[PATCH] D80167: [mlir][gpu] Refactor ConvertGpuLaunchFuncToCudaCalls pass.

[Stephan Herhut via Phabricator via llvm-commits]

herhut added a comment.

As an alternative, we could stick with fixed names, replace the `mcu` prefix by something neutral and then for AMD use case we link a different helper library in the tests. WDYT?



================
Comment at: mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp:93
+  LLVM::LLVMType getGpuRuntimeResultType() {
     // This is declared as an enum in CUDA but helpers use i32.
     return getInt32Type();
----------------
There is a `CUDA` left-over here.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80167/new/

https://reviews.llvm.org/D80167