[AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_size

These two attributes specify the same info in a different way.
AMGPU BE only checks the latter as a target specific attribute
as opposed to language specific reqd_work_group_size.

This change produces amdgpu_flat_work_group_size out of
reqd_work_group_size if specified.

Differential Revision: https://reviews.llvm.org/D31728

llvm-svn: 299678

1 files changed, 8 insertions, 3 deletions

diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index fadbcea9b03..94c3880ea26 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -7302,9 +7302,14 @@ void AMDGPUTargetCodeGenInfo::setTargetAttributes(
 
   llvm::Function *F = cast<llvm::Function>(GV);
 
-  if (const auto *Attr = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>()) {
-    unsigned Min = Attr->getMin();
-    unsigned Max = Attr->getMax();
+  const auto *ReqdWGS = M.getLangOpts().OpenCL ?
+    FD->getAttr<ReqdWorkGroupSizeAttr>() : nullptr;
+  const auto *FlatWGS = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>();
+  if (ReqdWGS || FlatWGS) {
+    unsigned Min = FlatWGS ? FlatWGS->getMin() : 0;
+    unsigned Max = FlatWGS ? FlatWGS->getMax() : 0;
+    if (ReqdWGS && Min == 0 && Max == 0)
+      Min = Max = ReqdWGS->getXDim() * ReqdWGS->getYDim() * ReqdWGS->getZDim();
 
     if (Min != 0) {
       assert(Min <= Max && "Min must be less than or equal Max");