[X86] Make _xgetbv/_xsetbv on non-windows platforms

[craig.topper]

Summary

This patch attempts to redo what was tried in r278783, but was reverted.

These intrinsics should be available on non-windows platforms with "xsave" feature check. But on Windows platforms they shouldn't have feature check since that's how MSVC behaves.

To accomplish this I've added a MS builtin with no feature check. And a normal gcc builtin with a feature check. When _MSC_VER is not defined _xgetbv/_xsetbv will be macros pointing to the gcc builtin name.

I've moved the forward declarations from intrin.h to immintrin.h to match the MSDN documentation and used that as the header file for the MS builtin.

I'm not super happy with this implementation, and I'm open to suggestions for better ways to do it.

[rnk]

lib/Headers/immintrin.h

381–394

I think we should try to simplify immintrin.h and push this complexity into xsaveintrin.h. Since it is small (i.e. not avx512intrin.h), we don't really need this !defined(_MSC_VER) || __has_feature(modules) check to improve compile time. If you rewrite it to:

#if defined(_MSC_VER) || defined(__XSAVE__)
#include <xsaveintrin.h>
#endif

Then xsaveintrin.h can do the XSAVE macro feature check internally.

test/Headers/ms-intrin.cpp

37

Surely __movsb and __readmsr should all be x86-only as well, at least according to MSDN?

[craig.topper]

Remove guard from include of xsaveintrin.h. We can't have any check because we need it to always include on non-windows platforms due to target attribute.

[craig.topper]

test/Headers/ms-intrin.cpp

37

I'm sure that's true, but I think thats a separate issue with the forward declarations in intrin.h

[rnk]

lgtm

include/clang/Basic/BuiltinsX86.def

 
 // FXSR
 TARGET_BUILTIN(__builtin_ia32_fxrstor, "vv*", "n", "fxsr")
 TARGET_BUILTIN(__builtin_ia32_fxsave, "vv*", "n", "fxsr")
 
 // XSAVE
 TARGET_BUILTIN(__builtin_ia32_xsave, "vv*ULLi", "n", "xsave")
 TARGET_BUILTIN(__builtin_ia32_xrstor, "vv*ULLi", "n", "xsave")
+TARGET_BUILTIN(__builtin_ia32_xgetbv, "ULLiUi", "n", "xsave")
+TARGET_HEADER_BUILTIN(_xgetbv, "UWiUi", "nh", "immintrin.h", ALL_MS_LANGUAGES, "")
+TARGET_BUILTIN(__builtin_ia32_xsetbv, "vUiULLi", "n", "xsave")
+TARGET_HEADER_BUILTIN(_xsetbv, "vUiUWi", "nh", "immintrin.h", ALL_MS_LANGUAGES, "")
 TARGET_BUILTIN(__builtin_ia32_xsaveopt, "vv*ULLi", "n", "xsaveopt")
 TARGET_BUILTIN(__builtin_ia32_xrstors, "vv*ULLi", "n", "xsaves")
 TARGET_BUILTIN(__builtin_ia32_xsavec, "vv*ULLi", "n", "xsavec")
 TARGET_BUILTIN(__builtin_ia32_xsaves, "vv*ULLi", "n", "xsaves")
 
 // SHSTK
 TARGET_BUILTIN(__builtin_ia32_incsspd, "vUi", "n", "shstk")
 TARGET_BUILTIN(__builtin_ia32_rdsspd, "UiUi", "n", "shstk")

lib/CodeGen/CGBuiltin.cpp

Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
   case X86::BI__builtin_ia32_xrstor64:
   case X86::BI__builtin_ia32_xsaveopt:
   case X86::BI__builtin_ia32_xsaveopt64:
   case X86::BI__builtin_ia32_xrstors:
   case X86::BI__builtin_ia32_xrstors64:
   case X86::BI__builtin_ia32_xsavec:
   case X86::BI__builtin_ia32_xsavec64:
   case X86::BI__builtin_ia32_xsaves:
-  case X86::BI__builtin_ia32_xsaves64: {
+  case X86::BI__builtin_ia32_xsaves64:
+  case X86::BI__builtin_ia32_xsetbv:
+  case X86::BI_xsetbv: {
     Intrinsic::ID ID;
 #define INTRINSIC_X86_XSAVE_ID(NAME) \
     case X86::BI__builtin_ia32_##NAME: \
       ID = Intrinsic::x86_##NAME; \
       break
     switch (BuiltinID) {
     default: llvm_unreachable("Unsupported intrinsic!");
     INTRINSIC_X86_XSAVE_ID(xsave);
     INTRINSIC_X86_XSAVE_ID(xsave64);
     INTRINSIC_X86_XSAVE_ID(xrstor);
     INTRINSIC_X86_XSAVE_ID(xrstor64);
     INTRINSIC_X86_XSAVE_ID(xsaveopt);
     INTRINSIC_X86_XSAVE_ID(xsaveopt64);
     INTRINSIC_X86_XSAVE_ID(xrstors);
     INTRINSIC_X86_XSAVE_ID(xrstors64);
     INTRINSIC_X86_XSAVE_ID(xsavec);
     INTRINSIC_X86_XSAVE_ID(xsavec64);
     INTRINSIC_X86_XSAVE_ID(xsaves);
     INTRINSIC_X86_XSAVE_ID(xsaves64);
+    INTRINSIC_X86_XSAVE_ID(xsetbv);
+    case X86::BI_xsetbv:
+      ID = Intrinsic::x86_xsetbv;
+      break;
     }
 #undef INTRINSIC_X86_XSAVE_ID
     Value *Mhi = Builder.CreateTrunc(
       Builder.CreateLShr(Ops[1], ConstantInt::get(Int64Ty, 32)), Int32Ty);
     Value *Mlo = Builder.CreateTrunc(Ops[1], Int32Ty);
     Ops[1] = Mhi;
     Ops.push_back(Mlo);
     return Builder.CreateCall(CGM.getIntrinsic(ID), Ops);
   }
+  case X86::BI__builtin_ia32_xgetbv:
+  case X86::BI_xgetbv:
+    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_xgetbv), Ops);
   case X86::BI__builtin_ia32_storedqudi128_mask:
   case X86::BI__builtin_ia32_storedqusi128_mask:
   case X86::BI__builtin_ia32_storedquhi128_mask:
   case X86::BI__builtin_ia32_storedquqi128_mask:
   case X86::BI__builtin_ia32_storeupd128_mask:
   case X86::BI__builtin_ia32_storeups128_mask:
   case X86::BI__builtin_ia32_storedqudi256_mask:
   case X86::BI__builtin_ia32_storedqusi256_mask:

lib/Headers/immintrin.h

 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__SHA__)
 #include <shaintrin.h>
 #endif
 
 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__FXSR__)
 #include <fxsrintrin.h>
 #endif
 
-#if !defined(_MSC_VER) || __has_feature(modules) || defined(__XSAVE__)
+/* No feature check desired due to internal MSC_VER checks */
 #include <xsaveintrin.h>
-#endif
 
 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__XSAVEOPT__)
 #include <xsaveoptintrin.h>
 #endif
 
 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__XSAVEC__)
 #include <xsavecintrin.h>
 #endif
 
 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__XSAVES__)
 #include <xsavesintrin.h>
 #endif
 
 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__SHSTK__)
 #include <cetintrin.h>
 #endif
 
 /* Some intrinsics inside adxintrin.h are available only on processors with ADX,
  * whereas others are also available at all times. */
 #include <adxintrin.h>

lib/Headers/intrin.h

 void _Store_HLERelease(long volatile *, long);
 void _Store64_HLERelease(__int64 volatile *, __int64);
 void _StorePointer_HLERelease(void *volatile *, void *);
 static __inline__ void
 __attribute__((__deprecated__("use other intrinsics or C++11 atomics instead")))
 _WriteBarrier(void);
 unsigned __int32 xbegin(void);
 void _xend(void);
-static __inline__
 #define _XCR_XFEATURE_ENABLED_MASK 0
-unsigned __int64 __cdecl _xgetbv(unsigned int);
-void __cdecl _xsetbv(unsigned int, unsigned __int64);
 
 /* These additional intrinsics are turned on in x64/amd64/x86_64 mode. */
 #ifdef __x86_64__
 void __addgsbyte(unsigned long, unsigned char);
 void __addgsdword(unsigned long, unsigned long);
 void __addgsqword(unsigned long, unsigned __int64);
 void __addgsword(unsigned long, unsigned short);
 static __inline__
__cpuid(int __info[4], int __level) {
   __asm__ ("cpuid" : "=a"(__info[0]), "=b" (__info[1]), "=c"(__info[2]), "=d"(__info[3])
                    : "a"(__level), "c"(0));
 }
 static __inline__ void __DEFAULT_FN_ATTRS
 __cpuidex(int __info[4], int __level, int __ecx) {
   __asm__ ("cpuid" : "=a"(__info[0]), "=b" (__info[1]), "=c"(__info[2]), "=d"(__info[3])
                    : "a"(__level), "c"(__ecx));
 }
-static __inline__ unsigned __int64 __cdecl __DEFAULT_FN_ATTRS
-_xgetbv(unsigned int __xcr_no) {
-  unsigned int __eax, __edx;
-  __asm__ ("xgetbv" : "=a" (__eax), "=d" (__edx) : "c" (__xcr_no));
-  return ((unsigned __int64)__edx << 32) | __eax;
-}
 static __inline__ void __DEFAULT_FN_ATTRS
 __halt(void) {
   __asm__ volatile ("hlt");
 }
 #endif
 
 #if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
 static __inline__ void __DEFAULT_FN_ATTRS

lib/Headers/xsaveintrin.h

 
 #ifndef __IMMINTRIN_H
 #error "Never use <xsaveintrin.h> directly; include <immintrin.h> instead."
 #endif
 
 #ifndef __XSAVEINTRIN_H
 #define __XSAVEINTRIN_H
 
+#ifndef _MSC_VER
+#define _XCR_XFEATURE_ENABLED_MASK 0
+#endif
+
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__,  __target__("xsave")))
 
 static __inline__ void __DEFAULT_FN_ATTRS
 _xsave(void *__p, unsigned long long __m) {
   __builtin_ia32_xsave(__p, __m);
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
 _xrstor(void *__p, unsigned long long __m) {
   __builtin_ia32_xrstor(__p, __m);
 }
 
+#ifndef _MSC_VER
+#define _xgetbv(A) __builtin_ia32_xgetbv((long long)(A))
+#define _xsetbv(A, B) __builtin_ia32_xsetbv((unsigned int)(A), (unsigned long long)(B));
+#else
+#ifdef __cplusplus
+extern "C" {
+#endif
+unsigned __int64 __cdecl _xgetbv(unsigned int);
+void __cdecl _xsetbv(unsigned int, unsigned __int64);
+#ifdef __cplusplus
+}
+#endif
+#endif /* _MSC_VER */
+
 #ifdef __x86_64__
 static __inline__ void __DEFAULT_FN_ATTRS
 _xsave64(void *__p, unsigned long long __m) {
   __builtin_ia32_xsave64(__p, __m);
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
 _xrstor64(void *__p, unsigned long long __m) {
   __builtin_ia32_xrstor64(__p, __m);
 }
+
 #endif
 
 #undef __DEFAULT_FN_ATTRS
 
 #endif

test/CodeGen/builtins-x86.c

#endif
   tmp_Ui = _mm_getcsr();
   (void)__builtin_ia32_fxsave(tmp_vp);
   (void)__builtin_ia32_fxsave64(tmp_vp);
   (void)__builtin_ia32_fxrstor(tmp_vp);
   (void)__builtin_ia32_fxrstor64(tmp_vp);
 
   (void)__builtin_ia32_xsave(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xsave64(tmp_vp, tmp_ULLi);
+  tmp_ULLi = __builtin_ia32_xgetbv(tmp_Ui);
+  (void)__builtin_ia32_xsetbv(tmp_Ui, tmp_ULLi);
   (void)__builtin_ia32_xrstor(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xrstor64(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xsaveopt(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xsaveopt64(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xrstors(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xrstors64(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xsavec(tmp_vp, tmp_ULLi);
   (void)__builtin_ia32_xsavec64(tmp_vp, tmp_ULLi);

test/CodeGen/x86_32-xsave.c

 // RUN: %clang_cc1 %s -DTEST_XSAVE -O0 -triple=i686-unknown-unknown -target-feature +xsave -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVE
 // RUN: %clang_cc1 %s -DTEST_XSAVE -O0 -triple=i686-unknown-unknown -target-feature +xsave -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVE
 
+// RUN: %clang_cc1 %s -DTEST_XGETBV -O0 -triple=i686-unknown-unknown -target-feature +xsave -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XGETBV
+// RUN: %clang_cc1 %s -DTEST_XSETBV -O0 -triple=i686-unknown-unknown -target-feature +xsave -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSETBV
+
 // RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=i686-unknown-unknown -target-feature +xsave -target-feature +xsaveopt -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEOPT
 // RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=i686-unknown-unknown -target-feature +xsave -target-feature +xsaveopt -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEOPT
 
 // RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=i686-unknown-unknown -target-feature +xsave -target-feature +xsavec -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEC
 // RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=i686-unknown-unknown -target-feature +xsave -target-feature +xsavec -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEC
 
 // RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=i686-unknown-unknown -target-feature +xsave -target-feature +xsaves -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVES
 // RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=i686-unknown-unknown -target-feature +xsave -target-feature +xsaves -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVES
 
+// Don't include mm_malloc.h, it's system specific.
+#define __MM_MALLOC_H
+#include <x86intrin.h>
+
 void test() {
-  unsigned long long tmp_ULLi = 0;
-  void*              tmp_vp = 0;
+  unsigned long long tmp_ULLi;
+  unsigned int       tmp_Ui;
+  void*              tmp_vp;
+  tmp_ULLi = 0; tmp_Ui = 0; tmp_vp = 0;
 
 #ifdef TEST_XSAVE
 // XSAVE: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 4
 // XSAVE: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVE: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVE: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVE: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32
 // XSAVE: call void @llvm.x86.xsave(i8* [[tmp_vp_1]], i32 [[high32_1]], i32 [[low32_1]])
   (void)__builtin_ia32_xsave(tmp_vp, tmp_ULLi);
 
 // XSAVE: [[tmp_vp_3:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 4
 // XSAVE: [[tmp_ULLi_3:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVE: [[high64_3:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_3]], 32
 // XSAVE: [[high32_3:%[0-9a-zA-Z]+]] = trunc i64 [[high64_3]] to i32
 // XSAVE: [[low32_3:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_3]] to i32
 // XSAVE: call void @llvm.x86.xrstor(i8* [[tmp_vp_3]], i32 [[high32_3]], i32 [[low32_3]])
   (void)__builtin_ia32_xrstor(tmp_vp, tmp_ULLi);
+  
+// XSAVE: call void @llvm.x86.xsave
+  (void)_xsave(tmp_vp, tmp_ULLi);
+  
+// XSAVE: call void @llvm.x86.xrstor
+  (void)_xrstor(tmp_vp, tmp_ULLi);
 #endif
 
 #ifdef TEST_XSAVEOPT
 // XSAVEOPT: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 4
 // XSAVEOPT: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVEOPT: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVEOPT: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVEOPT: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32
 // XSAVEOPT: call void @llvm.x86.xsaveopt(i8* [[tmp_vp_1]], i32 [[high32_1]], i32 [[low32_1]])
   (void)__builtin_ia32_xsaveopt(tmp_vp, tmp_ULLi);
+  
+// XSAVEOPT: call void @llvm.x86.xsaveopt
+  (void)_xsaveopt(tmp_vp, tmp_ULLi);
 #endif
 
 #ifdef TEST_XSAVEC
 // XSAVEC: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 4
 // XSAVEC: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVEC: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVEC: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVEC: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32
 // XSAVEC: call void @llvm.x86.xsavec(i8* [[tmp_vp_1]], i32 [[high32_1]], i32 [[low32_1]])
   (void)__builtin_ia32_xsavec(tmp_vp, tmp_ULLi);
+ 
+// XSAVEC: call void @llvm.x86.xsavec 
+  (void)_xsavec(tmp_vp, tmp_ULLi);
 #endif
 
 #ifdef TEST_XSAVES
 // XSAVES: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 4
 // XSAVES: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVES: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVES: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVES: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32
 // XSAVES: call void @llvm.x86.xsaves(i8* [[tmp_vp_1]], i32 [[high32_1]], i32 [[low32_1]])
   (void)__builtin_ia32_xsaves(tmp_vp, tmp_ULLi);
 
 // XSAVES: [[tmp_vp_3:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 4
 // XSAVES: [[tmp_ULLi_3:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVES: [[high64_3:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_3]], 32
 // XSAVES: [[high32_3:%[0-9a-zA-Z]+]] = trunc i64 [[high64_3]] to i32
 // XSAVES: [[low32_3:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_3]] to i32
 // XSAVES: call void @llvm.x86.xrstors(i8* [[tmp_vp_3]], i32 [[high32_3]], i32 [[low32_3]])
   (void)__builtin_ia32_xrstors(tmp_vp, tmp_ULLi);
+  
+// XSAVES: call void @llvm.x86.xsaves
+  (void)_xsaves(tmp_vp, tmp_ULLi); 
+
+// XSAVES: call void @llvm.x86.xrstors
+  (void)_xrstors(tmp_vp, tmp_ULLi);
 #endif
+
+#ifdef TEST_XGETBV
+// XGETBV: [[tmp_Ui:%[0-9a-zA-z]+]] = load i32, i32* %tmp_Ui, align 4
+// XGETBV: call i64 @llvm.x86.xgetbv(i32 [[tmp_Ui]])
+  tmp_ULLi = __builtin_ia32_xgetbv(tmp_Ui);
+  
+// XGETBV: call i64 @llvm.x86.xgetbv
+  tmp_ULLi = _xgetbv(tmp_Ui);
+#endif
+
+#ifdef TEST_XSETBV
+// XSETBV: [[tmp_Ui:%[0-9a-zA-z]+]] = load i32, i32* %tmp_Ui, align 4
+// XSETBV: [[tmp_ULLi_3:%[0-9a-zA-z]+]] = load i64, i64* %tmp_ULLi, align 8
+// XSETBV: [[high64_3:%[0-9a-zA-z]+]] = lshr i64 [[tmp_ULLi_3]], 32
+// XSETBV: [[high32_3:%[0-9a-zA-z]+]] = trunc i64 [[high64_3]] to i32
+// XSETBV: [[low32_3:%[0-9a-zA-z]+]] = trunc i64 [[tmp_ULLi_3]] to i32
+// XSETBV: call void @llvm.x86.xsetbv(i32 [[tmp_Ui]], i32 [[high32_3]], i32 [[low32_3]])
+  (void)__builtin_ia32_xsetbv(tmp_Ui, tmp_ULLi);
+  
+  // XSETBV: call void @llvm.x86.xsetbv
+  (void)_xsetbv(tmp_Ui, tmp_ULLi);
+#endif
+
 }

test/CodeGen/x86_64-xsave.c

 // RUN: %clang_cc1 %s -DTEST_XSAVE -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVE
 // RUN: %clang_cc1 %s -DTEST_XSAVE -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVE
 
+// RUN: %clang_cc1 %s -DTEST_XGETBV -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XGETBV
+// RUN: %clang_cc1 %s -DTEST_XSETBV -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSETBV
+
 // RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -target-feature +xsaveopt -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEOPT
 // RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -target-feature +xsaveopt -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEOPT
 
 // RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -target-feature +xsavec -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEC
 // RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -target-feature +xsavec -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVEC
 
 // RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -target-feature +xsaves -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVES
 // RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -target-feature +xsaves -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefix=XSAVES
 
+// Don't include mm_malloc.h, it's system specific.
+#define __MM_MALLOC_H
+#include <x86intrin.h>
+
+
 void test() {
-  unsigned long long tmp_ULLi = 0;
-  void*              tmp_vp = 0;
+  unsigned long long tmp_ULLi;
+  unsigned int       tmp_Ui;
+  void*              tmp_vp;
+  tmp_ULLi = 0; tmp_Ui = 0; tmp_vp = 0;
 
 #ifdef TEST_XSAVE
 // XSAVE: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVE: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVE: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVE: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVE: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32
 // XSAVE: call void @llvm.x86.xsave(i8* [[tmp_vp_1]], i32 [[high32_1]], i32 [[low32_1]])

 
 // XSAVE: [[tmp_vp_4:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVE: [[tmp_ULLi_4:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVE: [[high64_4:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_4]], 32
 // XSAVE: [[high32_4:%[0-9a-zA-Z]+]] = trunc i64 [[high64_4]] to i32
 // XSAVE: [[low32_4:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_4]] to i32
 // XSAVE: call void @llvm.x86.xrstor64(i8* [[tmp_vp_4]], i32 [[high32_4]], i32 [[low32_4]])
   (void)__builtin_ia32_xrstor64(tmp_vp, tmp_ULLi);
+  
+// XSAVE: call void @llvm.x86.xsave
+  (void)_xsave(tmp_vp, tmp_ULLi);
+  
+// XSAVE: call void @llvm.x86.xsave64
+  (void)_xsave64(tmp_vp, tmp_ULLi);
+  
+// XSAVE: call void @llvm.x86.xrstor
+  (void)_xrstor(tmp_vp, tmp_ULLi);
+  
+// XSAVE: call void @llvm.x86.xrstor64
+  (void)_xrstor64(tmp_vp, tmp_ULLi);
 #endif
 
 #ifdef TEST_XSAVEOPT
 // XSAVEOPT: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVEOPT: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVEOPT: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVEOPT: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVEOPT: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32
 // XSAVEOPT: call void @llvm.x86.xsaveopt(i8* [[tmp_vp_1]], i32 [[high32_1]], i32 [[low32_1]])
   (void)__builtin_ia32_xsaveopt(tmp_vp, tmp_ULLi);
 
 // XSAVEOPT: [[tmp_vp_2:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVEOPT: [[tmp_ULLi_2:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVEOPT: [[high64_2:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_2]], 32
 // XSAVEOPT: [[high32_2:%[0-9a-zA-Z]+]] = trunc i64 [[high64_2]] to i32
 // XSAVEOPT: [[low32_2:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_2]] to i32
 // XSAVEOPT: call void @llvm.x86.xsaveopt64(i8* [[tmp_vp_2]], i32 [[high32_2]], i32 [[low32_2]])
   (void)__builtin_ia32_xsaveopt64(tmp_vp, tmp_ULLi);
+  
+// XSAVEOPT: call void @llvm.x86.xsaveopt
+  (void)_xsaveopt(tmp_vp, tmp_ULLi);
+  
+// XSAVEOPT: call void @llvm.x86.xsaveopt64
+  (void)_xsaveopt64(tmp_vp, tmp_ULLi);
 #endif
 
 #ifdef TEST_XSAVEC
 // XSAVEC: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVEC: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVEC: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVEC: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVEC: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32
 // XSAVEC: call void @llvm.x86.xsavec(i8* [[tmp_vp_1]], i32 [[high32_1]], i32 [[low32_1]])
   (void)__builtin_ia32_xsavec(tmp_vp, tmp_ULLi);
 
 // XSAVEC: [[tmp_vp_2:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVEC: [[tmp_ULLi_2:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVEC: [[high64_2:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_2]], 32
 // XSAVEC: [[high32_2:%[0-9a-zA-Z]+]] = trunc i64 [[high64_2]] to i32
 // XSAVEC: [[low32_2:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_2]] to i32
 // XSAVEC: call void @llvm.x86.xsavec64(i8* [[tmp_vp_2]], i32 [[high32_2]], i32 [[low32_2]])
   (void)__builtin_ia32_xsavec64(tmp_vp, tmp_ULLi);
+  
+// XSAVEC: call void @llvm.x86.xsavec 
+  (void)_xsavec(tmp_vp, tmp_ULLi);
+  
+// XSAVEC: call void @llvm.x86.xsavec64
+  (void)_xsavec64(tmp_vp, tmp_ULLi);
 #endif
 
 #ifdef TEST_XSAVES
 // XSAVES: [[tmp_vp_1:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVES: [[tmp_ULLi_1:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVES: [[high64_1:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_1]], 32
 // XSAVES: [[high32_1:%[0-9a-zA-Z]+]] = trunc i64 [[high64_1]] to i32
 // XSAVES: [[low32_1:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_1]] to i32

 
 // XSAVES: [[tmp_vp_4:%[0-9a-zA-Z]+]] = load i8*, i8** %tmp_vp, align 8
 // XSAVES: [[tmp_ULLi_4:%[0-9a-zA-Z]+]] = load i64, i64* %tmp_ULLi, align 8
 // XSAVES: [[high64_4:%[0-9a-zA-Z]+]] = lshr i64 [[tmp_ULLi_4]], 32
 // XSAVES: [[high32_4:%[0-9a-zA-Z]+]] = trunc i64 [[high64_4]] to i32
 // XSAVES: [[low32_4:%[0-9a-zA-Z]+]] = trunc i64 [[tmp_ULLi_4]] to i32
 // XSAVES: call void @llvm.x86.xrstors64(i8* [[tmp_vp_4]], i32 [[high32_4]], i32 [[low32_4]])
   (void)__builtin_ia32_xrstors64(tmp_vp, tmp_ULLi);
+  
+// XSAVES: call void @llvm.x86.xsaves
+  (void)_xsaves(tmp_vp, tmp_ULLi); 
+  
+// XSAVES: call void @llvm.x86.xsaves64
+  (void)_xsaves64(tmp_vp, tmp_ULLi); 
+
+// XSAVES: call void @llvm.x86.xrstors
+  (void)_xrstors(tmp_vp, tmp_ULLi);
+  
+// XSAVES: call void @llvm.x86.xrstors64
+  (void)_xrstors64(tmp_vp, tmp_ULLi);
+#endif
+
+#ifdef TEST_XGETBV
+// XGETBV: [[tmp_Ui:%[0-9a-zA-z]+]] = load i32, i32* %tmp_Ui, align 4
+// XGETBV: call i64 @llvm.x86.xgetbv(i32 [[tmp_Ui]])
+  tmp_ULLi = __builtin_ia32_xgetbv(tmp_Ui);
+  
+// XGETBV: call i64 @llvm.x86.xgetbv
+  tmp_ULLi = _xgetbv(tmp_Ui);
+#endif
+
+#ifdef TEST_XSETBV
+// XSETBV: [[tmp_Ui:%[0-9a-zA-z]+]] = load i32, i32* %tmp_Ui, align 4
+// XSETBV: [[tmp_ULLi_3:%[0-9a-zA-z]+]] = load i64, i64* %tmp_ULLi, align 8
+// XSETBV: [[high64_3:%[0-9a-zA-z]+]] = lshr i64 [[tmp_ULLi_3]], 32
+// XSETBV: [[high32_3:%[0-9a-zA-z]+]] = trunc i64 [[high64_3]] to i32
+// XSETBV: [[low32_3:%[0-9a-zA-z]+]] = trunc i64 [[tmp_ULLi_3]] to i32
+// XSETBV: call void @llvm.x86.xsetbv(i32 [[tmp_Ui]], i32 [[high32_3]], i32 [[low32_3]])
+  (void)__builtin_ia32_xsetbv(tmp_Ui, tmp_ULLi);
+  
+  // XSETBV: call void @llvm.x86.xsetbv
+  (void)_xsetbv(tmp_Ui, tmp_ULLi);
 #endif
 }

test/Headers/ms-intrin.cpp

 // Use some C++ to make sure we closed the extern "C" brackets.
 template <typename T>
 void foo(T V) {}
 
 // __asm__ blocks are only checked for inline functions that end up being
 // emitted, so call functions with __asm__ blocks to make sure their inline
 // assembly parses.
 void f() {
   __movsb(0, 0, 0);
   __movsd(0, 0, 0);
   __movsw(0, 0, 0);
 
   __stosd(0, 0, 0);
   __stosw(0, 0, 0);
 
 #ifdef _M_X64
   __movsq(0, 0, 0);
   __stosq(0, 0, 0);
 #endif
 
   int info[4];
   __cpuid(info, 0);
   __cpuidex(info, 0, 0);
+#if defined(_M_X64) || defined(_M_IX86)
   _xgetbv(0);
+#endif
   __halt();
   __nop();
   __readmsr(0);
 
   // FIXME: Call these in 64-bit too once the intrinsics have been fixed to
   // work there, PR19301
 #ifndef _M_X64
   __readcr3();