Adjust MaxAtomicInlineWidth for i386/i486 targets.

This is to fix the bug reported in https://bugs.llvm.org/show_bug.cgi?id=34347#c6.
Currently, all  MaxAtomicInlineWidth of x86-32 targets are set to 64. However,
i386 doesn't support any cmpxchg related instructions. i486 only supports cmpxchg.
So in this patch MaxAtomicInlineWidth is reset as follows:
For i386, the MaxAtomicInlineWidth should be 0 because no cmpxchg is supported.
For i486, the MaxAtomicInlineWidth should be 32 because it supports cmpxchg.
For others 32 bits x86 cpu, the MaxAtomicInlineWidth should be 64 because of cmpxchg8b.

Differential Revision: https://reviews.llvm.org/D42154

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@323281 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Basic/Targets/X86.h b/lib/Basic/Targets/X86.h
index 836cc68163957cdc441ebe14ea18363f3a218ba9..abe10017ca265909e8011416def28a68c2de7d41 100644 (file)
--- a/lib/Basic/Targets/X86.h
+++ b/lib/Basic/Targets/X86.h
@@ -100,6 +100,7 @@ class LLVM_LIBRARY_VISIBILITY X86TargetInfo : public TargetInfo {
   bool HasRetpoline = false;
   bool HasRetpolineExternalThunk = false;
 
+protected:
   /// \brief Enumeration of all of the X86 CPUs supported by Clang.
   ///
   /// Each enumeration represents a particular CPU supported by Clang. These
@@ -325,9 +326,11 @@ public:
          (1 << TargetInfo::LongDouble));
 
     // x86-32 has atomics up to 8 bytes
-    // FIXME: Check that we actually have cmpxchg8b before setting
-    // MaxAtomicInlineWidth. (cmpxchg8b is an i586 instruction.)
-    MaxAtomicPromoteWidth = MaxAtomicInlineWidth = 64;
+    CPUKind Kind = getCPUKind(Opts.CPU);
+    if (Kind >= CK_i586 || Kind == CK_Generic)
+      MaxAtomicPromoteWidth = MaxAtomicInlineWidth = 64;
+    else if (Kind >= CK_i486)
+      MaxAtomicPromoteWidth = MaxAtomicInlineWidth = 32;
   }
 
   BuiltinVaListKind getBuiltinVaListKind() const override {

diff --git a/test/CodeGenCXX/atomic-inline.cpp b/test/CodeGenCXX/atomic-inline.cpp
index fe727589d2e275409d967c587989deed4f994010..327f85d5667fdf7bf3e3b92cfa775a5058909d65 100644 (file)
--- a/test/CodeGenCXX/atomic-inline.cpp
+++ b/test/CodeGenCXX/atomic-inline.cpp
@@ -1,6 +1,52 @@
 // 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.
+// RUN: %clang_cc1 %s -std=c++11 -emit-llvm -o - -triple=i386-linux-gnu -target-cpu i386 | FileCheck %s --check-prefix=I386
+// RUN: %clang_cc1 %s -std=c++11 -emit-llvm -o - -triple=i386-linux-gnu -target-cpu i486 | FileCheck %s --check-prefix=I486
+// Check the atomic code generation for cpu targets w/wo cx, cx8 and cx16 support.
+
+struct alignas(4) AM4 {
+  short f1, f2;
+};
+AM4 m4;
+AM4 load4() {
+  AM4 am;
+  // CHECK-LABEL: @_Z5load4v
+  // CHECK: load atomic i32, {{.*}} monotonic
+  // CORE2-LABEL: @_Z5load4v
+  // CORE2: load atomic i32, {{.*}} monotonic
+  // I386-LABEL: @_Z5load4v
+  // I386: call i32 @__atomic_load_4
+  // I486-LABEL: @_Z5load4v
+  // I486: load atomic i32, {{.*}} monotonic
+  __atomic_load(&m4, &am, 0);
+  return am;
+}
+
+AM4 s4;
+void store4() {
+  // CHECK-LABEL: @_Z6store4v
+  // CHECK: store atomic i32 {{.*}} monotonic
+  // CORE2-LABEL: @_Z6store4v
+  // CORE2: store atomic i32 {{.*}} monotonic
+  // I386-LABEL: @_Z6store4v
+  // I386: call void @__atomic_store_4
+  // I486-LABEL: @_Z6store4v
+  // I486: store atomic i32 {{.*}} monotonic
+  __atomic_store(&m4, &s4, 0);
+}
+
+bool cmpxchg4() {
+  AM4 am;
+  // CHECK-LABEL: @_Z8cmpxchg4v
+  // CHECK: cmpxchg i32* {{.*}} monotonic
+  // CORE2-LABEL: @_Z8cmpxchg4v
+  // CORE2: cmpxchg i32* {{.*}} monotonic
+  // I386-LABEL: @_Z8cmpxchg4v
+  // I386: call zeroext i1 @__atomic_compare_exchange_4
+  // I486-LABEL: @_Z8cmpxchg4v
+  // I486: cmpxchg i32* {{.*}} monotonic
+  return __atomic_compare_exchange(&m4, &s4, &am, 0, 0, 0);
+}
 
 struct alignas(8) AM8 {
   int f1, f2;
@@ -12,6 +58,10 @@ AM8 load8() {
   // CHECK: load atomic i64, {{.*}} monotonic
   // CORE2-LABEL: @_Z5load8v
   // CORE2: load atomic i64, {{.*}} monotonic
+  // I386-LABEL: @_Z5load8v
+  // I386: call i64 @__atomic_load_8
+  // I486-LABEL: @_Z5load8v
+  // I486: call i64 @__atomic_load_8
   __atomic_load(&m8, &am, 0);
   return am;
 }
@@ -22,6 +72,10 @@ void store8() {
   // CHECK: store atomic i64 {{.*}} monotonic
   // CORE2-LABEL: @_Z6store8v
   // CORE2: store atomic i64 {{.*}} monotonic
+  // I386-LABEL: @_Z6store8v
+  // I386: call void @__atomic_store_8
+  // I486-LABEL: @_Z6store8v
+  // I486: call void @__atomic_store_8
   __atomic_store(&m8, &s8, 0);
 }
 
@@ -31,6 +85,10 @@ bool cmpxchg8() {
   // CHECK: cmpxchg i64* {{.*}} monotonic
   // CORE2-LABEL: @_Z8cmpxchg8v
   // CORE2: cmpxchg i64* {{.*}} monotonic
+  // I386-LABEL: @_Z8cmpxchg8v
+  // I386: call zeroext i1 @__atomic_compare_exchange_8
+  // I486-LABEL: @_Z8cmpxchg8v
+  // I486: call zeroext i1 @__atomic_compare_exchange_8
   return __atomic_compare_exchange(&m8, &s8, &am, 0, 0, 0);
 }
 
@@ -66,4 +124,3 @@ bool cmpxchg16() {
   // CORE2: cmpxchg i128* {{.*}} monotonic
   return __atomic_compare_exchange(&m16, &s16, &am, 0, 0, 0);
 }
-