[PATCH] D124189: [CUDA][HIP] Externalize kernels with internal linkage

[Yaxun Liu via Phabricator via cfe-commits]

yaxunl marked 7 inline comments as done.
yaxunl added inline comments.


================
Comment at: clang/test/CodeGenCUDA/device-var-linkage.cu:1-2
 // RUN: %clang_cc1 -no-opaque-pointers -triple nvptx -fcuda-is-device \
 // RUN:   -emit-llvm -o - -x hip %s \
 // RUN:   | FileCheck -check-prefixes=DEV,NORDC %s
----------------
tra wrote:
> This is odd -- the tests use `-x hip` and  `-triple nvptx`.
> 
> I think we need to change them  into HIP+amdgpu and CUDA +nvptx variants ans we now have language-dependent behavior here and are interested in the language/triple combinations that we do use in practice.
will change them to amdgcn and add CUDA variant when committing.


================
Comment at: clang/test/CodeGenCUDA/kernel-in-anon-ns.cu:3
 // RUN:   -aux-triple x86_64-unknown-linux-gnu -std=c++11 -fgpu-rdc \
 // RUN:   -emit-llvm -o - -x hip %s > %t.dev
 
----------------
tra wrote:
> We should have CUDA test variants here, too.
will add CUDA test when committing.


================
Comment at: clang/test/CodeGenCUDA/managed-var.cu:1
 // REQUIRES: x86-registered-target, amdgpu-registered-target
 
----------------
tra wrote:
> Tests above do not have REQUIRED. Is it needed here?
> 
No. I will remove it when committing.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124189/new/

https://reviews.llvm.org/D124189