VLIW on NVidia Cuda
VLIW code for NVidia is only required for cheap sm_21 models. Basically Ti series cards < 9xx series, like the 560Ti. It is required to get out maximum performance for those cards. With newer cards you don't need this.

Basically this C++ classes just create code which generates code using the same instructions multiple times in a row but for different data sets. As you said, it's like SIMD.

Note that CUDA is getting replaced with OpenCL with oclHashcat v2.10.

Messages In This Thread
VLIW on NVidia Cuda - by AlexTeos - 01-12-2016, 03:32 PM
RE: VLIW on NVidia Cuda - by atom - 01-12-2016, 08:21 PM