[X86] Add inline assembly versions of _InterlockedExchange_HLEAcquire/Release and _InterlockedCompareExchange_HLEAcquire/Release for MSVC compatibility.

Clang/LLVM doesn't have a way to pass an HLE hint through to the X86 backend to emit HLE prefixed instructions. So this is a good short term fix.

Differential Revision: https://reviews.llvm.org/D47672

llvm-svn: 334751

2 files changed, 84 insertions, 10 deletions

diff --git a/clang/lib/Headers/immintrin.h b/clang/lib/Headers/immintrin.h
index 3eead044976..e7bfbf964d5 100644
--- a/clang/lib/Headers/immintrin.h
+++ b/clang/lib/Headers/immintrin.h
@@ -380,4 +380,88 @@ _writegsbase_u64(unsigned long long __V)
 #include <invpcidintrin.h>
 #endif
 
+#ifdef _MSC_VER
+/* Define the default attributes for these intrinsics */
+#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
+#ifdef __cplusplus
+extern "C" {
+#endif
+/*----------------------------------------------------------------------------*\
+|* Interlocked Exchange HLE
+\*----------------------------------------------------------------------------*/
+#if defined(__i386__) || defined(__x86_64__)
+static __inline__ long __DEFAULT_FN_ATTRS
+_InterlockedExchange_HLEAcquire(long volatile *_Target, long _Value) {
+  __asm__ __volatile__(".byte 0xf2 ; lock ; xchg %0, %1"
+                       : "+r" (_Value), "+m" (*_Target) :: "memory");
+  return _Value;
+}
+static __inline__ long __DEFAULT_FN_ATTRS
+_InterlockedExchange_HLERelease(long volatile *_Target, long _Value) {
+  __asm__ __volatile__(".byte 0xf3 ; lock ; xchg %0, %1"
+                       : "+r" (_Value), "+m" (*_Target) :: "memory");
+  return _Value;
+}
+#endif
+#if defined(__x86_64__)
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedExchange64_HLEAcquire(__int64 volatile *_Target, __int64 _Value) {
+  __asm__ __volatile__(".byte 0xf2 ; lock ; xchg %0, %1"
+                       : "+r" (_Value), "+m" (*_Target) :: "memory");
+  return _Value;
+}
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedExchange64_HLERelease(__int64 volatile *_Target, __int64 _Value) {
+  __asm__ __volatile__(".byte 0xf3 ; lock ; xchg %0, %1"
+                       : "+r" (_Value), "+m" (*_Target) :: "memory");
+  return _Value;
+}
+#endif
+/*----------------------------------------------------------------------------*\
+|* Interlocked Compare Exchange HLE
+\*----------------------------------------------------------------------------*/
+#if defined(__i386__) || defined(__x86_64__)
+static __inline__ long __DEFAULT_FN_ATTRS
+_InterlockedCompareExchange_HLEAcquire(long volatile *_Destination,
+                              long _Exchange, long _Comparand) {
+  __asm__ __volatile__(".byte 0xf2 ; lock ; cmpxchg %2, %1"
+                       : "+a" (_Comparand), "+m" (*_Destination)
+                       : "r" (_Exchange) : "memory");
+  return _Comparand;
+}
+static __inline__ long __DEFAULT_FN_ATTRS
+_InterlockedCompareExchange_HLERelease(long volatile *_Destination,
+                              long _Exchange, long _Comparand) {
+  __asm__ __volatile__(".byte 0xf3 ; lock ; cmpxchg %2, %1"
+                       : "+a" (_Comparand), "+m" (*_Destination)
+                       : "r" (_Exchange) : "memory");
+  return _Comparand;
+}
+#endif
+#if defined(__x86_64__)
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedCompareExchange64_HLEAcquire(__int64 volatile *_Destination,
+                              __int64 _Exchange, __int64 _Comparand) {
+  __asm__ __volatile__(".byte 0xf2 ; lock ; cmpxchg %2, %1"
+                       : "+a" (_Comparand), "+m" (*_Destination)
+                       : "r" (_Exchange) : "memory");
+  return _Comparand;
+}
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedCompareExchange64_HLERelease(__int64 volatile *_Destination,
+                              __int64 _Exchange, __int64 _Comparand) {
+  __asm__ __volatile__(".byte 0xf3 ; lock ; cmpxchg %2, %1"
+                       : "+a" (_Comparand), "+m" (*_Destination)
+                       : "r" (_Exchange) : "memory");
+  return _Comparand;
+}
+#endif
+#ifdef __cplusplus
+}
+#endif
+
+#undef __DEFAULT_FN_ATTRS
+
+#endif /* _MSC_VER */
+
 #endif /* __IMMINTRIN_H */
diff --git a/clang/lib/Headers/intrin.h b/clang/lib/Headers/intrin.h
index 4118fb7d8f1..5ac8e300874 100644
--- a/clang/lib/Headers/intrin.h
+++ b/clang/lib/Headers/intrin.h
@@ -170,12 +170,6 @@ void __cdecl _enable(void);
 long _InterlockedAddLargeStatistic(__int64 volatile *_Addend, long _Value);
 unsigned char _interlockedbittestandreset(long volatile *, long);
 unsigned char _interlockedbittestandset(long volatile *, long);
-long _InterlockedCompareExchange_HLEAcquire(long volatile *, long, long);
-long _InterlockedCompareExchange_HLERelease(long volatile *, long, long);
-__int64 _InterlockedcompareExchange64_HLEAcquire(__int64 volatile *, __int64,
-                                                 __int64);
-__int64 _InterlockedCompareExchange64_HLERelease(__int64 volatile *, __int64,
-                                                 __int64);
 void *_InterlockedCompareExchangePointer_HLEAcquire(void *volatile *, void *,
                                                     void *);
 void *_InterlockedCompareExchangePointer_HLERelease(void *volatile *, void *,
@@ -278,10 +272,6 @@ unsigned char _InterlockedCompareExchange128_np(__int64 volatile *_Destination,
                                                 __int64 *_ComparandResult);
 short _InterlockedCompareExchange16_np(short volatile *_Destination,
                                        short _Exchange, short _Comparand);
-__int64 _InterlockedCompareExchange64_HLEAcquire(__int64 volatile *, __int64,
-                                                 __int64);
-__int64 _InterlockedCompareExchange64_HLERelease(__int64 volatile *, __int64,
-                                                 __int64);
 __int64 _InterlockedCompareExchange64_np(__int64 volatile *_Destination,
                                          __int64 _Exchange, __int64 _Comparand);
 void *_InterlockedCompareExchangePointer_np(void *volatile *_Destination,