41 Commits (07f119c28b464907beb5e94ac3c44c3991821f13)

Author	SHA1	Message	Date
jsteube	e4e1c1d515	We can't mix inline functions with static constants	6 years ago
jsteube	3e08750900	OpenCL Kernels: Add general function declaration keyword (static inline)	6 years ago
jsteube	53f3da9f63	OpenCL Kernels: Use static declaraction for uXXa variables used in __constant space	7 years ago
jsteube	1aa76eac15	Refactor use of __constant to match up with the user selected attack mode	7 years ago
jsteube	1d04de3a8e	Limit kernel-loops in straight-mode to 256, therefore allow rules to be stored in constant memory	7 years ago
jsteube	319799bbbf	Switch the datatypes of the variables responsible for work-item count and work-item size from u32 to u64	7 years ago
jsteube	2802f1d592	Fix vector function calls and datatypes	7 years ago
jsteube	50aeade65c	Add pure kernels for NetNTLMv1 / NetNTLMv1+ESS	7 years ago
jsteube	beb6ee2061	Add OPTI_TYPE_OPTIMIZED_KERNEL ... Rename unconverted fast hash kernels to optimized kernels Finalize some converted fast hashes to default kernels	7 years ago
jsteube	c918173fcf	Get rid of comb_t which can be safely replace with pw_t now	7 years ago
jsteube	b8ad89c529	Rename function and variables containing 'unicode' to 'utf16le' because that's what's meant actually	7 years ago
jsteube	2ece9742e1	Compress multiple newlines to one	7 years ago
jsteube	d0fa9d059d	Remove some unused macros	7 years ago
jsteube	6401c58568	Align all the __constant buffers to workaround OpenCL JIT compiler errors in NV drivers 378.x	7 years ago
jsteube	bbb4c74e85	OpenCL Kernel: Remove "static" keyword from function declarations; Causes older Intel OpenCL runtimes to fail compiling	7 years ago
Gabriele Gristina	ce6c07ec1d	Fix kernel build warnings (no previous prototypes and/or incompatible function parameters ...	8 years ago
Jens Steube	7fe575e204	Add const qualifier to variable declaration of matching global memory objects	8 years ago
jsteube	3daf0af480	Added docs/credits.txt ... Added docs/team.txt	8 years ago
jsteube	8702d0e3e1	Workaround memory allocation limit from OpenCL by using multiple buffers for scrypt	8 years ago
Jens Steube	ed1863c263	Move macros DGST_R0 - DGST_R3 to host, define dgst_size for opencl kernel from host; both at runtime	8 years ago
Jens Steube	2899f53a15	Move files from include/ to OpenCL/ if they are used within kernels ... Rename includes in OpenCL so that it's easier to recognize them as such	8 years ago
jsteube	c79bed3b7d	Prepare for a more dynamic #pragma unroll use	8 years ago
Jens Steube	0b3743ce94	- Added inline declaration to functions from simd.c, common.c, rp.c and types_ocl.c to increase performance ... - Dropped static declaration from functions in all kernel to achieve OpenCL 1.1 compatibility - Added -cl-std=CL1.1 to all kernel build options - Created environment variable to inform NVidia OpenCL runtime to not create its own kernel cache - Created environment variable to inform pocl OpenCL runtime to not create its own kernel cache	8 years ago
Jens Steube	d6e5f7e829	Cleanup -m 55xx kernels to latest standard	8 years ago
jsteube	dad03e394d	Fixed two major problems ... 1) SIMD code for all attack-mode Macro vector_accessible() was not refactored and missing completely. Had to rename variables rules_cnt, combs_cnt and bfs_cnt into il_cnt which was a good thing anyway as with new SIMD code they all act in the same way. 2) SIMD code for attack-mode 0 With new SIMD code, apply_rules_vect() has to return u32 not u32x. This has massive impact on all *_a0 kernels. I've rewritten most of them. Deep testing using test.sh is still required. Some kernel need more fixes: - Some are kind of completely incompatible like m10400 but they still use old check_* includes, we should get rid of them as they are no longer neccessary as we have simd.c - Some have a chance but require additional effort like m11500. We can use commented out "#define NEW_SIMD_CODE" to find them This change can have negative impact on -a0 performance for device that require vectorization. That is mostly CPU devices. New GPU's are all scalar, so they wont get hurt by this. This change also proofes that there's no way to efficiently vectorize kernel rules with new SIMD code, but it enables the addition of the rule functions like @ that we were missing for some long time. This is a TODO.	8 years ago
Jens Steube	e6e5005a6b	Revert "Zero pws_buf before reuse" ... This reverts commit b409e5e9e1.	8 years ago
Jens Steube	b409e5e9e1	Zero pws_buf before reuse	8 years ago
jsteube	19b9455c42	Workaround JIT-compiler or ForceWare Bug in sm_50	9 years ago
Gabriele 'matrix' Gristina	0f0984fe86	Fixed all gpu code (see PR #179 for details)	9 years ago
Jens Steube	1d3795a3ab	Converted _a3 kernels, use SIMD for CPU and GPU	9 years ago
Jens Steube	a62b7ed06e	Upgrade kernel to support dynamic local work sizes	9 years ago
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	9 years ago
jsteube	331188167c	Replace the substring GPU to a more appropriate "device" or "kernel" substring depending on the context	9 years ago
jsteube	5f7c47b461	Fix path to includes	9 years ago
jsteube	f3a394b85d	Workaround buggy NV OpenCL runtime	9 years ago
jsteube	0522ca9cbe	Revert "Workaround buggy NV OpenCL runtime" ... This reverts commit 90eba9cd2e.	9 years ago
jsteube	90eba9cd2e	Workaround buggy NV OpenCL runtime	9 years ago
jsteube	aedc142d0b	fix -m 5500	9 years ago
jsteube	76cc1631be	More kernel fixes for function calls and vector datatypes	9 years ago
jsteube	50f39b3563	Fix append_* function calls	9 years ago
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	9 years ago