Merge pull request #131 from dcci/swift-4.1-branch
[Atomic][X8664] set max atomic inline width according to the target
diff --git a/include/clang/Basic/TargetInfo.h b/include/clang/Basic/TargetInfo.h
index d1a9ea8..beb1a7b 100644
--- a/include/clang/Basic/TargetInfo.h
+++ b/include/clang/Basic/TargetInfo.h
@@ -447,6 +447,9 @@
/// \brief Return the maximum width lock-free atomic operation which can be
/// inlined given the supported features of the given target.
unsigned getMaxAtomicInlineWidth() const { return MaxAtomicInlineWidth; }
+ /// \brief Set the maximum inline or promote width lock-free atomic operation
+ /// for the given target.
+ virtual void setMaxAtomicWidth() {}
/// \brief Returns true if the given target supports lock-free atomic
/// operations at the specified width and alignment.
virtual bool hasBuiltinAtomic(uint64_t AtomicSizeInBits,
diff --git a/lib/Basic/Targets.cpp b/lib/Basic/Targets.cpp
index 915c161..b0dc0d2 100644
--- a/lib/Basic/Targets.cpp
+++ b/lib/Basic/Targets.cpp
@@ -4881,7 +4881,7 @@
// x86-64 has atomics up to 16 bytes.
MaxAtomicPromoteWidth = 128;
- MaxAtomicInlineWidth = 128;
+ MaxAtomicInlineWidth = 64;
}
BuiltinVaListKind getBuiltinVaListKind() const override {
return TargetInfo::X86_64ABIBuiltinVaList;
@@ -4938,6 +4938,13 @@
return llvm::makeArrayRef(BuiltinInfoX86,
X86::LastTSBuiltin - Builtin::FirstTSBuiltin);
}
+
+ void setMaxAtomicWidth() override {
+ if (hasFeature("cx16"))
+ MaxAtomicInlineWidth = 128;
+ return;
+ }
+
};
// x86-64 Windows target
@@ -10029,6 +10036,7 @@
Target->setSupportedOpenCLOpts();
Target->setOpenCLExtensionOpts();
+ Target->setMaxAtomicWidth();
if (!Target->validateTarget(Diags))
return nullptr;
diff --git a/test/CodeGenCXX/atomic-inline.cpp b/test/CodeGenCXX/atomic-inline.cpp
new file mode 100644
index 0000000..fe72758
--- /dev/null
+++ b/test/CodeGenCXX/atomic-inline.cpp
@@ -0,0 +1,69 @@
+// RUN: %clang_cc1 %s -std=c++11 -emit-llvm -o - -triple=x86_64-linux-gnu | FileCheck %s
+// RUN: %clang_cc1 %s -std=c++11 -emit-llvm -o - -triple=x86_64-linux-gnu -target-cpu core2 | FileCheck %s --check-prefix=CORE2
+// Check the atomic code generation for cpu targets w/wo cx16 support.
+
+struct alignas(8) AM8 {
+ int f1, f2;
+};
+AM8 m8;
+AM8 load8() {
+ AM8 am;
+ // CHECK-LABEL: @_Z5load8v
+ // CHECK: load atomic i64, {{.*}} monotonic
+ // CORE2-LABEL: @_Z5load8v
+ // CORE2: load atomic i64, {{.*}} monotonic
+ __atomic_load(&m8, &am, 0);
+ return am;
+}
+
+AM8 s8;
+void store8() {
+ // CHECK-LABEL: @_Z6store8v
+ // CHECK: store atomic i64 {{.*}} monotonic
+ // CORE2-LABEL: @_Z6store8v
+ // CORE2: store atomic i64 {{.*}} monotonic
+ __atomic_store(&m8, &s8, 0);
+}
+
+bool cmpxchg8() {
+ AM8 am;
+ // CHECK-LABEL: @_Z8cmpxchg8v
+ // CHECK: cmpxchg i64* {{.*}} monotonic
+ // CORE2-LABEL: @_Z8cmpxchg8v
+ // CORE2: cmpxchg i64* {{.*}} monotonic
+ return __atomic_compare_exchange(&m8, &s8, &am, 0, 0, 0);
+}
+
+struct alignas(16) AM16 {
+ long f1, f2;
+};
+
+AM16 m16;
+AM16 load16() {
+ AM16 am;
+ // CHECK-LABEL: @_Z6load16v
+ // CHECK: call void @__atomic_load
+ // CORE2-LABEL: @_Z6load16v
+ // CORE2: load atomic i128, {{.*}} monotonic
+ __atomic_load(&m16, &am, 0);
+ return am;
+}
+
+AM16 s16;
+void store16() {
+ // CHECK-LABEL: @_Z7store16v
+ // CHECK: call void @__atomic_store
+ // CORE2-LABEL: @_Z7store16v
+ // CORE2: store atomic i128 {{.*}} monotonic
+ __atomic_store(&m16, &s16, 0);
+}
+
+bool cmpxchg16() {
+ AM16 am;
+ // CHECK-LABEL: @_Z9cmpxchg16v
+ // CHECK: call zeroext i1 @__atomic_compare_exchange
+ // CORE2-LABEL: @_Z9cmpxchg16v
+ // CORE2: cmpxchg i128* {{.*}} monotonic
+ return __atomic_compare_exchange(&m16, &s16, &am, 0, 0, 0);
+}
+
diff --git a/test/OpenMP/atomic_capture_codegen.cpp b/test/OpenMP/atomic_capture_codegen.cpp
index 0a22e42..5140359 100644
--- a/test/OpenMP/atomic_capture_codegen.cpp
+++ b/test/OpenMP/atomic_capture_codegen.cpp
@@ -1,6 +1,6 @@
-// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -target-cpu core2 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
diff --git a/test/OpenMP/atomic_read_codegen.c b/test/OpenMP/atomic_read_codegen.c
index 0cd46e3..0cfb2d2 100644
--- a/test/OpenMP/atomic_read_codegen.c
+++ b/test/OpenMP/atomic_read_codegen.c
@@ -1,6 +1,6 @@
-// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -target-cpu core2 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
// REQUIRES: x86-registered-target
#ifndef HEADER
diff --git a/test/OpenMP/atomic_update_codegen.cpp b/test/OpenMP/atomic_update_codegen.cpp
index 8c02a43..bb3b42e 100644
--- a/test/OpenMP/atomic_update_codegen.cpp
+++ b/test/OpenMP/atomic_update_codegen.cpp
@@ -1,6 +1,6 @@
-// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -target-cpu core2 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
diff --git a/test/OpenMP/atomic_write_codegen.c b/test/OpenMP/atomic_write_codegen.c
index 050d7a5..0c85b6e 100644
--- a/test/OpenMP/atomic_write_codegen.c
+++ b/test/OpenMP/atomic_write_codegen.c
@@ -1,6 +1,6 @@
-// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -target-cpu core2 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
// REQUIRES: x86-registered-target
#ifndef HEADER
