- 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

docs/changes.txt

@@ -1,5 +1,10 @@
 * changes v2.01 -> not-known-yet:
 
+Type.: Feature
+File.: Kernel
+Desc.: For NVidia, dropped CUDA support and switched to OpenCL
+Issue: 1
+
 Type.: Feature
 File.: Host
 Desc.: Implemented a new feature that allows to quit at next restore point update (and disable it)
@@ -10,10 +15,6 @@ File.: Host
 Desc.: Fixed a bug in combination of --restore and a user immediately aborting the session after restart
 Trac.: 684
 
-Type.: Change
-File.: Docs
-Desc.: Updated docs/readme.txt -- Starting with v2.01 OpenCL 2.00 is required; we need Catalyst 15.7 or higher
-
 * changes v2.00 -> v2.01:
 
 Type.: Bug

docs/readme.txt

@@ -2,7 +2,7 @@ oclHashcat v2.00
 ================
 
 NV users require ForceWare 346.59 or later
-AMD users require Catalyst 15.7 or later
+AMD users require Catalyst 14.9 or later
 
 ##
 ## Features