hfinkel updated this revision to Diff 63394.
hfinkel added a comment.
Herald added a subscriber: mcrosier.
Rebased. Recursive AST visitor (which John pointed out was bad because it
caused quadratic behavior and was wasteful in terms of code size) replaced with
a function with some loops over the statements in each compound statement.
http://reviews.llvm.org/D9403
Files:
lib/CodeGen/CGDecl.cpp
lib/CodeGen/CGExpr.cpp
lib/CodeGen/CGStmt.cpp
lib/CodeGen/CodeGenFunction.cpp
lib/CodeGen/CodeGenFunction.h
test/CodeGen/noalias.c
test/OpenMP/taskloop_firstprivate_codegen.cpp
test/OpenMP/taskloop_lastprivate_codegen.cpp
test/OpenMP/taskloop_private_codegen.cpp
test/OpenMP/taskloop_simd_firstprivate_codegen.cpp
test/OpenMP/taskloop_simd_lastprivate_codegen.cpp
test/OpenMP/taskloop_simd_private_codegen.cpp
Index: test/OpenMP/taskloop_simd_private_codegen.cpp
===================================================================
--- test/OpenMP/taskloop_simd_private_codegen.cpp
+++ test/OpenMP/taskloop_simd_private_codegen.cpp
@@ -223,7 +223,8 @@
// CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
// CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
// CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
@@ -351,7 +352,8 @@
// CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
Index: test/OpenMP/taskloop_simd_lastprivate_codegen.cpp
===================================================================
--- test/OpenMP/taskloop_simd_lastprivate_codegen.cpp
+++ test/OpenMP/taskloop_simd_lastprivate_codegen.cpp
@@ -258,7 +258,8 @@
// CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
// CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
@@ -426,7 +427,8 @@
// CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
Index: test/OpenMP/taskloop_simd_firstprivate_codegen.cpp
===================================================================
--- test/OpenMP/taskloop_simd_firstprivate_codegen.cpp
+++ test/OpenMP/taskloop_simd_firstprivate_codegen.cpp
@@ -285,7 +285,8 @@
// CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
// CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
@@ -442,7 +443,8 @@
// CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
Index: test/OpenMP/taskloop_private_codegen.cpp
===================================================================
--- test/OpenMP/taskloop_private_codegen.cpp
+++ test/OpenMP/taskloop_private_codegen.cpp
@@ -223,7 +223,8 @@
// CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
// CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
// CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
@@ -351,7 +352,8 @@
// CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
Index: test/OpenMP/taskloop_lastprivate_codegen.cpp
===================================================================
--- test/OpenMP/taskloop_lastprivate_codegen.cpp
+++ test/OpenMP/taskloop_lastprivate_codegen.cpp
@@ -258,7 +258,8 @@
// CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
// CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
@@ -426,7 +427,8 @@
// CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
Index: test/OpenMP/taskloop_firstprivate_codegen.cpp
===================================================================
--- test/OpenMP/taskloop_firstprivate_codegen.cpp
+++ test/OpenMP/taskloop_firstprivate_codegen.cpp
@@ -285,7 +285,8 @@
// CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
// CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
@@ -442,7 +443,8 @@
// CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
Index: test/CodeGen/noalias.c
===================================================================
--- /dev/null
+++ test/CodeGen/noalias.c
@@ -0,0 +1,83 @@
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -disable-llvm-optzns %s -emit-llvm -o - | FileCheck %s
+
+int r;
+void ex1(int *);
+
+int *a;
+int *foo() {
+ int * restrict x = a;
+ return x;
+
+// CHECK-LABEL: define i32* @foo()
+// CHECK: [[x_addr_foo1:%[a-z0-9_.]+]] = alloca i32*
+// CHECK: [[x_foo1:%[a-z0-9_.]+]] = load i32*, i32** @a{{.*}}, !noalias [[TAG_foo1:!.*]]
+// CHECK: [[x_a_foo1:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo1]], metadata [[TAG_foo1]])
+// CHECK: store i32* [[x_a_foo1]], i32** [[x_addr_foo1]]{{.*}}, !noalias [[TAG_foo1]]
+}
+
+int *a2;
+int *foo1(int b) {
+ int * restrict x;
+
+// CHECK-LABEL: define i32* @foo1(i32 %b)
+// CHECK: [[x_addr_foo2:%[a-z0-9_.]+]] = alloca i32*
+// CHECK: [[x2_addr_foo2:%[a-z0-9_.]+]] = alloca i32*
+
+ if (b) {
+ x = a;
+ r += *x;
+ ex1(x);
+
+// CHECK: [[x_foo2:%[a-z0-9_.]+]] = load i32*, i32** @a{{.*}}, !noalias [[x_x2_tag_foo2:!.*]]
+// CHECK: [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2:!.*]])
+// CHECK: store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+ ++x;
+ *x = r;
+ ex1(x);
+
+// CHECK: [[old_x_foo2:%[a-z0-9_.]+]] = load i32*, i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: [[x_foo2:%[a-z0-9_.]+]] = getelementptr inbounds i32, i32* [[old_x_foo2]], i32 1
+// CHECK: [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2]])
+// CHECK: store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+
+ x += b;
+ *x = r;
+ ex1(x);
+
+// CHECK: [[old_x_foo2:%[a-z0-9_.]+]] = load i32*, i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: [[x_foo2:%[a-z0-9_.]+]] = getelementptr inbounds i32, i32* [[old_x_foo2]], i64
+// CHECK: [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2]])
+// CHECK: store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+
+ int * restrict x2 = a2;
+ *x2 = r;
+ ex1(x2);
+
+// CHECK: [[x2_foo2:%[a-z0-9_.]+]] = load i32*, i32** @a2{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: [[x2_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x2_foo2]], metadata [[x2_tag_foo2:!.*]])
+// CHECK: store i32* [[x2_a_foo2]], i32** [[x2_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+ } else {
+ x = a2;
+ r += *x;
+
+// CHECK: [[x_foo2:%[a-z0-9_.]+]] = load i32*, i32** @a2{{.*}}, !noalias [[x_tag_foo2]]
+// CHECK: [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2]])
+// CHECK: store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_tag_foo2]]
+ }
+
+ return x;
+}
+
+int *bar() {
+ int * x = a;
+ return x;
+
+// CHECK-LABEL: define i32* @bar()
+// CHECK-NOT: noalias
+// CHECK: ret i32*
+}
+
Index: lib/CodeGen/CodeGenFunction.h
===================================================================
--- lib/CodeGen/CodeGenFunction.h
+++ lib/CodeGen/CodeGenFunction.h
@@ -144,7 +144,7 @@
/// instruction is created using Builder.
void InsertHelper(llvm::Instruction *I, const llvm::Twine &Name,
llvm::BasicBlock *BB,
- llvm::BasicBlock::iterator InsertPt) const;
+ llvm::BasicBlock::iterator InsertPt);
/// CurFuncDecl - Holds the Decl for the current outermost
/// non-closure context.
@@ -531,7 +531,34 @@
}
};
- class LexicalScope : public RunCleanupsScope {
+ bool hasLocalRestrictVars(const CompoundStmt &S);
+
+ struct LexicalNoAliasInfo {
+ bool RecordMemoryInsts;
+ SmallVector<llvm::Instruction *, 8> MemoryInsts;
+ SmallVector<llvm::Metadata *, 4> NoAliasScopes;
+
+ LexicalNoAliasInfo(bool RMI = false) : RecordMemoryInsts(RMI) {}
+
+ void recordMemoryInsts() {
+ RecordMemoryInsts = true;
+ }
+
+ void recordMemoryInstruction(llvm::Instruction *I) {
+ if (RecordMemoryInsts)
+ MemoryInsts.push_back(I);
+ }
+
+ void addNoAliasScope(llvm::MDNode *Scope) {
+ assert(RecordMemoryInsts &&
+ "Adding noalias scope but not recording memory accesses!");
+ NoAliasScopes.push_back(Scope);
+ }
+
+ void addNoAliasMD();
+ } FnNoAliasInfo;
+
+ class LexicalScope : public RunCleanupsScope, public LexicalNoAliasInfo {
SourceRange Range;
SmallVector<const LabelDecl*, 4> Labels;
LexicalScope *ParentScope;
@@ -541,8 +568,10 @@
public:
/// \brief Enter a new cleanup scope.
- explicit LexicalScope(CodeGenFunction &CGF, SourceRange Range)
- : RunCleanupsScope(CGF), Range(Range), ParentScope(CGF.CurLexicalScope) {
+ explicit LexicalScope(CodeGenFunction &CGF, SourceRange Range,
+ bool RMI = false)
+ : RunCleanupsScope(CGF), LexicalNoAliasInfo(RMI), Range(Range),
+ ParentScope(CGF.CurLexicalScope) {
CGF.CurLexicalScope = this;
if (CGDebugInfo *DI = CGF.getDebugInfo())
DI->EmitLexicalBlockStart(CGF.Builder, Range.getBegin());
@@ -553,6 +582,14 @@
Labels.push_back(label);
}
+ void recordMemoryInstruction(llvm::Instruction *I) {
+ LexicalNoAliasInfo::recordMemoryInstruction(I);
+ if (ParentScope)
+ ParentScope->recordMemoryInstruction(I);
+ else
+ CGF.FnNoAliasInfo.recordMemoryInstruction(I);
+ }
+
/// \brief Exit this cleanup scope, emitting any accumulated
/// cleanups.
~LexicalScope() {
@@ -570,6 +607,8 @@
/// \brief Force the emission of cleanups now, instead of waiting
/// until this object is destroyed.
void ForceCleanup() {
+ addNoAliasMD();
+
CGF.CurLexicalScope = ParentScope;
RunCleanupsScope::ForceCleanup();
@@ -582,6 +621,20 @@
typedef llvm::DenseMap<const Decl *, Address> DeclMapTy;
+ void recordMemoryInstruction(llvm::Instruction *I) {
+ if (CurLexicalScope)
+ CurLexicalScope->recordMemoryInstruction(I);
+ else
+ FnNoAliasInfo.recordMemoryInstruction(I);
+ }
+
+ void addNoAliasScope(llvm::MDNode *Scope) {
+ if (CurLexicalScope)
+ CurLexicalScope->addNoAliasScope(Scope);
+ else
+ FnNoAliasInfo.addNoAliasScope(Scope);
+ }
+
/// \brief The scope used to remap some variables as private in the OpenMP
/// loop body (or other captured region emitted without outlining), and to
/// restore old vars back on exit.
@@ -1188,6 +1241,12 @@
void EmitOpenCLKernelMetadata(const FunctionDecl *FD,
llvm::Function *Fn);
+ /// The noalias domain metadata for this function.
+ llvm::MDNode* NoAliasDomain;
+ /// A map between the addresses of local restrict-qualified variables and
+ /// their noalias scope.
+ llvm::DenseMap<llvm::Value *, llvm::MDNode*> NoAliasAddrMap;
+
public:
CodeGenFunction(CodeGenModule &cgm, bool suppressNewContext=false);
~CodeGenFunction();
@@ -2180,6 +2239,8 @@
void emitAutoVarTypeCleanup(const AutoVarEmission &emission,
QualType::DestructionKind dtorKind);
+ void EmitAutoVarNoAlias(const AutoVarEmission &emission);
+
void EmitStaticVarDecl(const VarDecl &D,
llvm::GlobalValue::LinkageTypes Linkage);
Index: lib/CodeGen/CodeGenFunction.cpp
===================================================================
--- lib/CodeGen/CodeGenFunction.cpp
+++ lib/CodeGen/CodeGenFunction.cpp
@@ -59,7 +59,7 @@
CXXStructorImplicitParamDecl(nullptr),
CXXStructorImplicitParamValue(nullptr), OutermostConditional(nullptr),
CurLexicalScope(nullptr), TerminateLandingPad(nullptr),
- TerminateHandler(nullptr), TrapBB(nullptr) {
+ TerminateHandler(nullptr), TrapBB(nullptr), NoAliasDomain(nullptr) {
if (!suppressNewContext)
CGM.getCXXABI().getMangleContext().startNewFunction();
@@ -884,10 +884,16 @@
void CodeGenFunction::EmitFunctionBody(FunctionArgList &Args,
const Stmt *Body) {
incrementProfileCounter(Body);
- if (const CompoundStmt *S = dyn_cast<CompoundStmt>(Body))
+ if (const CompoundStmt *S = dyn_cast<CompoundStmt>(Body)) {
+ if (hasLocalRestrictVars(*S))
+ FnNoAliasInfo.recordMemoryInsts();
+
EmitCompoundStmtWithoutScope(*S);
- else
+
+ FnNoAliasInfo.addNoAliasMD();
+ } else {
EmitStmt(Body);
+ }
}
/// When instrumenting to collect profile data, the counts for some blocks
@@ -1886,10 +1892,13 @@
void CodeGenFunction::InsertHelper(llvm::Instruction *I,
const llvm::Twine &Name,
llvm::BasicBlock *BB,
- llvm::BasicBlock::iterator InsertPt) const {
+ llvm::BasicBlock::iterator InsertPt) {
LoopStack.InsertHelper(I);
if (IsSanitizerScope)
CGM.getSanitizerMetadata()->disableSanitizerForInstruction(I);
+
+ if (I->mayReadOrWriteMemory())
+ recordMemoryInstruction(I);
}
void CGBuilderInserter::InsertHelper(
Index: lib/CodeGen/CGStmt.cpp
===================================================================
--- lib/CodeGen/CGStmt.cpp
+++ lib/CodeGen/CGStmt.cpp
@@ -314,6 +314,22 @@
return true;
}
+bool CodeGenFunction::hasLocalRestrictVars(const CompoundStmt &S) {
+ // We may have restrict-qualified variables, but if we're not optimizing, we
+ // don't do anything special with them.
+ if (CGM.getCodeGenOpts().OptimizationLevel == 0)
+ return false;
+
+ for (const auto *C : S.body())
+ if (const auto *DS = dyn_cast<DeclStmt>(C))
+ for (const auto *I : DS->decls())
+ if (const auto *VD = dyn_cast<VarDecl>(I))
+ if (VD->getType().isRestrictQualified())
+ return true;
+
+ return false;
+}
+
/// EmitCompoundStmt - Emit a compound statement {..} node. If GetLast is true,
/// this captures the expression result of the last sub-statement and returns it
/// (for use by the statement expression extension).
@@ -323,7 +339,7 @@
"LLVM IR generation of compound statement ('{}')");
// Keep track of the current cleanup stack depth, including debug scopes.
- LexicalScope Scope(*this, S.getSourceRange());
+ LexicalScope Scope(*this, S.getSourceRange(), hasLocalRestrictVars(S));
return EmitCompoundStmtWithoutScope(S, GetLast, AggSlot);
}
@@ -505,6 +521,23 @@
}
}
+void CodeGenFunction::LexicalNoAliasInfo::addNoAliasMD() {
+ if (MemoryInsts.empty() || NoAliasScopes.empty())
+ return;
+
+ llvm::MDNode *NewScopeList =
+ llvm::MDNode::get(MemoryInsts[0]->getParent()->getContext(),
+ NoAliasScopes);
+
+ for (auto &I : MemoryInsts)
+ I->setMetadata(
+ llvm::LLVMContext::MD_noalias,
+ llvm::MDNode::concatenate(I->getMetadata(
+ llvm::LLVMContext::MD_noalias),
+ NewScopeList));
+
+ MemoryInsts.clear();
+}
void CodeGenFunction::EmitLabelStmt(const LabelStmt &S) {
EmitLabel(S.getDecl());
Index: lib/CodeGen/CGExpr.cpp
===================================================================
--- lib/CodeGen/CGExpr.cpp
+++ lib/CodeGen/CGExpr.cpp
@@ -1402,6 +1402,10 @@
Value = EmitToMemory(Value, Ty);
+ auto NAI = NoAliasAddrMap.find(Addr.getPointer());
+ if (NAI != NoAliasAddrMap.end())
+ Value = Builder.CreateNoAliasPointer(Value, NAI->second);
+
LValue AtomicLValue =
LValue::MakeAddr(Addr, Ty, getContext(), AlignSource, TBAAInfo);
if (Ty->isAtomicType() ||
Index: lib/CodeGen/CGDecl.cpp
===================================================================
--- lib/CodeGen/CGDecl.cpp
+++ lib/CodeGen/CGDecl.cpp
@@ -30,6 +30,7 @@
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Type.h"
using namespace clang;
@@ -903,6 +904,7 @@
/// These turn into simple stack objects, or GlobalValues depending on target.
void CodeGenFunction::EmitAutoVarDecl(const VarDecl &D) {
AutoVarEmission emission = EmitAutoVarAlloca(D);
+ EmitAutoVarNoAlias(emission);
EmitAutoVarInit(emission);
EmitAutoVarCleanups(emission);
}
@@ -1272,6 +1274,47 @@
}
}
+void CodeGenFunction::EmitAutoVarNoAlias(const AutoVarEmission &emission) {
+ assert(emission.Variable && "emission was not valid!");
+
+ // Don't emit noalias intrinsics unless we're optimizing.
+ if (CGM.getCodeGenOpts().OptimizationLevel == 0)
+ return;
+
+ const VarDecl &D = *emission.Variable;
+ QualType type = D.getType();
+
+ // Emit a noalias intrinsic for restrict-qualified variables.
+ if (!type.isRestrictQualified())
+ return;
+
+ llvm::MDBuilder MDB(CurFn->getContext());
+ if (!NoAliasDomain)
+ NoAliasDomain = MDB.createAnonymousAliasScopeDomain(CurFn->getName());
+
+ std::string Name = CurFn->getName();
+ Name += ": ";
+ Name += D.getName();
+
+ llvm::MDNode *Scope =
+ MDB.createAnonymousAliasScope(NoAliasDomain, Name);
+ addNoAliasScope(Scope);
+
+ SmallVector<llvm::Metadata *, 8> ScopeListEntries(1, Scope);
+ llvm::MDNode *ScopeList =
+ llvm::MDNode::get(CurFn->getContext(), ScopeListEntries);
+
+ // Check whether this is a byref variable that's potentially
+ // captured and moved by its own initializer. If so, we'll need to
+ // emit the initializer first, then copy into the variable.
+ const Expr *Init = D.getInit();
+ bool capturedByInit = emission.IsByRef && isCapturedBy(D, Init);
+
+ Address Loc =
+ capturedByInit ? emission.Addr : emission.getObjectAddress(*this);
+ NoAliasAddrMap[Loc.getPointer()] = ScopeList;
+}
+
/// Emit an expression as an initializer for a variable at the given
/// location. The expression is not necessarily the normal
/// initializer for the variable, and the address is not necessarily
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
