 10:08:28 +02:00
8853884f2a
Fix append_four_byte() in case sm8 is 0
jsteube2017-08-21 16:04:43 +02:00
064e53fa23
Add missing changes to changes.txt
jsteube2017-08-19 17:55:50 +02:00
0846b33f52
Fixed an invalid progress value in status view if words from the base wordlist get rejected because of length
jsteube2017-08-19 17:02:05 +02:00
319799bbbf
Switch the datatypes of the variables responsible for work-item count and work-item size from u32 to u64
jsteube2017-08-19 16:39:22 +02:00