[PATCH] D84260: [OpenMP][AMDGCN] Support OpenMP offloading for AMDGCN architecture - Part 3

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added inline comments.


================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeAMDGCN.h:30-31
+
+  /// Declare AMDGCN specific specialization of functions which
+  /// have been generalized as virtual functions in CGOpenMPRuntimeGPU
+
----------------
These 2 lines can be removed, they do not add anything useful.


================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.h:30-31
+
+  /// Declare NVPTX specific specialization of functions which
+  /// have been generalized as virtual functions in CGOpenMPRuntimeGPU
+
----------------
These 2 lines can be removed, they do not add anything useful.


================
Comment at: clang/test/OpenMP/amdgcn_target_codegen.cpp:19
+// CHECK-NEXT: sub nuw i32 [[VAR]], 64
+// CHECK-DAG: call i32 @llvm.amdgcn.workitem.id.x()
+#pragma omp target
----------------
Remove `DAG`


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D84260/new/

https://reviews.llvm.org/D84260