diff options
| author | Guray Ozen <guray.ozen@gmail.com> | 2023-07-20 13:56:11 +0200 |
|---|---|---|
| committer | Guray Ozen <guray.ozen@gmail.com> | 2023-07-21 10:23:25 +0200 |
| commit | 70c2e0618a0f3c09ed7149d88b4987b932eb6705 (patch) | |
| tree | 361f0f70a7991acd1b3288d8fa4ce9ba1894343d /lldb/source/Plugins/ScriptInterpreter/Python/ScriptInterpreterPython.cpp | |
| parent | 2469cdd156c5290c087116a2b5eaf99f9ef12f09 (diff) | |
[mlir][nvgpu] Add nvgpu.tma.async.load and nvgpu.tma.descriptor
This work adds `nvgpu.tma.async.load` Op that requests tma load asyncronusly using mbarrier object.
It also creates nvgpu.tma.descriptor type. The type is supposed be created by `cuTensorMapEncodeTiled` cuda drivers api.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D155453
Diffstat (limited to 'lldb/source/Plugins/ScriptInterpreter/Python/ScriptInterpreterPython.cpp')
0 files changed, 0 insertions, 0 deletions