[all-commits] [llvm/llvm-project] a48f0a: [mlir][vulkan-runner] Simplify vulkan launch call op.

[Denis Khalikov via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: a48f0a3c7e9f0f389b6fa35117ae51f1367973f9
      https://github.com/llvm/llvm-project/commit/a48f0a3c7e9f0f389b6fa35117ae51f1367973f9
  Author: Denis Khalikov <khalikov.denis at huawei.com>
  Date:   2020-04-18 (Sat, 18 Apr 2020)

  Changed paths:
    M mlir/lib/Conversion/GPUToVulkan/ConvertGPULaunchFuncToVulkanLaunchFunc.cpp
    M mlir/lib/Conversion/GPUToVulkan/ConvertLaunchFuncToVulkanCalls.cpp
    M mlir/test/Conversion/GPUToVulkan/invoke-vulkan.mlir
    M mlir/test/Conversion/GPUToVulkan/lower-gpu-launch-vulkan-launch.mlir

  Log Message:
  -----------
  [mlir][vulkan-runner] Simplify vulkan launch call op.

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.

Differential Revision: https://reviews.llvm.org/D78307