Age | Commit message (Expand) | Author |
---|---|---|
2017-08-21 | Remove multistrategy and related functions | mcian |
2017-07-23 | Code refactoring | mcian |
2017-04-22 | Increased the default number of runs for the tuner from 2 up to 10 for fast k... | Cedric Nugteren |
2017-04-17 | Fixed a namespace clash with CUDA FP16 for the half-datatype | Cedric Nugteren |
2017-03-14 | Added the possibility to tune batched kernels | Cedric Nugteren |
2016-11-27 | Made it possible to use the command-line environmental variables for each exe... | Cedric Nugteren |
2016-10-22 | Moved files around a bit; created a utilities subfolder | Cedric Nugteren |
2016-10-02 | Set the default number of runs for all kernels to at least 2 runs | Cedric Nugteren |
2016-10-01 | Added default num-runs to the tuner adding averaging over 10 runs as a defaul... | Cedric Nugteren |
2016-07-10 | Now passing alpha/beta to the kernel as arguments as before fp16 support; in ... | Cedric Nugteren |
2016-06-19 | Renamed all C++ source files to .cpp to match the .hpp extension better | Cedric Nugteren |