Add some MS aliases for existing intrinsics

Reviewers: thakis, compnerd, majnemer, rsmith, rnk

Subscribers: alexshap, cfe-commits

Differential Revision: https://reviews.llvm.org/D24330

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@281540 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Basic/Builtins.def b/include/clang/Basic/Builtins.def
index 7316901ab86e593bc6f00d4ce108288db940f2c6..6de2dec9a47b0bfa415974c32094007a36ec34b3 100644 (file)
--- a/include/clang/Basic/Builtins.def
+++ b/include/clang/Basic/Builtins.def
@@ -74,6 +74,7 @@
 //  f -> this is a libc/libm function without the '__builtin_' prefix. It can
 //       be followed by ':headername:' to state which header this function
 //       comes from.
+//  h -> this function requires a specific header or an explicit declaration.
 //  i -> this is a runtime library implemented function without the
 //       '__builtin_' prefix. It will be implemented in compiler-rt or libgcc.
 //  p:N: -> this is a printf-like function whose Nth argument is the format
@@ -708,6 +709,9 @@ BUILTIN(__builtin_rindex, "c*cC*i", "Fn")
 // Microsoft builtins.  These are only active with -fms-extensions.
 LANGBUILTIN(_alloca,          "v*z", "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(__assume,         "vb",  "n", ALL_MS_LANGUAGES)
+LIBBUILTIN(_byteswap_ushort, "UsUs",     "fnc", "stdlib.h", ALL_MS_LANGUAGES)
+LIBBUILTIN(_byteswap_ulong,  "ULiULi",   "fnc", "stdlib.h", ALL_MS_LANGUAGES)
+LIBBUILTIN(_byteswap_uint64, "ULLiULLi", "fnc", "stdlib.h", ALL_MS_LANGUAGES)
 LANGBUILTIN(__debugbreak,     "v",   "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(__exception_code, "ULi", "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(_exception_code,  "ULi", "n", ALL_MS_LANGUAGES)
@@ -745,6 +749,9 @@ LANGBUILTIN(_InterlockedXor8,  "ccD*c",       "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(_InterlockedXor16, "ssD*s",       "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(_InterlockedXor,   "LiLiD*Li",    "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(__noop,           "i.",  "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__popcnt16, "UsUs",     "nc", ALL_MS_LANGUAGES)
+LANGBUILTIN(__popcnt,   "UiUi",     "nc", ALL_MS_LANGUAGES)
+LANGBUILTIN(__popcnt64, "ULLiULLi", "nc", ALL_MS_LANGUAGES)
 LANGBUILTIN(__readfsdword,    "ULiULi", "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(_rotl8,  "UcUcUc",    "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(_rotl16, "UsUsUc",    "n", ALL_MS_LANGUAGES)

diff --git a/include/clang/Basic/Builtins.h b/include/clang/Basic/Builtins.h
index 15e9a413fb42090738657643dae34f64248f765a..87c1f93eedefe7649faf6094b81561e778a8da47 100644 (file)
--- a/include/clang/Basic/Builtins.h
+++ b/include/clang/Basic/Builtins.h
@@ -139,6 +139,13 @@ public:
     return strchr(getRecord(ID).Attributes, 'f') != nullptr;
   }
 
+  /// \brief Returns true if this builtin requires appropriate header in other
+  /// compilers. In Clang it will work even without including it, but we can emit
+  /// a warning about missing header.
+  bool isHeaderDependentFunction(unsigned ID) const {
+    return strchr(getRecord(ID).Attributes, 'h') != nullptr;
+  }
+
   /// \brief Determines whether this builtin is a predefined compiler-rt/libgcc
   /// function, such as "__clear_cache", where we know the signature a
   /// priori.

diff --git a/include/clang/Basic/BuiltinsX86.def b/include/clang/Basic/BuiltinsX86.def
index a9577cf837f2607dc184e24fb1a2481dd50d1b81..033ed6e21aa33ea6535714b5c39ebf1c52094f33 100644 (file)
--- a/include/clang/Basic/BuiltinsX86.def
+++ b/include/clang/Basic/BuiltinsX86.def
@@ -23,6 +23,10 @@
 #   define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE) BUILTIN(ID, TYPE, ATTRS)
 #endif
 
+#if defined(BUILTIN) && !defined(TARGET_HEADER_BUILTIN)
+#  define TARGET_HEADER_BUILTIN(ID, TYPE, ATTRS, HEADER, LANG, FEATURE) BUILTIN(ID, TYPE, ATTRS)
+#endif
+
 // FIXME: Are these nothrow/const?
 
 // Miscellaneous builtin for checking x86 cpu features.
@@ -301,7 +305,9 @@ TARGET_BUILTIN(__builtin_ia32_pabsw128, "V8sV8s", "", "ssse3")
 TARGET_BUILTIN(__builtin_ia32_pabsd128, "V4iV4i", "", "ssse3")
 
 TARGET_BUILTIN(__builtin_ia32_ldmxcsr, "vUi", "", "sse")
+TARGET_HEADER_BUILTIN(_mm_setcsr, "vUi", "h","xmmintrin.h", ALL_LANGUAGES, "sse")
 TARGET_BUILTIN(__builtin_ia32_stmxcsr, "Ui", "", "sse")
+TARGET_HEADER_BUILTIN(_mm_getcsr, "Ui", "h", "xmmintrin.h", ALL_LANGUAGES, "sse")
 TARGET_BUILTIN(__builtin_ia32_cvtss2si, "iV4f", "", "sse")
 TARGET_BUILTIN(__builtin_ia32_cvttss2si, "iV4f", "", "sse")
 TARGET_BUILTIN(__builtin_ia32_cvtss2si64, "LLiV4f", "", "sse")
@@ -310,6 +316,7 @@ TARGET_BUILTIN(__builtin_ia32_storehps, "vV2i*V4f", "", "sse")
 TARGET_BUILTIN(__builtin_ia32_storelps, "vV2i*V4f", "", "sse")
 TARGET_BUILTIN(__builtin_ia32_movmskps, "iV4f", "", "sse")
 TARGET_BUILTIN(__builtin_ia32_sfence, "v", "", "sse")
+TARGET_HEADER_BUILTIN(_mm_sfence, "v", "h", "xmmintrin.h", ALL_LANGUAGES, "sse")
 TARGET_BUILTIN(__builtin_ia32_rcpps, "V4fV4f", "", "sse")
 TARGET_BUILTIN(__builtin_ia32_rcpss, "V4fV4f", "", "sse")
 TARGET_BUILTIN(__builtin_ia32_rsqrtps, "V4fV4f", "", "sse")
@@ -337,9 +344,13 @@ TARGET_BUILTIN(__builtin_ia32_cvtsd2ss, "V4fV4fV2d", "", "sse2")
 TARGET_BUILTIN(__builtin_ia32_cvtps2dq, "V4iV4f", "", "sse2")
 TARGET_BUILTIN(__builtin_ia32_cvttps2dq, "V4iV4f", "", "sse2")
 TARGET_BUILTIN(__builtin_ia32_clflush, "vvC*", "", "sse2")
+TARGET_HEADER_BUILTIN(_mm_clflush, "vvC*", "h", "emmintrin.h", ALL_LANGUAGES, "sse2")
 TARGET_BUILTIN(__builtin_ia32_lfence, "v", "", "sse2")
+TARGET_HEADER_BUILTIN(_mm_lfence, "v", "h", "emmintrin.h", ALL_LANGUAGES, "sse2")
 TARGET_BUILTIN(__builtin_ia32_mfence, "v", "", "sse2")
+TARGET_HEADER_BUILTIN(_mm_mfence, "v", "h", "emmintrin.h", ALL_LANGUAGES, "sse2")
 TARGET_BUILTIN(__builtin_ia32_pause, "v", "", "sse2")
+TARGET_HEADER_BUILTIN(_mm_pause, "v", "h", "emmintrin.h", ALL_LANGUAGES, "sse2")
 TARGET_BUILTIN(__builtin_ia32_pmuludq128, "V2LLiV4iV4i", "", "sse2")
 TARGET_BUILTIN(__builtin_ia32_psraw128, "V8sV8sV8s", "", "sse2")
 TARGET_BUILTIN(__builtin_ia32_psrad128, "V4iV4iV4i", "", "sse2")
@@ -894,6 +905,7 @@ TARGET_BUILTIN(__builtin_ia32_xtest, "i", "", "rtm")
 
 BUILTIN(__builtin_ia32_rdpmc, "ULLii", "")
 BUILTIN(__builtin_ia32_rdtsc, "ULLi", "")
+BUILTIN(__rdtsc, "ULLi", "")
 BUILTIN(__builtin_ia32_rdtscp, "ULLiUi*", "")
 // PKU
 TARGET_BUILTIN(__builtin_ia32_rdpkru, "Ui", "", "pku")
@@ -2059,3 +2071,4 @@ TARGET_BUILTIN(__builtin_ia32_mwaitx, "vUiUiUi", "", "mwaitx")
 
 #undef BUILTIN
 #undef TARGET_BUILTIN
+#undef TARGET_HEADER_BUILTIN

diff --git a/lib/Basic/Targets.cpp b/lib/Basic/Targets.cpp
index b549d1485ba0fca1320e5c2e30e008010e221efa..62ecd1e28ce6d029defbd128008956b89c3c4dcd 100644 (file)
--- a/lib/Basic/Targets.cpp
+++ b/lib/Basic/Targets.cpp
@@ -2303,6 +2303,8 @@ const Builtin::Info BuiltinInfo[] = {
   { #ID, TYPE, ATTRS, HEADER, ALL_LANGUAGES, nullptr },
 #define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE)                               \
   { #ID, TYPE, ATTRS, nullptr, ALL_LANGUAGES, FEATURE },
+#define TARGET_HEADER_BUILTIN(ID, TYPE, ATTRS, HEADER, LANGS, FEATURE)         \
+  { #ID, TYPE, ATTRS, HEADER, LANGS, FEATURE },
 #include "clang/Basic/BuiltinsX86.def"
 };
 

diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp
index 27c0b837766e844bb279d04bc35e54d226b327de..e105a06b147a475b702c193531567db94a2f9992 100644 (file)
--- a/lib/CodeGen/CGBuiltin.cpp
+++ b/lib/CodeGen/CGBuiltin.cpp
@@ -681,6 +681,9 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
                                      "cast");
     return RValue::get(Result);
   }
+  case Builtin::BI__popcnt16:
+  case Builtin::BI__popcnt:
+  case Builtin::BI__popcnt64:
   case Builtin::BI__builtin_popcount:
   case Builtin::BI__builtin_popcountl:
   case Builtin::BI__builtin_popcountll: {
@@ -6954,6 +6957,25 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
     Value *F = CGM.getIntrinsic(Intrinsic::prefetch);
     return Builder.CreateCall(F, {Address, RW, Locality, Data});
   }
+  case X86::BI_mm_clflush: {
+    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_clflush),
+                              Ops[0]);
+  }
+  case X86::BI_mm_lfence: {
+    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_lfence));
+  }
+  case X86::BI_mm_mfence: {
+    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_mfence));
+  }
+  case X86::BI_mm_sfence: {
+    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse_sfence));
+  }
+  case X86::BI_mm_pause: {
+    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_pause));
+  }
+  case X86::BI__rdtsc: {
+    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_rdtsc));
+  }
   case X86::BI__builtin_ia32_undef128:
   case X86::BI__builtin_ia32_undef256:
   case X86::BI__builtin_ia32_undef512:
@@ -6966,12 +6988,14 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
   case X86::BI__builtin_ia32_vec_ext_v2si:
     return Builder.CreateExtractElement(Ops[0],
                                   llvm::ConstantInt::get(Ops[1]->getType(), 0));
+  case X86::BI_mm_setcsr:
   case X86::BI__builtin_ia32_ldmxcsr: {
     Address Tmp = CreateMemTemp(E->getArg(0)->getType());
     Builder.CreateStore(Ops[0], Tmp);
     return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse_ldmxcsr),
                           Builder.CreateBitCast(Tmp.getPointer(), Int8PtrTy));
   }
+  case X86::BI_mm_getcsr:
   case X86::BI__builtin_ia32_stmxcsr: {
     Address Tmp = CreateMemTemp(E->getType());
     Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse_stmxcsr),

diff --git a/lib/Headers/emmintrin.h b/lib/Headers/emmintrin.h
index d73b3a8eda1983c57879662ff24208ba18a355a7..3703b4879c2d1884be63e61aaeb4a8ec53a379ab 100644 (file)
--- a/lib/Headers/emmintrin.h
+++ b/lib/Headers/emmintrin.h
@@ -2447,6 +2447,10 @@ _mm_stream_si64(long long *__p, long long __a)
 }
 #endif
 
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
 /// \brief The cache line containing __p is flushed and invalidated from all
 ///    caches in the coherency domain.
 ///
@@ -2457,11 +2461,7 @@ _mm_stream_si64(long long *__p, long long __a)
 /// \param __p
 ///    A pointer to the memory location used to identify the cache line to be
 ///    flushed.
-static __inline__ void __DEFAULT_FN_ATTRS
-_mm_clflush(void const *__p)
-{
-  __builtin_ia32_clflush(__p);
-}
+void _mm_clflush(void const *);
 
 /// \brief Forces strong memory ordering (serialization) between load
 ///    instructions preceding this instruction and load instructions following
@@ -2472,11 +2472,7 @@ _mm_clflush(void const *__p)
 ///
 /// This intrinsic corresponds to the \c LFENCE instruction.
 ///
-static __inline__ void __DEFAULT_FN_ATTRS
-_mm_lfence(void)
-{
-  __builtin_ia32_lfence();
-}
+void _mm_lfence(void);
 
 /// \brief Forces strong memory ordering (serialization) between load and store
 ///    instructions preceding this instruction and load and store instructions
@@ -2487,11 +2483,11 @@ _mm_lfence(void)
 ///
 /// This intrinsic corresponds to the \c MFENCE instruction.
 ///
-static __inline__ void __DEFAULT_FN_ATTRS
-_mm_mfence(void)
-{
-  __builtin_ia32_mfence();
-}
+void _mm_mfence(void);
+
+#if defined(__cplusplus)
+} // extern "C"
+#endif
 
 /// \brief Converts 16-bit signed integers from both 128-bit integer vector
 ///    operands into 8-bit signed integers, and packs the results into the
@@ -3213,11 +3209,10 @@ _mm_castsi128_pd(__m128i __a)
 ///
 /// This intrinsic corresponds to the \c PAUSE instruction.
 ///
-static __inline__ void __DEFAULT_FN_ATTRS
-_mm_pause(void)
-{
-  __builtin_ia32_pause();
-}
+#if defined(__cplusplus)
+extern "C"
+#endif
+void _mm_pause(void);
 
 #undef __DEFAULT_FN_ATTRS
 

diff --git a/lib/Headers/ia32intrin.h b/lib/Headers/ia32intrin.h
index 397f3fd13e010d3cd869af09a67a0c10b08fbe2c..4928300103adc639cbc9976b36687a028431941d 100644 (file)
--- a/lib/Headers/ia32intrin.h
+++ b/lib/Headers/ia32intrin.h
@@ -60,12 +60,6 @@ __rdpmc(int __A) {
   return __builtin_ia32_rdpmc(__A);
 }
 
-/* __rdtsc */
-static __inline__ unsigned long long __attribute__((__always_inline__, __nodebug__))
-__rdtsc(void) {
-  return __builtin_ia32_rdtsc();
-}
-
 /* __rdtscp */
 static __inline__ unsigned long long __attribute__((__always_inline__, __nodebug__))
 __rdtscp(unsigned int *__A) {

diff --git a/lib/Headers/intrin.h b/lib/Headers/intrin.h
index c19202eb6138873c653855079cacb49f6a1b629d..ed2032f35e5fad7758648ff114b9805ba1316043 100644 (file)
--- a/lib/Headers/intrin.h
+++ b/lib/Headers/intrin.h
@@ -463,14 +463,6 @@ _BitScanReverse(unsigned long *_Index, unsigned long _Mask) {
   *_Index = 31 - __builtin_clzl(_Mask);
   return 1;
 }
-static __inline__ unsigned short __DEFAULT_FN_ATTRS
-__popcnt16(unsigned short _Value) {
-  return __builtin_popcount((int)_Value);
-}
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__popcnt(unsigned int _Value) {
-  return __builtin_popcount(_Value);
-}
 static __inline__ unsigned char __DEFAULT_FN_ATTRS
 _bittest(long const *_BitBase, long _BitPos) {
   return (*_BitBase >> _BitPos) & 1;
@@ -513,11 +505,6 @@ _BitScanReverse64(unsigned long *_Index, unsigned __int64 _Mask) {
   *_Index = 63 - __builtin_clzll(_Mask);
   return 1;
 }
-static __inline__
-unsigned __int64 __DEFAULT_FN_ATTRS
-__popcnt64(unsigned __int64 _Value) {
-  return __builtin_popcountll(_Value);
-}
 static __inline__ unsigned char __DEFAULT_FN_ATTRS
 _bittest64(__int64 const *_BitBase, __int64 _BitPos) {
   return (*_BitBase >> _BitPos) & 1;
@@ -546,63 +533,63 @@ _interlockedbittestandset64(__int64 volatile *_BitBase, __int64 _BitPos) {
       __atomic_fetch_or(_BitBase, 1ll << _BitPos, __ATOMIC_SEQ_CST);
   return (_PrevVal >> _BitPos) & 1;
 }
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked Exchange Add\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedExchangeAdd64(__int64 volatile *_Addend, __int64 _Value) {\r
-       return __atomic_fetch_add(_Addend, _Value, __ATOMIC_SEQ_CST);\r
-}\r
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked Exchange Sub\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedExchangeSub64(__int64 volatile *_Subend, __int64 _Value) {\r
-       return __atomic_fetch_sub(_Subend, _Value, __ATOMIC_SEQ_CST);\r
-}\r
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked Increment\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedIncrement64(__int64 volatile *_Value) {\r
-       return __atomic_add_fetch(_Value, 1, __ATOMIC_SEQ_CST);\r
-}\r
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked Decrement\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedDecrement64(__int64 volatile *_Value) {\r
-       return __atomic_sub_fetch(_Value, 1, __ATOMIC_SEQ_CST);\r
-}\r
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked And\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedAnd64(__int64 volatile *_Value, __int64 _Mask) {\r
-       return __atomic_fetch_and(_Value, _Mask, __ATOMIC_SEQ_CST);\r
-}\r
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked Or\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedOr64(__int64 volatile *_Value, __int64 _Mask) {\r
-       return __atomic_fetch_or(_Value, _Mask, __ATOMIC_SEQ_CST);\r
-}\r
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked Xor\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedXor64(__int64 volatile *_Value, __int64 _Mask) {\r
-       return __atomic_fetch_xor(_Value, _Mask, __ATOMIC_SEQ_CST);\r
-}\r
-/*----------------------------------------------------------------------------*\\r
-|* Interlocked Exchange\r
-\*----------------------------------------------------------------------------*/\r
-static __inline__ __int64 __DEFAULT_FN_ATTRS\r
-_InterlockedExchange64(__int64 volatile *_Target, __int64 _Value) {\r
-       __atomic_exchange(_Target, &_Value, &_Value, __ATOMIC_SEQ_CST);\r
-       return _Value;\r
-}\r
+/*----------------------------------------------------------------------------*\
+|* Interlocked Exchange Add
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedExchangeAdd64(__int64 volatile *_Addend, __int64 _Value) {
+       return __atomic_fetch_add(_Addend, _Value, __ATOMIC_SEQ_CST);
+}
+/*----------------------------------------------------------------------------*\
+|* Interlocked Exchange Sub
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedExchangeSub64(__int64 volatile *_Subend, __int64 _Value) {
+       return __atomic_fetch_sub(_Subend, _Value, __ATOMIC_SEQ_CST);
+}
+/*----------------------------------------------------------------------------*\
+|* Interlocked Increment
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedIncrement64(__int64 volatile *_Value) {
+       return __atomic_add_fetch(_Value, 1, __ATOMIC_SEQ_CST);
+}
+/*----------------------------------------------------------------------------*\
+|* Interlocked Decrement
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedDecrement64(__int64 volatile *_Value) {
+       return __atomic_sub_fetch(_Value, 1, __ATOMIC_SEQ_CST);
+}
+/*----------------------------------------------------------------------------*\
+|* Interlocked And
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedAnd64(__int64 volatile *_Value, __int64 _Mask) {
+       return __atomic_fetch_and(_Value, _Mask, __ATOMIC_SEQ_CST);
+}
+/*----------------------------------------------------------------------------*\
+|* Interlocked Or
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedOr64(__int64 volatile *_Value, __int64 _Mask) {
+       return __atomic_fetch_or(_Value, _Mask, __ATOMIC_SEQ_CST);
+}
+/*----------------------------------------------------------------------------*\
+|* Interlocked Xor
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedXor64(__int64 volatile *_Value, __int64 _Mask) {
+       return __atomic_fetch_xor(_Value, _Mask, __ATOMIC_SEQ_CST);
+}
+/*----------------------------------------------------------------------------*\
+|* Interlocked Exchange
+\*----------------------------------------------------------------------------*/
+static __inline__ __int64 __DEFAULT_FN_ATTRS
+_InterlockedExchange64(__int64 volatile *_Target, __int64 _Value) {
+       __atomic_exchange(_Target, &_Value, &_Value, __ATOMIC_SEQ_CST);
+       return _Value;
+}
 #endif
 /*----------------------------------------------------------------------------*\
 |* Barriers

diff --git a/lib/Headers/xmmintrin.h b/lib/Headers/xmmintrin.h
index 373fc76aa7c4523f2ae80ca0edfb7372ffcfab1a..2d86482f9f83f4039f2b11359a17a8ffb5390755 100644 (file)
--- a/lib/Headers/xmmintrin.h
+++ b/lib/Headers/xmmintrin.h
@@ -2094,11 +2094,10 @@ _mm_stream_ps(float *__p, __m128 __a)
 ///
 /// This intrinsic corresponds to the \c SFENCE instruction.
 ///
-static __inline__ void __DEFAULT_FN_ATTRS
-_mm_sfence(void)
-{
-  __builtin_ia32_sfence();
-}
+#if defined(__cplusplus)
+extern "C"
+#endif
+void _mm_sfence(void);
 
 /// \brief Extracts 16-bit element from a 64-bit vector of [4 x i16] and
 ///    returns it, as specified by the immediate integer operand.
@@ -2376,6 +2375,10 @@ _mm_sad_pu8(__m64 __a, __m64 __b)
   return (__m64)__builtin_ia32_psadbw((__v8qi)__a, (__v8qi)__b);
 }
 
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
 /// \brief Returns the contents of the MXCSR register as a 32-bit unsigned
 ///    integer value. There are several groups of macros associated with this
 ///    intrinsic, including:
@@ -2408,11 +2411,7 @@ _mm_sad_pu8(__m64 __a, __m64 __b)
 ///
 /// \returns A 32-bit unsigned integer containing the contents of the MXCSR
 ///    register.
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_mm_getcsr(void)
-{
-  return __builtin_ia32_stmxcsr();
-}
+unsigned int _mm_getcsr(void);
 
 /// \brief Sets the MXCSR register with the 32-bit unsigned integer value. There
 ///    are several groups of macros associated with this intrinsic, including:
@@ -2450,11 +2449,11 @@ _mm_getcsr(void)
 ///
 /// \param __i
 ///    A 32-bit unsigned integer value to be written to the MXCSR register.
-static __inline__ void __DEFAULT_FN_ATTRS
-_mm_setcsr(unsigned int __i)
-{
-  __builtin_ia32_ldmxcsr(__i);
-}
+void _mm_setcsr(unsigned int);
+
+#if defined(__cplusplus)
+} // extern "C"
+#endif
 
 /// \brief Selects 4 float values from the 128-bit operands of [4 x float], as
 ///    specified by the immediate value operand.

diff --git a/lib/Sema/SemaDecl.cpp b/lib/Sema/SemaDecl.cpp
index 67a3497efb44130a1ddfb98f4e76556903fbb46c..f7b67658e60e09624370ae42992be3c35bb21f2e 100644 (file)
--- a/lib/Sema/SemaDecl.cpp
+++ b/lib/Sema/SemaDecl.cpp
@@ -1791,7 +1791,9 @@ NamedDecl *Sema::LazilyCreateBuiltin(IdentifierInfo *II, unsigned ID,
     return nullptr;
   }
 
-  if (!ForRedeclaration && Context.BuiltinInfo.isPredefinedLibFunction(ID)) {
+  if (!ForRedeclaration &&
+      (Context.BuiltinInfo.isPredefinedLibFunction(ID) ||
+       Context.BuiltinInfo.isHeaderDependentFunction(ID))) {
     Diag(Loc, diag::ext_implicit_lib_function_decl)
         << Context.BuiltinInfo.getName(ID) << R;
     if (Context.BuiltinInfo.getHeaderName(ID) &&

diff --git a/test/CodeGen/builtins-x86.c b/test/CodeGen/builtins-x86.c
index 8fa24e668f74631f54f3baa8607afa66075be3e1..ec8a8bf868c525f153d3f45a435aa23e32083ca3 100644 (file)
--- a/test/CodeGen/builtins-x86.c
+++ b/test/CodeGen/builtins-x86.c
@@ -262,7 +262,9 @@ void f0() {
   tmp_i = __builtin_ia32_vec_ext_v2si(tmp_V2i, 0);
 
   (void) __builtin_ia32_ldmxcsr(tmp_Ui);
+  (void) _mm_setcsr(tmp_Ui);
   tmp_Ui = __builtin_ia32_stmxcsr();
+  tmp_Ui = _mm_getcsr();
   (void)__builtin_ia32_fxsave(tmp_vp);
   (void)__builtin_ia32_fxsave64(tmp_vp);
   (void)__builtin_ia32_fxrstor(tmp_vp);
@@ -290,6 +292,7 @@ void f0() {
   tmp_i = __builtin_ia32_cvttss2si(tmp_V4f);
 
   tmp_i = __builtin_ia32_rdtsc();
+  tmp_i = __rdtsc();
   tmp_i = __builtin_ia32_rdtscp(&tmp_Ui);
   tmp_LLi = __builtin_ia32_rdpmc(tmp_i);
 #ifdef USE_64
@@ -304,6 +307,7 @@ void f0() {
   tmp_i = __builtin_ia32_pmovmskb(tmp_V8c);
   (void) __builtin_ia32_movntq(tmp_V1LLip, tmp_V1LLi);
   (void) __builtin_ia32_sfence();
+  (void) _mm_sfence();
 
   tmp_V4s = __builtin_ia32_psadbw(tmp_V8c, tmp_V8c);
   tmp_V4f = __builtin_ia32_rcpps(tmp_V4f);
@@ -339,8 +343,13 @@ void f0() {
   tmp_V4i = __builtin_ia32_cvtps2dq(tmp_V4f);
   tmp_V4i = __builtin_ia32_cvttps2dq(tmp_V4f);
   (void) __builtin_ia32_clflush(tmp_vCp);
+  (void) _mm_clflush(tmp_vCp);
   (void) __builtin_ia32_lfence();
+  (void) _mm_lfence();
   (void) __builtin_ia32_mfence();
+  (void) _mm_mfence();
+  (void) __builtin_ia32_pause();
+  (void) _mm_pause();
   tmp_V4s = __builtin_ia32_psllwi(tmp_V4s, tmp_i);
   tmp_V2i = __builtin_ia32_pslldi(tmp_V2i, tmp_i);
   tmp_V1LLi = __builtin_ia32_psllqi(tmp_V1LLi, tmp_i);

diff --git a/test/Headers/x86intrin.cpp b/test/Headers/x86intrin.cpp
new file mode 100644 (file)
index 0000000..11d442d
--- /dev/null
+++ b/test/Headers/x86intrin.cpp
@@ -0,0 +1,11 @@
+// RUN: %clang_cc1 -fsyntax-only -ffreestanding %s -verify
+// expected-no-diagnostics
+
+#if defined(i386) || defined(__x86_64__)
+
+// Include the metaheader that includes all x86 intrinsic headers.
+extern "C++" {
+#include <x86intrin.h>
+}
+
+#endif

diff --git a/test/Sema/implicit-intel-builtin-decl.c b/test/Sema/implicit-intel-builtin-decl.c
new file mode 100644 (file)
index 0000000..e588a4b
--- /dev/null
+++ b/test/Sema/implicit-intel-builtin-decl.c
@@ -0,0 +1,40 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -target-feature +sse2 -fsyntax-only -verify %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -target-feature +sse2 -fsyntax-only -verify %s -x c++
+
+void f() {
+  (void)_mm_getcsr(); // expected-warning{{implicitly declaring library function '_mm_getcsr'}} \
+  // expected-note{{include the header <xmmintrin.h> or explicitly provide a declaration for '_mm_getcsr'}}
+  _mm_setcsr(1); // expected-warning{{implicitly declaring library function '_mm_setcsr'}} \
+  // expected-note{{include the header <xmmintrin.h> or explicitly provide a declaration for '_mm_setcsr'}}
+  _mm_sfence(); // expected-warning{{implicitly declaring library function '_mm_sfence'}} \
+  // expected-note{{include the header <xmmintrin.h> or explicitly provide a declaration for '_mm_sfence'}}
+
+  _mm_clflush((void*)0); // expected-warning{{implicitly declaring library function '_mm_clflush'}} \
+  // expected-note{{include the header <emmintrin.h> or explicitly provide a declaration for '_mm_clflush'}}
+  _mm_lfence(); // expected-warning{{implicitly declaring library function '_mm_lfence'}} \
+  // expected-note{{include the header <emmintrin.h> or explicitly provide a declaration for '_mm_lfence'}}
+  _mm_mfence(); // expected-warning{{implicitly declaring library function '_mm_mfence'}} \
+  // expected-note{{include the header <emmintrin.h> or explicitly provide a declaration for '_mm_mfence'}}
+  _mm_pause(); // expected-warning{{implicitly declaring library function '_mm_pause'}} \
+  // expected-note{{include the header <emmintrin.h> or explicitly provide a declaration for '_mm_pause'}}
+}
+
+unsigned int _mm_getcsr();
+void _mm_setcsr(unsigned int);
+void _mm_sfence();
+
+void _mm_clflush(void const *);
+void _mm_lfence();
+void _mm_mfence();
+void _mm_pause();
+
+void g() {
+  (void)_mm_getcsr();
+  _mm_setcsr(1);
+  _mm_sfence();
+
+  _mm_clflush((void*)0);
+  _mm_lfence();
+  _mm_mfence();
+  _mm_pause();
+}

diff --git a/test/Sema/implicit-ms-builtin-decl.c b/test/Sema/implicit-ms-builtin-decl.c
new file mode 100644 (file)
index 0000000..e43d8f8
--- /dev/null
+++ b/test/Sema/implicit-ms-builtin-decl.c
@@ -0,0 +1,19 @@
+// RUN: %clang_cc1 -fsyntax-only -verify %s -fms-extensions
+
+void f() {
+  (void)_byteswap_ushort(42); // expected-warning{{implicitly declaring library function '_byteswap_ushort}} \
+  // expected-note{{include the header <stdlib.h> or explicitly provide a declaration for '_byteswap_ushort'}}
+  (void)_byteswap_uint64(42LL); // expected-warning{{implicitly declaring library function '_byteswap_uint64}} \
+  // expected-note{{include the header <stdlib.h> or explicitly provide a declaration for '_byteswap_uint64'}}
+}
+
+void _byteswap_ulong(); // expected-warning{{incompatible redeclaration of library function '_byteswap_ulong'}} \
+// expected-note{{'_byteswap_ulong' is a builtin}}
+
+unsigned short _byteswap_ushort(unsigned short);
+unsigned long long _byteswap_uint64(unsigned long long);
+
+void g() {
+  (void)_byteswap_ushort(42);
+  (void)_byteswap_uint64(42LL);
+}