Hi doug.gregor, hfinkel, rjmccall, rsmith, fraggamuffin, ejstotzer,
This patch generates call to "__kmpc_push_num_threads(ident_t *loc, kmp_int32
global_tid, kmp_int32 num_threads);" library function before calling
"__kmpc_fork_call" each time there is an associated "num_threads" clause in the
"omp parallel" directive.
http://reviews.llvm.org/D5145
Files:
include/clang/AST/StmtOpenMP.h
lib/AST/Stmt.cpp
lib/CodeGen/CGOpenMPRuntime.cpp
lib/CodeGen/CGOpenMPRuntime.h
lib/CodeGen/CGStmtOpenMP.cpp
lib/Sema/SemaOpenMP.cpp
test/OpenMP/parallel_num_threads_codegen.cpp
Index: test/OpenMP/parallel_num_threads_codegen.cpp
===================================================================
--- test/OpenMP/parallel_num_threads_codegen.cpp
+++ test/OpenMP/parallel_num_threads_codegen.cpp
@@ -0,0 +1,84 @@
+// RUN: %clang_cc1 -verify -fopenmp=libiomp5 -x c++ -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp=libiomp5 -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp=libiomp5 -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+typedef __INTPTR_TYPE__ intptr_t;
+
+// CHECK-DAG: [[IDENT_T_TY:%.+]] = type { i32, i32, i32, i32, i8* }
+// CHECK-DAG: [[S_TY:%.+]] = type { [[INTPTR_T_TY:i[0-9]+]], [[INTPTR_T_TY]], [[INTPTR_T_TY]] }
+// CHECK-DAG: [[STR:@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
+// CHECK-DAG: [[DEF_LOC_2:@.+]] = private unnamed_addr constant [[IDENT_T_TY]] { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8]* [[STR]], i32 0, i32 0) }
+
+void foo();
+
+struct S {
+ intptr_t a, b, c;
+ S(intptr_t a) : a(a) {}
+ operator char() { return a; }
+ ~S() {}
+};
+
+template <typename T, int C>
+int tmain() {
+#pragma omp parallel num_threads(C)
+ foo();
+#pragma omp parallel num_threads(T(23))
+ foo();
+ return 0;
+}
+
+int main() {
+ S s(0);
+ char a = s;
+#pragma omp parallel num_threads(2)
+ foo();
+#pragma omp parallel num_threads(a)
+ foo();
+ return a + tmain<char, 5>() + tmain<S, 1>();
+}
+
+// CHECK: define [[INT_TY:i[0-9]+]] @main(
+// CHECK-DAG: [[S_ADDR:%.+]] = alloca [[S_TY]]
+// CHECK-DAG: [[A_ADDR:%.+]] = alloca i8
+// CHECK-DAG: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEF_LOC_2]])
+// CHECK-DAG: call void [[S_TY_CONSTR:@.+]]([[S_TY]]* [[S_ADDR]], [[INTPTR_T_TY]] 0)
+// CHECK: [[S_CHAR_OP:%.+]] = invoke{{.*}} i8 [[S_TY_CHAR_OP:@.+]]([[S_TY]]* [[S_ADDR]])
+// CHECK: store i8 [[S_CHAR_OP]], i8* [[A_ADDR]]
+// CHECK: call void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID]], i32 2)
+// CHECK: call void {{.*}}* @__kmpc_fork_call(
+// CHECK: [[A_VAL:%.+]] = load i8* [[A_ADDR]]
+// CHECK: [[RES:%.+]] = sext i8 [[A_VAL]] to i32
+// CHECK: call void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID]], i32 [[RES]])
+// CHECK: call void {{.*}}* @__kmpc_fork_call(
+// CHECK: invoke [[INT_TY]] [[TMAIN_CHAR_5:@.+]]()
+// CHECK: invoke [[INT_TY]] [[TMAIN_S_1:@.+]]()
+// CHECK: call void [[S_TY_DESTR:@.+]]([[S_TY]]* [[S_ADDR]])
+// CHECK: ret [[INT_TY]]
+// CHECK: }
+
+// CHECK: define{{.*}} [[INT_TY]] [[TMAIN_CHAR_5]]()
+// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEF_LOC_2]])
+// CHECK: call void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID]], i32 5)
+// CHECK: call void {{.*}}* @__kmpc_fork_call(
+// CHECK: call void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID]], i32 23)
+// CHECK: call void {{.*}}* @__kmpc_fork_call(
+// CHECK: ret [[INT_TY]] 0
+// CHECK-NEXT: }
+
+// CHECK: define{{.*}} [[INT_TY]] [[TMAIN_S_1]]()
+// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEF_LOC_2]])
+// CHECK: call void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID]], i32 1)
+// CHECK: call void {{.*}}* @__kmpc_fork_call(
+// CHECK: call void [[S_TY_CONSTR]]([[S_TY]]* [[S_TEMP:%.+]], [[INTPTR_T_TY]] 23)
+// CHECK: [[S_CHAR_OP:%.+]] = invoke{{.*}} i8 [[S_TY_CHAR_OP]]([[S_TY]]* [[S_TEMP]])
+// CHECK: [[RES:%.+]] = sext i8 [[S_CHAR_OP]] to i32
+// CHECK: call void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID]], i32 [[RES]])
+// CHECK: call void [[S_TY_DESTR]]([[S_TY]]* [[S_TEMP]])
+// CHECK: call void {{.*}}* @__kmpc_fork_call(
+// CHECK: ret [[INT_TY]] 0
+// CHECK: }
+
+#endif
Index: include/clang/AST/StmtOpenMP.h
===================================================================
--- include/clang/AST/StmtOpenMP.h
+++ include/clang/AST/StmtOpenMP.h
@@ -128,6 +128,10 @@
operator bool() { return Current != End; }
};
+ /// \brief Gets single clause of the specified kind \a K associated with the
+ /// current directive iff there is only one clause of this kind.
+ const OMPClause *getSingleClause(OpenMPClauseKind K) const;
+
/// \brief Returns starting location of directive kind.
SourceLocation getLocStart() const { return StartLoc; }
/// \brief Returns ending location of directive.
Index: lib/Sema/SemaOpenMP.cpp
===================================================================
--- lib/Sema/SemaOpenMP.cpp
+++ lib/Sema/SemaOpenMP.cpp
@@ -2609,6 +2609,11 @@
<< "num_threads" << NumThreads->getSourceRange();
return nullptr;
}
+ // Convert to int32 for runtime call.
+ ValExpr = PerformImplicitConversion(
+ ValExpr,
+ Context.getIntTypeForBitwidth(/*DestWidth*/ 32, /*Signed*/ true),
+ /*Action*/ AA_Casting).get();
}
return new (Context)
Index: lib/AST/Stmt.cpp
===================================================================
--- lib/AST/Stmt.cpp
+++ lib/AST/Stmt.cpp
@@ -1384,12 +1384,24 @@
return new (Mem) OMPFlushClause(N);
}
+const OMPClause *
+OMPExecutableDirective::getSingleClause(OpenMPClauseKind K) const {
+ auto ClauseFilter =
+ [=](const OMPClause *C) -> bool { return C->getClauseKind() == K; };
+ OMPExecutableDirective::filtered_clause_iterator<decltype(ClauseFilter)> I(
+ clauses(), ClauseFilter);
+
+ if (I) {
+ auto PrevI = I;
+ assert(!++I && "There is at least 2 clauses of the specified kind");
+ return *PrevI;
+ }
+ return nullptr;
+}
+
OMPParallelDirective *OMPParallelDirective::Create(
- const ASTContext &C,
- SourceLocation StartLoc,
- SourceLocation EndLoc,
- ArrayRef<OMPClause *> Clauses,
- Stmt *AssociatedStmt) {
+ const ASTContext &C, SourceLocation StartLoc, SourceLocation EndLoc,
+ ArrayRef<OMPClause *> Clauses, Stmt *AssociatedStmt) {
unsigned Size = llvm::RoundUpToAlignment(sizeof(OMPParallelDirective),
llvm::alignOf<OMPClause *>());
void *Mem = C.Allocate(Size + sizeof(OMPClause *) * Clauses.size() +
Index: lib/CodeGen/CGOpenMPRuntime.cpp
===================================================================
--- lib/CodeGen/CGOpenMPRuntime.cpp
+++ lib/CodeGen/CGOpenMPRuntime.cpp
@@ -196,6 +196,16 @@
RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_global_thread_num");
break;
}
+ case OMPRTL__kmpc_push_num_threads: {
+ // Build void __kmpc_push_num_threads(ident_t *loc, kmp_int32 global_tid,
+ // kmp_int32 num_threads)
+ llvm::Type *TypeParams[] = {getIdentTyPointerTy(), CGM.Int32Ty,
+ CGM.Int32Ty};
+ llvm::FunctionType *FnTy =
+ llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
+ RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_push_num_threads");
+ break;
+ }
}
return RTLFn;
}
Index: lib/CodeGen/CGStmtOpenMP.cpp
===================================================================
--- lib/CodeGen/CGStmtOpenMP.cpp
+++ lib/CodeGen/CGStmtOpenMP.cpp
@@ -23,6 +23,22 @@
// OpenMP Directive Emission
//===----------------------------------------------------------------------===//
+static void EmitOMPNumThreadsClause(CodeGenFunction &CGF,
+ const OMPNumThreadsClause *C) {
+ CodeGenFunction::RunCleanupsScope NumThreads(CGF);
+
+ // __kmpc_push_num_threads(&loc, global_tid, num_threads);
+ llvm::Value *Args[] = {
+ CGF.CGM.getOpenMPRuntime()
+ .EmitOpenMPUpdateLocation(CGF, C->getLocStart()),
+ CGF.CGM.getOpenMPRuntime()
+ .GetOpenMPGlobalThreadNum(CGF, C->getLocStart()),
+ CGF.EmitScalarExpr(C->getNumThreads(), /*IgnoreResultAssign*/ true)};
+ llvm::Constant *RTLFn = CGF.CGM.getOpenMPRuntime().CreateRuntimeFunction(
+ CGOpenMPRuntime::OMPRTL__kmpc_push_num_threads);
+ CGF.EmitRuntimeCall(RTLFn, Args);
+}
+
void CodeGenFunction::EmitOMPParallelDirective(const OMPParallelDirective &S) {
const CapturedStmt *CS = cast<CapturedStmt>(S.getAssociatedStmt());
llvm::Value *CapturedStruct = GenerateCapturedStmtArgument(*CS);
@@ -34,6 +50,8 @@
CGF.CapturedStmtInfo = &CGInfo;
OutlinedFn = CGF.GenerateCapturedStmtFunction(*CS);
}
+ if (auto C = S.getSingleClause(/*K*/ OMPC_num_threads))
+ EmitOMPNumThreadsClause(*this, cast<OMPNumThreadsClause>(C));
// Build call __kmpc_fork_call(loc, 1, microtask, captured_struct/*context*/)
llvm::Value *Args[] = {
Index: lib/CodeGen/CGOpenMPRuntime.h
===================================================================
--- lib/CodeGen/CGOpenMPRuntime.h
+++ lib/CodeGen/CGOpenMPRuntime.h
@@ -67,8 +67,11 @@
// Call to void __kmpc_fork_call(ident_t *loc, kmp_int32 argc, kmpc_micro
// microtask, ...);
OMPRTL__kmpc_fork_call,
- // Call to kmp_int32 kmpc_global_thread_num(ident_t *loc);
- OMPRTL__kmpc_global_thread_num
+ // Call to __kmpc_int32 kmpc_global_thread_num(ident_t *loc);
+ OMPRTL__kmpc_global_thread_num,
+ // Call to __kmpc_push_num_threads(ident_t *loc, kmp_int32 global_tid,
+ // kmp_int32 num_threads);
+ OMPRTL__kmpc_push_num_threads
};
private:
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.cs.uiuc.edu/mailman/listinfo/cfe-commits
