commit 68e11a6ecac7a37a5772d8c5c9c56c19614fc7f0
author Tony Tye <Tony.Tye@amd.com> Fri Mar 23 18:51:45 2018 +0000
committer Tony Tye <Tony.Tye@amd.com> Fri Mar 23 18:51:45 2018 +0000
tree df920ecf6634b45a3142222ab72dcf713682c4e3
parent 7a893d4e34e7261368c58ad583dfaa600108b7e1

[AMDGPU] Update OpenCL to use 48 bytes of implicit arguments for AMDGPU (CLANG)

Add two additional implicit arguments for OpenCL for the AMDGPU target using the AMDHSA runtime to support device enqueue.

Differential Revision: https://reviews.llvm.org/D44696

llvm-svn: 328350

clang/lib/CodeGen/TargetInfo.cpp

diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index 435565d..466253c 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -7664,7 +7664,7 @@
 
   if (M.getLangOpts().OpenCL && FD->hasAttr<OpenCLKernelAttr>() &&
       (M.getTriple().getOS() == llvm::Triple::AMDHSA))
-    F->addFnAttr("amdgpu-implicitarg-num-bytes", "32");
+    F->addFnAttr("amdgpu-implicitarg-num-bytes", "48");
 
   const auto *FlatWGS = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>();
   if (ReqdWGS || FlatWGS) {