Commit Graph

317 Commits (d9889727e650fb30497be26b03f51d69cdf9657c)

Author SHA1 Message Date
jsteube f1e0cd6d56 Autotune: 200 loops should be fine for a start
9 years ago
Jens Steube 515385c57d Add dedicated steps for loops and accel
9 years ago
Jens Steube 72e0553e44 Fixed a missing condition
9 years ago
Jens Steube c09bc848f7 Autotuning engine prototype
9 years ago
Jens Steube c0293928dd Prepare for better autotuning capabilities
9 years ago
Gabriele 'matrix' Gristina 2a1d0d21ff Get rid of hc_clEnqueueNDRangeKernel double call
9 years ago
Gabriele 'matrix' Gristina c97dbf56cb Fix bug in weak_hash_check(), wrong kernel_loops assigned
9 years ago
Jens Steube 2dfe9200d6 Remove Wordload-Profiles from tuningdb, we can simply calculate it
9 years ago
Jens Steube 10dc25f807 Merge pull request #217 from magnumripper/master
9 years ago
jsteube 5c01349ba6 Update event handling to workaround event handling error in nvidia opencl runtime
9 years ago
magnum 162bc25a3d Use device's preferred vector width, not the native one. Also, don't
9 years ago
Gabriele 'Matrix' Gristina 20ee62e196 Revert "Use per-device timer resolution in total_time calculations"
9 years ago
Jens Steube 02ad834c7f Added new concept of a tuning database; tryout phase
9 years ago
Jens Steube 8d85b7539d Fixed a bug in line counter: Conditional jump or move depends on uninitialised value
9 years ago
Jens Steube e80541d6dd Check for allocatable device-memory depending on kernel_accel amplifier before trying to allocate
9 years ago
Gabriele 'matrix' Gristina 523a7bfe93 Use CL_DEVICE_PROFILING_TIMER_RESOLUTION per-device value in total_time calculations
9 years ago
Jens Steube 9fc360e39d Added the execution time of the running kernel to the status display
9 years ago
Gabriele 'matrix' Gristina 74be8e2e25 skip device if buildProgram() fail
9 years ago
Jens Steube 6d37c123a5 Merge branch 'master' of https://github.com/hashcat/oclHashcat
9 years ago
Jens Steube ab5ecd8eaa Fix some updated buffer sizes and new optimizer descriptions
9 years ago
Jens Steube 952c20e0f8 Merge pull request #211 from gm4tr1x/issue150
9 years ago
Gabriele 'matrix' Gristina 91fae7e49a Fixed bug in 8900 (probably relate with issue #150)
9 years ago
Gabriele 'matrix' Gristina e2db8afdf8 Add missing pthread_setaffinity_np for osx
9 years ago
Gabriele 'matrix' Gristina 5953130062 Fix clEnqueueNDRangeKernel() error -54
9 years ago
Jens Steube 8650212b80 Remove Workload display in benchmark, remove unused variable
9 years ago
Jens Steube fa0e6fb78e Merge pull request #204 from gm4tr1x/LoopAccelMod
9 years ago
Gabriele 'matrix' Gristina fa7465aa86 gpu loops/accel per-device
9 years ago
Jens Steube 22834781f5 Hack in NvAPI_GPU_GetCoolerSettings(); Enables query fanspeed in percentage on windows
9 years ago
Jens Steube 6c5938201b Revert "Merge pull request #202 from magnumripper/master"
9 years ago
magnum 947a927ed2 Do not silently ignore -w2 for -b. Closes #201.
9 years ago
magnum 68dbaa6f8a Bugfix: putenv(3) was used with a stack variable, that's a no-no.
9 years ago
Gabriele 'matrix' Gristina 89e5ed2574 handling possible clEnqueueFillBuffer not found in opencl lib
9 years ago
Jens Steube 2381af313d Some cleanups
9 years ago
Jens Steube 4d2be9073e Consolidate hardware monitoring interface status on startup
9 years ago
Gabriele 'matrix' Gristina 74db620d51 Add missing memset and update ext_nvapi.c header
9 years ago
Jens Steube e01038083c Update Makefile and BUILD.md
9 years ago
Gabriele 'matrix' Gristina e67eec1ae0 get rid of nvidia nvapi static linking
9 years ago
Gabriele 'matrix' Gristina f3407cd7f4 HWMon mod
9 years ago
Gabriele 'matrix' Gristina 88087295b3 Removed deprecated and unused ADL function (ADL_DisplayEnable_Set)
9 years ago
Jens Steube f256363448 Merge pull request #190 from gm4tr1x/fixLoopsAccelV3
9 years ago
Jens Steube 102dee00eb Merge pull request #192 from gm4tr1x/ADL_LibraryLoader
9 years ago
Gabriele 'matrix' Gristina d120ede655 Update ADL Library Loader
9 years ago
jsteube d0d3507dc2 Fix TI series detection
9 years ago
jsteube 21525b74e1 Remove more unnecessary libOpenCL*.a related stuff
9 years ago
Gabriele 'matrix' Gristina b542d4a431 Fixed loops/accel for 6800, 11300 and 11600 (osx)
9 years ago
Gabriele 'matrix' Gristina dcb4888dd5 Remove unnecessary libOpenCL*.a from Makefile
9 years ago
Jens Steube 55d4904dd3 Merge pull request #185 from gm4tr1x/fixLoopsAccelv2
9 years ago
Gabriele 'matrix' Gristina 53faf6a24a Fixed some gpu loops/accel settings
9 years ago
Gabriele 'matrix' Gristina 0a907fc210 Fixed typo in help
9 years ago
Gabriele 'matrix' Gristina 0f0984fe86 Fixed all gpu code (see PR #179 for details)
9 years ago
Jens Steube 9aea991424 Use a rc for first result, easier to read
9 years ago
Gabriele 'matrix' Gristina f9598f691d Fixed CL_INVALID_WORK_GROUP_SIZE error with Apple CPU
9 years ago
Gabriele 'matrix' Gristina d147d89f5e cleanup unnecessary clGetProgramBuildInfo code
9 years ago
Gabriele 'matrix' Gristina 5d4160dc8c Fixed gcc warnings about missing field initializers
9 years ago
Jens Steube 2c4ad77275 Some systems don't like using the same buffer for both input and output at the same time with snprintf()
9 years ago
magnum ce170ea980 Acquire an exclusive lock before writing to any file. Note that in
9 years ago
Gabriele 'matrix' Gristina ebd28553a5 Handling clBuildProgram failure (show build log on errors)
9 years ago
Gabriele 'matrix' Gristina 3952fa7e06 Updated gpu accel for -m 6211 and default runtime value to 8
9 years ago
Jens Steube bfe3f148d7 As long as we depend on NVAPI for windows we also need to add a path to its includes
9 years ago
Gabriele 'matrix' Gristina 9eefb4bcd7 Fixed get_profile_dir and get_session_dir byte missing bug
9 years ago
Jens Steube 2232b1632e Merge pull request #169 from magnumripper/onetwenty
9 years ago
Jens Steube af7ff57b3d Merge pull request #168 from magnumripper/onesixfour
9 years ago
Jens Steube 98ec1bcee7 Merge pull request #156 from gm4tr1x/master
9 years ago
magnum 115d2b6a5a Drop dependencies on non-distributable ADL/NVML headers. The needed glue
9 years ago
Jens Steube cae457df0c Merge pull request #167 from gm4tr1x/issue84
9 years ago
magnum f5d6f9b6d4 Do not create a kernel cache file if build failed. Also disregard any
9 years ago
Jens Steube 9ec2c86cd0 Merge pull request #165 from gm4tr1x/gcc-warnings
9 years ago
Gabriele 'matrix' Gristina b7d3a7c5bc Fixed gcc warnings
9 years ago
Gabriele 'matrix' Gristina 5bae9de3a3 Implemented OpenCL library loader
9 years ago
Gabriele 'matrix' Gristina 6ba392c0df Modified as @jsteube request
9 years ago
Gabriele 'matrix' Gristina 1124687270 OpenCL runtime environment is no longer required with --keyspace option
9 years ago
Gabriele 'matrix' Gristina dcc4b5a60f Added custom OSX kernel loops and gpu accel default values
9 years ago
Gabriele 'matrix' Gristina 479327fc20 Re-enable gpu-temp-disable argument for osx build
9 years ago
Gabriele 'matrix' Gristina 58359f3b7e Fixed 'buf' initialization for windows
9 years ago
Jens Steube 0997ae029e Remove NO-BREAK SPACE character (utf8) from sources
9 years ago
Jens Steube 9c89b58f76 Merge pull request #153 from gm4tr1x/missingcheck
9 years ago
Jens Steube d275748c7c Merge pull request #152 from gm4tr1x/buf
9 years ago
Gabriele 'matrix' Gristina 17d885ffa4 Added missing check for in_len in _old_apply_rule function
9 years ago
Gabriele 'matrix' Gristina 8674959a93 @philsmd suggestion (PR #152)
9 years ago
Gabriele 'matrix' Gristina 3abacf515c Optimized memset calls and also some initializations
9 years ago
Gabriele 'matrix' Gristina 8d891ef0ba Avoid sprintf
9 years ago
Jens Steube 20b0c23af1 Merge pull request #146 from gm4tr1x/master
9 years ago
Jens Steube 1d3795a3ab Converted _a3 kernels, use SIMD for CPU and GPU
9 years ago
Gabriele 'matrix' Gristina 076597fe01 Fixed some memory allocations and other small things
9 years ago
Jens Steube 4c0e520fd8 Test convert for -m 1000 with -a 0 for SIMD, speed is now on par or faster than hashcat
9 years ago
Jens Steube add18eaa6d Fix for last commit
9 years ago
Jens Steube bfc4495bd3 Expanded version information as discussed in https://github.com/hashcat/oclHashcat/issues/138
9 years ago
Gabriele 'matrix' Gristina 5da79e4411 Added support for build without ADL/NVML/NVAPI (issue #120)
9 years ago
philsmd 751a364125 #137: fixes padding for base64_encode () and base64_decode()
9 years ago
philsmd e1ae2538c6 cosmetic fix: some fixed typos e.g. to -> too
9 years ago
philsmd 5e92020180 buffer overflow fix for -m 8900 = scrypt
9 years ago
Jens Steube a62b7ed06e Upgrade kernel to support dynamic local work sizes
9 years ago
Jens Steube 44b0cb4e65 Merge pull request #135 from gm4tr1x/master
9 years ago
jsteube e3c0c80b6f Prepare new SIMD code for kernel, -m 0, 10, 20, 1000 should work in -a 3 mode and other hopefully stay unaffected
9 years ago
Gabriele 'matrix' Gristina 29636ca0a3 Re-fix ascii_digest
9 years ago
Gabriele 'matrix' Gristina e9bc4caed3 Fixed a buffer overflow in ascii_digest for hash type 8300
9 years ago
Jens Steube 45431d9201 Fixed a buffer overflow in potfile handling
9 years ago
jsteube 471c10c4f7 Make sure to spawn threads for all devices, even skipped, and then instantly return
9 years ago
jsteube 954be23a12 Fix some code formating
9 years ago
Jens Steube b9c61eb66f Merge pull request #134 from yhfudev/add-cl-error-messages
9 years ago
jsteube 0524e78617 Enable forced JIT compilation for MD5, if requested
9 years ago
jsteube 09de56b720 Make sure to select an active device for weak_hash_check
9 years ago
Jens Steube 36251e1fe5 Merge pull request #132 from neheb/master
9 years ago
yhfudev edc6c920a9 human-readable error message for the OpenCL error codes.
9 years ago
jsteube 9fb506f15f Fixed out of bounds access in -m 11300
9 years ago
Mangix 54c7c23ad4 Remove some memsets
9 years ago
Jens Steube bc24e3d79b Add bitness to filename for cached kernels, otherwise a user would load a 32 bit kernel with a 64 bit host binary in case he used the 32 bit binary before which leads to a segfault
9 years ago
Jens Steube 98b1a9370c Fix AMD OpenCL runtime bug in clGetProgramInfo()
9 years ago
Jens Steube b35d2dd2eb Fix native compiler
9 years ago
Jens Steube 05505030b8 Fix CFLAGS
9 years ago
jsteube 5ae5a4bc25 Reorder device mapping
9 years ago
Jens Steube 63e06f582b Prepare fix for datatypes, not final
9 years ago
Jens Steube 2e61685f48 Fix outputting wrong password for weak-hash-check in case user defined -r or -g
9 years ago
Jens Steube ed91e69ae3 Fix out of bounds access in -m 7500
9 years ago
Jens Steube f3b85a6363 Fix some clang compiler warnings
9 years ago
jsteube 76612ac031 Fix more missing casts to uint in rule-engine
9 years ago
jsteube 497b41fee4 Fix more missing casts to uint
9 years ago
jsteube d3981ee66a Fix missing cast to uint
9 years ago
Jens Steube 7bfee268d4 Fixed some heap buffer overflow
9 years ago
Jens Steube 245301c9b4 Started optimizing some of the OpenCL kernel for latest AMD Catalyst 15.12:
9 years ago
Jens Steube 24b5aa6226 Merge pull request #128 from philsmd/pr-set-iter-for-dcc2
9 years ago
philsmd cbe6be9246 set default iteration count for -m 2100 = DCC2 to 10240
9 years ago
philsmd 88cbb45ca5 add skipped devices to the --benchmark output
9 years ago
philsmd 7b53ccab70 minor: remove quiet_sav, was just intended for debugging
9 years ago
Jens Steube 49d0767aa8 Run weak-hash checks only in straight-attack mode, this greatly reduces code complexity
9 years ago
Jens Steube cfff6220fc Fix -m 1500 in combination with new weak-hash-check
9 years ago
philsmd 4ed6b2c10a HMS: nvapi does not need a dll (windows + NV)
9 years ago
jsteube e7e6c4da17 Do not use OpenCL CPU devices by default to avoid slow GPU synchronization, user needs to explicitly enable them using --opencl-device-type
9 years ago
Jens Steube d3dc57896e Merge pull request #123 from philsmd/pr-tab-typo-fix
9 years ago
philsmd 182819af11 cosmetic: replace tab by spaces
9 years ago
philsmd 7081e3cdf6 Makefile: remove kernels/ directory when running make clean
9 years ago
Jens Steube 52d71de0d4 Added support to utilize multiple different OpenCL platforms in parallel, ex: AMD + NV
9 years ago
Jens Steube 0ff49c5b44 Fix segfault in related to weak-hash-check on CPU devices
9 years ago
Jens Steube 54ed58e28b Merge pull request #119 from philsmd/pr-fix-adl-mapping-CPU
9 years ago
philsmd b47452e343 HMS fix: only copy the ADL adapter info for GPU devices, for CPU devices we leave it AS-IS (zeroed out)
9 years ago
philsmd 2e1e3318ec fixed % and C (degrees celcius) in status display
9 years ago
Jens Steube 730044e26e Added option --opencl-device-types to filter for specific OpenCL device types
9 years ago
philsmd 02cecce247 fixed hardware monitor: mapping between supported ADL devices and available GPU (and CPUs) fixed
9 years ago
jsteube 93427c073c Prepare for some HSM updates related to device_type
9 years ago
Jens Steube 87dca98a51 Fix segfault if a weak hash is detected for some fast hashes
9 years ago
Jens Steube 1d628ca6e0 The weak-hash-check feature didn't work for algorithms that made use of some automatic optimizer flags
9 years ago
jsteube 3cdee2e06e We need an esalt to hold the unused IV otherwise the unique salt count becomes incorrect in multihash sitations
9 years ago
jsteube f0a84a2410 Added new hash mode -m 13000 = RAR5
9 years ago
jsteube 332b3c35e5 Added new hash mode -m 12900 = Android FDE (Samsung DEK)
9 years ago
jsteube e8229af09b Fix for -m 1500, -m 3000: Missing "defined" keyword
9 years ago
Jens Steube 6dab39e69c Merge pull request #64 from philsmd/master
9 years ago
philsmd 82ac8cbcfe additional --opencl-platform value check
9 years ago
philsmd 6fcc3f2728 typo
9 years ago
philsmd 7b7caf3842 added additional --opencl-platform check (reject numbers > number of OpenCL platforms)
9 years ago
jsteube 36df3ef329 A CPU is not a GPU
9 years ago