commit 1bea97c971d60f261f1bdfaa7b6d9cb30a6962fd
author Yaxun Liu <Yaxun.Liu@amd.com> Tue Sep 03 18:50:24 2019 +0000
committer Yaxun Liu <Yaxun.Liu@amd.com> Tue Sep 03 18:50:24 2019 +0000
tree 6ebff5f97e28459a528341b0ec311cec51a1bc47
parent 0581a44e02e4d7170d3205d6109e84b101cbb71a

[AMDGPU] Set default flat work group size to (1,256) for HIP

Differential Revision: https://reviews.llvm.org/D67048

llvm-svn: 370808

clang/lib/CodeGen/TargetInfo.cpp

diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index 231a20c..760895a 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -7915,8 +7915,9 @@
 
   const bool IsOpenCLKernel = M.getLangOpts().OpenCL &&
                               FD->hasAttr<OpenCLKernelAttr>();
-  if ((IsOpenCLKernel ||
-       (M.getLangOpts().HIP && FD->hasAttr<CUDAGlobalAttr>())) &&
+  const bool IsHIPKernel = M.getLangOpts().HIP &&
+                           FD->hasAttr<CUDAGlobalAttr>();
+  if ((IsOpenCLKernel || IsHIPKernel) &&
       (M.getTriple().getOS() == llvm::Triple::AMDHSA))
     F->addFnAttr("amdgpu-implicitarg-num-bytes", "56");
 
@@ -7942,7 +7943,7 @@
       F->addFnAttr("amdgpu-flat-work-group-size", AttrVal);
     } else
       assert(Max == 0 && "Max must be zero");
-  } else if (IsOpenCLKernel) {
+  } else if (IsOpenCLKernel || IsHIPKernel) {
     // By default, restrict the maximum size to 256.
     F->addFnAttr("amdgpu-flat-work-group-size", "1,256");
   }