Index: include/clang/Basic/Builtins.h =================================================================== --- include/clang/Basic/Builtins.h +++ include/clang/Basic/Builtins.h @@ -139,6 +139,13 @@ 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. Index: include/clang/Basic/Builtins.def =================================================================== --- include/clang/Basic/Builtins.def +++ 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 @@ // 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) @@ -724,6 +728,9 @@ LANGBUILTIN(_InterlockedExchangePointer, "v*v*D*v*", "n", ALL_MS_LANGUAGES) LANGBUILTIN(_InterlockedIncrement, "LiLiD*", "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(__va_start, "vc**.", "nt", ALL_MS_LANGUAGES) Index: include/clang/Basic/BuiltinsX86.def =================================================================== --- include/clang/Basic/BuiltinsX86.def +++ 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_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_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_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 @@ 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 @@ #undef BUILTIN #undef TARGET_BUILTIN +#undef TARGET_HEADER_BUILTIN Index: lib/Basic/Targets.cpp =================================================================== --- lib/Basic/Targets.cpp +++ lib/Basic/Targets.cpp @@ -2301,6 +2301,8 @@ { #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" }; Index: lib/CodeGen/CGBuiltin.cpp =================================================================== --- lib/CodeGen/CGBuiltin.cpp +++ lib/CodeGen/CGBuiltin.cpp @@ -681,6 +681,9 @@ "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: { @@ -6880,6 +6883,25 @@ 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: @@ -6892,12 +6914,14 @@ 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), Index: lib/Headers/emmintrin.h =================================================================== --- lib/Headers/emmintrin.h +++ lib/Headers/emmintrin.h @@ -2457,11 +2457,7 @@ /// \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 +2468,7 @@ /// /// 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 +2479,7 @@ /// /// This intrinsic corresponds to the \c MFENCE instruction. /// -static __inline__ void __DEFAULT_FN_ATTRS -_mm_mfence(void) -{ - __builtin_ia32_mfence(); -} +void _mm_mfence(void); /// \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 +3201,7 @@ /// /// This intrinsic corresponds to the \c PAUSE instruction. /// -static __inline__ void __DEFAULT_FN_ATTRS -_mm_pause(void) -{ - __builtin_ia32_pause(); -} +void _mm_pause(void); #undef __DEFAULT_FN_ATTRS Index: lib/Headers/ia32intrin.h =================================================================== --- lib/Headers/ia32intrin.h +++ lib/Headers/ia32intrin.h @@ -60,12 +60,6 @@ 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) { Index: lib/Headers/intrin.h =================================================================== --- lib/Headers/intrin.h +++ lib/Headers/intrin.h @@ -518,14 +518,6 @@ *_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; @@ -568,11 +560,6 @@ *_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; Index: lib/Headers/xmmintrin.h =================================================================== --- lib/Headers/xmmintrin.h +++ lib/Headers/xmmintrin.h @@ -2094,11 +2094,7 @@ /// /// This intrinsic corresponds to the \c SFENCE instruction. /// -static __inline__ void __DEFAULT_FN_ATTRS -_mm_sfence(void) -{ - __builtin_ia32_sfence(); -} +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. @@ -2408,11 +2404,7 @@ /// /// \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 +2442,7 @@ /// /// \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); /// \brief Selects 4 float values from the 128-bit operands of [4 x float], as /// specified by the immediate value operand. Index: lib/Sema/SemaDecl.cpp =================================================================== --- lib/Sema/SemaDecl.cpp +++ lib/Sema/SemaDecl.cpp @@ -1791,7 +1791,9 @@ 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) && Index: test/CodeGen/builtins-x86.c =================================================================== --- test/CodeGen/builtins-x86.c +++ test/CodeGen/builtins-x86.c @@ -262,7 +262,9 @@ 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 @@ 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 @@ 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 @@ 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); Index: test/Sema/implicit-intel-builtin-decl.c =================================================================== --- /dev/null +++ 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 or explicitly provide a declaration for '_mm_getcsr'}} + _mm_setcsr(1); // expected-warning{{implicitly declaring library function '_mm_setcsr'}} \ + // expected-note{{include the header or explicitly provide a declaration for '_mm_setcsr'}} + _mm_sfence(); // expected-warning{{implicitly declaring library function '_mm_sfence'}} \ + // expected-note{{include the header 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 or explicitly provide a declaration for '_mm_clflush'}} + _mm_lfence(); // expected-warning{{implicitly declaring library function '_mm_lfence'}} \ + // expected-note{{include the header or explicitly provide a declaration for '_mm_lfence'}} + _mm_mfence(); // expected-warning{{implicitly declaring library function '_mm_mfence'}} \ + // expected-note{{include the header or explicitly provide a declaration for '_mm_mfence'}} + _mm_pause(); // expected-warning{{implicitly declaring library function '_mm_pause'}} \ + // expected-note{{include the header 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(); +} Index: test/Sema/implicit-ms-builtin-decl.c =================================================================== --- /dev/null +++ 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 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 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); +}