[OpenMP][Clang] Add call to global data sharing stack initialization on the workers side

Summary: The workers also need to initialize the global stack. The call to the initialization function needs to happen after the kernel_init() function is called by the master. This ensures that the per-team data structures of the runtime have been initialized.

Reviewers: ABataev, grokos, carlo.bertolli, caomhin

Reviewed By: ABataev

Subscribers: jholewinski, guansong, cfe-commits

Differential Revision: https://reviews.llvm.org/D44749

llvm-svn: 328219

2 files changed, 10 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
index 8ab890cb4c3..62131cd0243 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -801,6 +801,11 @@ void CGOpenMPRuntimeNVPTX::emitWorkerLoop(CodeGenFunction &CGF,
   // Wait for parallel work
   syncCTAThreads(CGF);
 
+  // For data sharing, we need to initialize the stack for workers.
+  CGF.EmitRuntimeCall(
+      createNVPTXRuntimeFunction(
+          OMPRTL_NVPTX__kmpc_data_sharing_init_stack));
+
   Address WorkFn =
       CGF.CreateDefaultAlignTempAlloca(CGF.Int8PtrTy, /*Name=*/"work_fn");
   Address ExecStatus =
diff --git a/clang/test/OpenMP/nvptx_data_sharing.cpp b/clang/test/OpenMP/nvptx_data_sharing.cpp
index 26ab3c0201b..68245c9abae 100644
--- a/clang/test/OpenMP/nvptx_data_sharing.cpp
+++ b/clang/test/OpenMP/nvptx_data_sharing.cpp
@@ -27,6 +27,11 @@ void test_ds(){
   }
 }
 
+/// ========= In the worker function ========= ///
+// CK1: {{.*}}define internal void @__omp_offloading{{.*}}test_ds{{.*}}_worker()
+// CK1: call void @llvm.nvvm.barrier0()
+// CK1: call void @__kmpc_data_sharing_init_stack
+
 /// ========= In the kernel function ========= ///
 
 // CK1: {{.*}}define void @__omp_offloading{{.*}}test_ds{{.*}}()