[OPENMP 4.1] Codegen for ‘simd’ clause in ‘ordered’ directive.
Description.
If the simd clause is specified, the ordered regions encountered by any thread will use only a single SIMD lane to execute the ordered regions in the order of the loop iterations.
Restrictions.
An ordered construct with the simd clause is the only OpenMP construct that can appear in the simd region.
An ordered directive with ‘simd’ clause is generated as an outlined function and corresponding function call to prevent this part of code from vectorization later in backend.
llvm-svn: 248772
diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index a06b0a2..45fa610 100644
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -1799,13 +1799,33 @@
}(), S.getLocStart());
}
+static llvm::Function *emitOutlinedOrderedFunction(CodeGenModule &CGM,
+ const CapturedStmt *S) {
+ CodeGenFunction CGF(CGM, /*suppressNewContext=*/true);
+ CodeGenFunction::CGCapturedStmtInfo CapStmtInfo;
+ CGF.CapturedStmtInfo = &CapStmtInfo;
+ auto *Fn = CGF.GenerateOpenMPCapturedStmtFunction(*S);
+ Fn->addFnAttr(llvm::Attribute::NoInline);
+ return Fn;
+}
+
void CodeGenFunction::EmitOMPOrderedDirective(const OMPOrderedDirective &S) {
LexicalScope Scope(*this, S.getSourceRange());
- auto &&CodeGen = [&S](CodeGenFunction &CGF) {
- CGF.EmitStmt(cast<CapturedStmt>(S.getAssociatedStmt())->getCapturedStmt());
+ auto *C = S.getSingleClause<OMPSIMDClause>();
+ auto &&CodeGen = [&S, C, this](CodeGenFunction &CGF) {
+ if (C) {
+ auto CS = cast<CapturedStmt>(S.getAssociatedStmt());
+ llvm::SmallVector<llvm::Value *, 16> CapturedVars;
+ CGF.GenerateOpenMPCapturedVars(*CS, CapturedVars);
+ auto *OutlinedFn = emitOutlinedOrderedFunction(CGM, CS);
+ CGF.EmitNounwindRuntimeCall(OutlinedFn, CapturedVars);
+ } else {
+ CGF.EmitStmt(
+ cast<CapturedStmt>(S.getAssociatedStmt())->getCapturedStmt());
+ }
CGF.EnsureInsertPoint();
};
- CGM.getOpenMPRuntime().emitOrderedRegion(*this, CodeGen, S.getLocStart());
+ CGM.getOpenMPRuntime().emitOrderedRegion(*this, CodeGen, S.getLocStart(), !C);
}
static llvm::Value *convertToScalarValue(CodeGenFunction &CGF, RValue Val,