Wayne Franz
Wayne Franz
@stanleytsang-amd - I've fixed up the merge conflicts. Sorry for the delay on this. In conflict cases where there were two different values for the same architecture, I've preferred StreamHPC's...
The PTS reports indicate a sobol32 regression of slightly less than -5% here for the uniform_double distribution. sobol32 is actually not a part of the config tuning process yet, so...
Added missing newlines at the ends of two of the config files.
I'm currently looking into the test failures on gfx1030, but if you'd like to have a look and leave some comments in the meantime, please feel free.
I believe I've finally ironed out all the issues on gfx1030 now, but we'll have to wait and see if the checks pass.
@nolmoonen Those are really good points, thank you. Here are a few thoughts in response: > It makes more sense to force initialization and keep the generator state alive. Is...
I've completed the requested changes.
Hi @yxsamliu, thanks for the information. I've created a pull request with the requested change [here](https://github.com/ROCm/hipCUB/pull/344).