[OPENMP][NVPTX]Mark __kmpc_barrier functions as convergent.
__kmpc_barrier runtime functions must be marked as convergent to prevent
some dangerous optimizations. Also, for NVPTX target all barriers must
be emitted as simple barriers.
llvm-svn: 348271
diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.cpp b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
index cade093..66f0783 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -3214,13 +3214,7 @@
emitInlinedDirective(CGF, OMPD_ordered, OrderedOpGen);
}
-void CGOpenMPRuntime::emitBarrierCall(CodeGenFunction &CGF, SourceLocation Loc,
- OpenMPDirectiveKind Kind, bool EmitChecks,
- bool ForceSimpleCall) {
- if (!CGF.HaveInsertPoint())
- return;
- // Build call __kmpc_cancel_barrier(loc, thread_id);
- // Build call __kmpc_barrier(loc, thread_id);
+unsigned CGOpenMPRuntime::getDefaultFlagsForBarriers(OpenMPDirectiveKind Kind) {
unsigned Flags;
if (Kind == OMPD_for)
Flags = OMP_IDENT_BARRIER_IMPL_FOR;
@@ -3232,6 +3226,17 @@
Flags = OMP_IDENT_BARRIER_EXPL;
else
Flags = OMP_IDENT_BARRIER_IMPL;
+ return Flags;
+}
+
+void CGOpenMPRuntime::emitBarrierCall(CodeGenFunction &CGF, SourceLocation Loc,
+ OpenMPDirectiveKind Kind, bool EmitChecks,
+ bool ForceSimpleCall) {
+ if (!CGF.HaveInsertPoint())
+ return;
+ // Build call __kmpc_cancel_barrier(loc, thread_id);
+ // Build call __kmpc_barrier(loc, thread_id);
+ unsigned Flags = getDefaultFlagsForBarriers(Kind);
// Build call __kmpc_cancel_barrier(loc, thread_id) or __kmpc_barrier(loc,
// thread_id);
llvm::Value *Args[] = {emitUpdateLocation(CGF, Loc, Flags),
diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.h b/clang/lib/CodeGen/CGOpenMPRuntime.h
index d332623..f4a8a97 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.h
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.h
@@ -290,6 +290,10 @@
/// default location.
virtual unsigned getDefaultLocationReserved2Flags() const { return 0; }
+ /// Returns default flags for the barriers depending on the directive, for
+ /// which this barier is going to be emitted.
+ static unsigned getDefaultFlagsForBarriers(OpenMPDirectiveKind Kind);
+
/// Get the LLVM type for the critical name.
llvm::ArrayType *getKmpCriticalNameTy() const {return KmpCriticalNameTy;}
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
index 2bc98f6..cf814a4 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -96,6 +96,8 @@
OMPRTL_NVPTX__kmpc_get_team_static_memory,
/// Call to void __kmpc_restore_team_static_memory(int16_t is_shared);
OMPRTL_NVPTX__kmpc_restore_team_static_memory,
+ // Call to void __kmpc_barrier(ident_t *loc, kmp_int32 global_tid);
+ OMPRTL__kmpc_barrier,
};
/// Pre(post)-action for different OpenMP constructs specialized for NVPTX.
@@ -1824,6 +1826,15 @@
CGM.CreateRuntimeFunction(FnTy, "__kmpc_restore_team_static_memory");
break;
}
+ case OMPRTL__kmpc_barrier: {
+ // Build void __kmpc_barrier(ident_t *loc, kmp_int32 global_tid);
+ llvm::Type *TypeParams[] = {getIdentTyPointerTy(), CGM.Int32Ty};
+ auto *FnTy =
+ llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
+ RTLFn = CGM.CreateRuntimeFunction(FnTy, /*Name*/ "__kmpc_barrier");
+ cast<llvm::Function>(RTLFn)->addFnAttr(llvm::Attribute::Convergent);
+ break;
+ }
}
return RTLFn;
}
@@ -2676,6 +2687,20 @@
}
}
+void CGOpenMPRuntimeNVPTX::emitBarrierCall(CodeGenFunction &CGF,
+ SourceLocation Loc,
+ OpenMPDirectiveKind Kind, bool,
+ bool) {
+ // Always emit simple barriers!
+ if (!CGF.HaveInsertPoint())
+ return;
+ // Build call __kmpc_cancel_barrier(loc, thread_id);
+ unsigned Flags = getDefaultFlagsForBarriers(Kind);
+ llvm::Value *Args[] = {emitUpdateLocation(CGF, Loc, Flags),
+ getThreadID(CGF, Loc)};
+ CGF.EmitRuntimeCall(createNVPTXRuntimeFunction(OMPRTL__kmpc_barrier), Args);
+}
+
void CGOpenMPRuntimeNVPTX::emitCriticalRegion(
CodeGenFunction &CGF, StringRef CriticalName,
const RegionCodeGenTy &CriticalOpGen, SourceLocation Loc,
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.h b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
index 8ba2759..8fb3b0a 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
@@ -274,6 +274,18 @@
ArrayRef<llvm::Value *> CapturedVars,
const Expr *IfCond) override;
+ /// Emit an implicit/explicit barrier for OpenMP threads.
+ /// \param Kind Directive for which this implicit barrier call must be
+ /// generated. Must be OMPD_barrier for explicit barrier generation.
+ /// \param EmitChecks true if need to emit checks for cancellation barriers.
+ /// \param ForceSimpleCall true simple barrier call must be emitted, false if
+ /// runtime class decides which one to emit (simple or with cancellation
+ /// checks).
+ ///
+ void emitBarrierCall(CodeGenFunction &CGF, SourceLocation Loc,
+ OpenMPDirectiveKind Kind, bool EmitChecks = true,
+ bool ForceSimpleCall = false) override;
+
/// Emits a critical region.
/// \param CriticalName Name of the critical region.
/// \param CriticalOpGen Generator for the statement associated with the given