| commit | dee2ffc7a0c6415accd8afb25af2e1f562ba2d83 | |
| author | Aleksei Iupinov <a.yupinov@gmail.com> | |
| Mon, 21 May 2018 08:40:08 +0000 (21 10:40 +0200) | ||
| committer | Mark Abraham <mark.j.abraham@gmail.com> | |
| Mon, 30 Jul 2018 15:53:16 +0000 (30 17:53 +0200) | ||
| tree | 0d311199922ae07da796b9ce99fbbef1759ae087 | treesnapshot (tar.gz zip) |
| parent | d805669dd4e9756456bcc437991e7c1702c7e622 | commitdiff |
Remove hardcoded warp_size == 32 assumption from PME GPU
The PME OpenCL host code now queries the warp_size aka max
execution width from the device. The CUDA/unit test handling
of constants/defines is adjusted. With this, only the PME
device-side code should be relying on warp_size define
(which will be passed to the compiler in the OpenCL
implementation).
Change-Id: Ic2d1512e04d36861590b13e02b5bd7a87240f9e2
The PME OpenCL host code now queries the warp_size aka max
execution width from the device. The CUDA/unit test handling
of constants/defines is adjusted. With this, only the PME
device-side code should be relying on warp_size define
(which will be passed to the compiler in the OpenCL
implementation).
Change-Id: Ic2d1512e04d36861590b13e02b5bd7a87240f9e2
14 files changed: