[OPENMP] Codegen for 'private' clause in 'for' directive.

This patch generates helper variables which used as a private copies of the corresponding original variables inside an OpenMP 'for' directive. These generated variables are initialized by default (with the default constructor, if any). In OpenMP region references to original variables are replaced by the references to these private helper variables.
Differential Revision: http://reviews.llvm.org/D9106

llvm-svn: 235503

diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index c83dda2..744f914 100644 (file)
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -242,22 +242,26 @@ void CodeGenFunction::EmitOMPPrivateClause(
   auto PrivateFilter = [](const OMPClause *C) -> bool {
     return C->getClauseKind() == OMPC_private;
   };
+  llvm::DenseSet<const VarDecl *> EmittedAsPrivate;
   for (OMPExecutableDirective::filtered_clause_iterator<decltype(PrivateFilter)>
-           I(D.clauses(), PrivateFilter); I; ++I) {
+           I(D.clauses(), PrivateFilter);
+       I; ++I) {
     auto *C = cast<OMPPrivateClause>(*I);
     auto IRef = C->varlist_begin();
     for (auto IInit : C->private_copies()) {
       auto *OrigVD = cast<VarDecl>(cast<DeclRefExpr>(*IRef)->getDecl());
-      auto VD = cast<VarDecl>(cast<DeclRefExpr>(IInit)->getDecl());
-      bool IsRegistered =
-          PrivateScope.addPrivate(OrigVD, [&]() -> llvm::Value * {
-            // Emit private VarDecl with copy init.
-            EmitDecl(*VD);
-            return GetAddrOfLocalVar(VD);
-          });
-      assert(IsRegistered && "private var already registered as private");
-      // Silence the warning about unused variable.
-      (void)IsRegistered;
+      if (EmittedAsPrivate.insert(OrigVD->getCanonicalDecl()).second) {
+        auto VD = cast<VarDecl>(cast<DeclRefExpr>(IInit)->getDecl());
+        bool IsRegistered =
+            PrivateScope.addPrivate(OrigVD, [&]() -> llvm::Value *{
+              // Emit private VarDecl with copy init.
+              EmitDecl(*VD);
+              return GetAddrOfLocalVar(VD);
+            });
+        assert(IsRegistered && "private var already registered as private");
+        // Silence the warning about unused variable.
+        (void)IsRegistered;
+      }
       ++IRef;
     }
   }
@@ -1072,6 +1076,7 @@ bool CodeGenFunction::EmitOMPWorksharingLoop(const OMPLoopDirective &S) {
         CGM.getOpenMPRuntime().emitBarrierCall(*this, S.getLocStart(),
                                                OMPD_unknown);
       }
+      EmitOMPPrivateClause(S, LoopScope);
       HasLastprivateClause = EmitOMPLastprivateClauseInit(S, LoopScope);
       EmitPrivateLoopCounters(*this, LoopScope, S.counters());
       (void)LoopScope.Privatize();

diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 0cfb94e..c960f8b 100644 (file)
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -4716,10 +4716,10 @@ OMPClause *Sema::ActOnOpenMPPrivateClause(ArrayRef<Expr *> VarList,
     // the new private variable in CodeGen. This new variable is not added to
     // IdResolver, so the code in the OpenMP region uses original variable for
     // proper diagnostics.
-    auto VDPrivate =
-        VarDecl::Create(Context, CurContext, DE->getLocStart(),
-                        DE->getExprLoc(), VD->getIdentifier(), VD->getType(),
-                        VD->getTypeSourceInfo(), /*S*/ SC_Auto);
+    auto VDPrivate = VarDecl::Create(Context, CurContext, DE->getLocStart(),
+                                     DE->getExprLoc(), VD->getIdentifier(),
+                                     VD->getType().getUnqualifiedType(),
+                                     VD->getTypeSourceInfo(), /*S*/ SC_Auto);
     ActOnUninitializedDecl(VDPrivate, /*TypeMayContainAuto*/ false);
     if (VDPrivate->isInvalidDecl())
       continue;

diff --git a/clang/test/OpenMP/for_private_codegen.cpp b/clang/test/OpenMP/for_private_codegen.cpp
new file mode 100644 (file)
index 0000000..e87473b
--- /dev/null
+++ b/clang/test/OpenMP/for_private_codegen.cpp
@@ -0,0 +1,182 @@
+// RUN: %clang_cc1 -verify -fopenmp=libiomp5 -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp=libiomp5 -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp=libiomp5 -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp=libiomp5 -x c++ -std=c++11 -DLAMBDA -triple %itanium_abi_triple -emit-llvm %s -o - | FileCheck -check-prefix=LAMBDA %s
+// RUN: %clang_cc1 -verify -fopenmp=libiomp5 -x c++ -fblocks -DBLOCKS -triple %itanium_abi_triple -emit-llvm %s -o - | FileCheck -check-prefix=BLOCKS %s
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+template <class T>
+struct S {
+  T f;
+  S(T a) : f(a) {}
+  S() : f() {}
+  operator T() { return T(); }
+  ~S() {}
+};
+
+volatile double g;
+
+// CHECK: [[S_FLOAT_TY:%.+]] = type { float }
+// CHECK: [[CAP_MAIN_TY:%.+]] = type { i{{[0-9]+}}*, [2 x i{{[0-9]+}}]*, [2 x [[S_FLOAT_TY]]]*, [[S_FLOAT_TY]]* }
+// CHECK: [[S_INT_TY:%.+]] = type { i{{[0-9]+}} }
+// CHECK: [[CAP_TMAIN_TY:%.+]] = type { i{{[0-9]+}}*, [2 x i{{[0-9]+}}]*, [2 x [[S_INT_TY]]]*, [[S_INT_TY]]* }
+template <typename T>
+T tmain() {
+  S<T> test;
+  T t_var = T();
+  T vec[] = {1, 2};
+  S<T> s_arr[] = {1, 2};
+  S<T> var(3);
+#pragma omp parallel
+#pragma omp for private(t_var, vec, s_arr, s_arr, var, var)
+  for (int i = 0; i < 2; ++i) {
+    vec[i] = t_var;
+    s_arr[i] = var;
+  }
+  return T();
+}
+
+int main() {
+#ifdef LAMBDA
+  // LAMBDA: [[G:@.+]] = global double
+  // LAMBDA-LABEL: @main
+  // LAMBDA: call{{( x86_thiscallcc)?}} void [[OUTER_LAMBDA:@.+]](
+  [&]() {
+  // LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
+  // LAMBDA: call void {{.+}} @__kmpc_fork_call({{.+}}, i32 1, {{.+}}* [[OMP_REGION:@.+]] to {{.+}}, i8* %{{.+}})
+#pragma omp parallel
+#pragma omp for private(g)
+  for (int i = 0; i < 2; ++i) {
+    // LAMBDA: define{{.*}} internal{{.*}} void [[OMP_REGION]](i32* %{{.+}}, i32* %{{.+}}, %{{.+}}* [[ARG:%.+]])
+    // LAMBDA: [[G_PRIVATE_ADDR:%.+]] = alloca double,
+    // LAMBDA: store %{{.+}}* [[ARG]], %{{.+}}** [[ARG_REF:%.+]],
+    g = 1;
+    // LAMBDA: call void @__kmpc_for_static_init_4(
+    // LAMBDA: store volatile double 1.0{{.+}}, double* [[G_PRIVATE_ADDR]],
+    // LAMBDA: [[G_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
+    // LAMBDA: store double* [[G_PRIVATE_ADDR]], double** [[G_PRIVATE_ADDR_REF]]
+    // LAMBDA: call{{( x86_thiscallcc)?}} void [[INNER_LAMBDA:@.+]](%{{.+}}* [[ARG]])
+    // LAMBDA: call void @__kmpc_for_static_fini(
+    [&]() {
+      // LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
+      // LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
+      g = 2;
+      // LAMBDA: [[ARG_PTR:%.+]] = load %{{.+}}*, %{{.+}}** [[ARG_PTR_REF]]
+      // LAMBDA: [[G_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
+      // LAMBDA: [[G_REF:%.+]] = load double*, double** [[G_PTR_REF]]
+      // LAMBDA: store volatile double 2.0{{.+}}, double* [[G_REF]]
+    }();
+  }
+  }();
+  return 0;
+#elif defined(BLOCKS)
+  // BLOCKS: [[G:@.+]] = global double
+  // BLOCKS-LABEL: @main
+  // BLOCKS: call void {{%.+}}(i8
+  ^{
+  // BLOCKS: define{{.*}} internal{{.*}} void {{.+}}(i8*
+  // BLOCKS: call void {{.+}} @__kmpc_fork_call({{.+}}, i32 1, {{.+}}* [[OMP_REGION:@.+]] to {{.+}}, i8* {{.+}})
+#pragma omp parallel
+#pragma omp for private(g)
+  for (int i = 0; i < 2; ++i) {
+    // BLOCKS: define{{.*}} internal{{.*}} void [[OMP_REGION]](i32* %{{.+}}, i32* %{{.+}}, %{{.+}}* [[ARG:%.+]])
+    // BLOCKS: [[G_PRIVATE_ADDR:%.+]] = alloca double,
+    // BLOCKS: store %{{.+}}* [[ARG]], %{{.+}}** [[ARG_REF:%.+]],
+    g = 1;
+    // BLOCKS: call void @__kmpc_for_static_init_4(
+    // BLOCKS: store volatile double 1.0{{.+}}, double* [[G_PRIVATE_ADDR]],
+    // BLOCKS-NOT: [[G]]{{[[^:word:]]}}
+    // BLOCKS: double* [[G_PRIVATE_ADDR]]
+    // BLOCKS-NOT: [[G]]{{[[^:word:]]}}
+    // BLOCKS: call void {{%.+}}(i8
+    // BLOCKS: call void @__kmpc_for_static_fini(
+    ^{
+      // BLOCKS: define {{.+}} void {{@.+}}(i8*
+      g = 2;
+      // BLOCKS-NOT: [[G]]{{[[^:word:]]}}
+      // BLOCKS: store volatile double 2.0{{.+}}, double*
+      // BLOCKS-NOT: [[G]]{{[[^:word:]]}}
+      // BLOCKS: ret
+    }();
+  }
+  }();
+  return 0;
+#else
+  S<float> test;
+  int t_var = 0;
+  int vec[] = {1, 2};
+  S<float> s_arr[] = {1, 2};
+  S<float> var(3);
+#pragma omp parallel
+#pragma omp for private(t_var, vec, s_arr, s_arr, var, var)
+  for (int i = 0; i < 2; ++i) {
+    vec[i] = t_var;
+    s_arr[i] = var;
+  }
+  return tmain<int>();
+#endif
+}
+
+// CHECK: define i{{[0-9]+}} @main()
+// CHECK: [[TEST:%.+]] = alloca [[S_FLOAT_TY]],
+// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR:@.+]]([[S_FLOAT_TY]]* [[TEST]])
+// CHECK: %{{.+}} = bitcast [[CAP_MAIN_TY]]*
+// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 1, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, [[CAP_MAIN_TY]]*)* [[MAIN_MICROTASK:@.+]] to void
+// CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
+// CHECK: call void [[S_FLOAT_TY_DESTR:@.+]]([[S_FLOAT_TY]]*
+// CHECK: ret
+//
+// CHECK: define internal void [[MAIN_MICROTASK]](i{{[0-9]+}}* [[GTID_ADDR:%.+]], i{{[0-9]+}}* %{{.+}}, [[CAP_MAIN_TY]]* %{{.+}})
+// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
+// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
+// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
+// CHECK-NOT: alloca [2 x [[S_FLOAT_TY]]],
+// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
+// CHECK-NOT: alloca [[S_FLOAT_TY]],
+// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
+// CHECK-NOT: [[T_VAR_PRIV]]
+// CHECK-NOT: [[VEC_PRIV]]
+// CHECK: {{.+}}:
+// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = phi [[S_FLOAT_TY]]*
+// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR]]([[S_FLOAT_TY]]* [[S_ARR_PRIV_ITEM]])
+// CHECK-NOT: [[T_VAR_PRIV]]
+// CHECK-NOT: [[VEC_PRIV]]
+// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR]]([[S_FLOAT_TY]]* [[VAR_PRIV]])
+// CHECK: call void @__kmpc_for_static_init_4(
+// CHECK: call void @__kmpc_for_static_fini(
+// CHECK-DAG: call void [[S_FLOAT_TY_DESTR]]([[S_FLOAT_TY]]* [[VAR_PRIV]])
+// CHECK-DAG: call void [[S_FLOAT_TY_DESTR]]([[S_FLOAT_TY]]*
+// CHECK: ret void
+
+// CHECK: define {{.*}} i{{[0-9]+}} [[TMAIN_INT]]()
+// CHECK: [[TEST:%.+]] = alloca [[S_INT_TY]],
+// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR:@.+]]([[S_INT_TY]]* [[TEST]])
+// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 1, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, [[CAP_TMAIN_TY]]*)* [[TMAIN_MICROTASK:@.+]] to void
+// CHECK: call void [[S_INT_TY_DESTR:@.+]]([[S_INT_TY]]*
+// CHECK: ret
+//
+// CHECK: define internal void [[TMAIN_MICROTASK]](i{{[0-9]+}}* [[GTID_ADDR:%.+]], i{{[0-9]+}}* %{{.+}}, [[CAP_TMAIN_TY]]* %{{.+}})
+// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
+// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
+// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_INT_TY]]],
+// CHECK-NOT: alloca [2 x [[S_INT_TY]]],
+// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_INT_TY]],
+// CHECK-NOT: alloca [[S_INT_TY]],
+// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]]
+// CHECK-NOT: [[T_VAR_PRIV]]
+// CHECK-NOT: [[VEC_PRIV]]
+// CHECK: {{.+}}:
+// CHECK: [[S_ARR_PRIV_ITEM:%.+]] = phi [[S_INT_TY]]*
+// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[S_ARR_PRIV_ITEM]])
+// CHECK-NOT: [[T_VAR_PRIV]]
+// CHECK-NOT: [[VEC_PRIV]]
+// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[VAR_PRIV]])
+// CHECK: call void @__kmpc_for_static_init_4(
+// CHECK: call void @__kmpc_for_static_fini(
+// CHECK-DAG: call void [[S_INT_TY_DESTR]]([[S_INT_TY]]* [[VAR_PRIV]])
+// CHECK-DAG: call void [[S_INT_TY_DESTR]]([[S_INT_TY]]*
+// CHECK: ret void
+#endif
+