Page MenuHomePhabricator

[mlir][vulkan-runner] Simplify vulkan launch call op.
ClosedPublic

Authored by denis13 on Apr 16 2020, 9:26 AM.

Details

Summary

Workgroup size is written into the kernel. So to properly modelling
vulkan launch, we have to skip local workgroup size for vulkan launch
call op.

Diff Detail

Event Timeline

denis13 created this revision.Apr 16 2020, 9:26 AM
Herald added a project: Restricted Project. · View Herald Transcript
mravishankar accepted this revision.Apr 16 2020, 10:25 AM
mravishankar added inline comments.
mlir/lib/Conversion/GPUToVulkan/ConvertGPULaunchFuncToVulkanLaunchFunc.cpp
107

Super Nit : I think this usage is different from the comment on what kVulkanLaunchNumConfigOperands says. The comment implies, off the argument list to the vulkan call how many of the arguments relate to configuration. Here it is used in the context that the first 3 arguments of the arguments to the gpu.launch_func are needed for the vulkan launch. Had to read this a couple of times to understand. Maybe just add a comment that says that the first kVulkanLaunchNumConfigOperands of the gpu.launch_func op are the same as the config operands for the vulkan call.

This revision is now accepted and ready to land.Apr 16 2020, 10:25 AM
denis13 marked an inline comment as done.Apr 16 2020, 1:30 PM
denis13 added inline comments.
mlir/lib/Conversion/GPUToVulkan/ConvertGPULaunchFuncToVulkanLaunchFunc.cpp
107

Thanks for review! Sure, will fix it!

This revision was automatically updated to reflect the committed changes.