8 Commits

Author	SHA1	Message	Date
jsteube	7be2c2fd8d	Fixed some speeds: ... 1800 3200 7100 7200 7400 8200 9300 9000 9600 11300 11600	2015-12-21 14:29:04 +01:00
jsteube	9115547601	Revert "Fix -m 10700" ... This reverts commit 15da53da38.	2015-12-19 18:18:28 +01:00
jsteube	15da53da38	Fix -m 10700	2015-12-19 18:17:19 +01:00
jsteube	91249942ab	Fix -m 1800 for NV	2015-12-17 19:19:31 +01:00
jsteube	9c392b472e	Removed useless comments	2015-12-16 11:18:57 +01:00
jsteube	c29c7c093f	Fix use of LOP3	2015-12-16 11:11:31 +01:00
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	2015-12-15 12:04:22 +01:00
Jens Steube	5065474b4e	Initial commit	2015-12-04 15:47:52 +01:00