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
// 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 =
}
}
+/// ========= 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{{.*}}()