[X86] Add XSAVE intrinsic family

Add intrinsics for the
  XSAVE instructions (XSAVE/XSAVE64/XRSTOR/XRSTOR64)
  XSAVEOPT instructions (XSAVEOPT/XSAVEOPT64)
  XSAVEC instructions (XSAVEC/XSAVEC64)
  XSAVES instructions (XSAVES/XSAVES64/XRSTORS/XRSTORS64)

Differential Revision: http://reviews.llvm.org/D13014

llvm-svn: 250158
This commit is contained in:
Amjad Aboud 2015-10-13 12:29:35 +00:00
parent 4015925606
commit 2b9b8a5921
12 changed files with 485 additions and 7 deletions

View File

@ -665,6 +665,20 @@ BUILTIN(__builtin_ia32_fxrstor64, "vv*", "")
BUILTIN(__builtin_ia32_fxsave, "vv*", "")
BUILTIN(__builtin_ia32_fxsave64, "vv*", "")
// XSAVE
BUILTIN(__builtin_ia32_xsave, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xsave64, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xrstor, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xrstor64, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xsaveopt, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xsaveopt64, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xrstors, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xrstors64, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xsavec, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xsavec64, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xsaves, "vv*ULLi", "")
BUILTIN(__builtin_ia32_xsaves64, "vv*ULLi", "")
// ADX
TARGET_BUILTIN(__builtin_ia32_addcarryx_u32, "UcUcUiUiUi*", "", "adx")
TARGET_BUILTIN(__builtin_ia32_addcarryx_u64, "UcUcULLiULLiULLi*", "", "adx")

View File

@ -6083,6 +6083,46 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
Builder.CreateBitCast(Tmp.getPointer(), Int8PtrTy));
return Builder.CreateLoad(Tmp, "stmxcsr");
}
case X86::BI__builtin_ia32_xsave:
case X86::BI__builtin_ia32_xsave64:
case X86::BI__builtin_ia32_xrstor:
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: {
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);
}
#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_storehps:
case X86::BI__builtin_ia32_storelps: {
llvm::Type *PtrTy = llvm::PointerType::getUnqual(Int64Ty);

View File

@ -66,6 +66,10 @@ set(files
x86intrin.h
xmmintrin.h
xopintrin.h
xsaveintrin.h
xsaveoptintrin.h
xsavecintrin.h
xsavesintrin.h
xtestintrin.h
)

View File

@ -289,9 +289,6 @@ void _xend(void);
static __inline__
#define _XCR_XFEATURE_ENABLED_MASK 0
unsigned __int64 __cdecl _xgetbv(unsigned int);
void __cdecl _xrstor(void const *, unsigned __int64);
void __cdecl _xsave(void *, unsigned __int64);
void __cdecl _xsaveopt(void *, unsigned __int64);
void __cdecl _xsetbv(unsigned int, unsigned __int64);
/* These additional intrinsics are turned on in x64/amd64/x86_64 mode. */
@ -431,9 +428,6 @@ __umulh(unsigned __int64 _Multiplier, unsigned __int64 _Multiplicand) {
(unsigned __int128)_Multiplier * (unsigned __int128)_Multiplicand;
return _FullProduct >> 64;
}
void __cdecl _xrstor64(void const *, unsigned __int64);
void __cdecl _xsave64(void *, unsigned __int64);
void __cdecl _xsaveopt64(void *, unsigned __int64);
#endif /* __x86_64__ */

View File

@ -144,6 +144,14 @@ _writegsbase_u64(unsigned long long __V)
#include <fxsrintrin.h>
#include <xsaveintrin.h>
#include <xsaveoptintrin.h>
#include <xsavecintrin.h>
#include <xsavesintrin.h>
/* Some intrinsics inside adxintrin.h are available only on processors with ADX,
* whereas others are also available at all times. */
#include <adxintrin.h>

View File

@ -0,0 +1,48 @@
/*===---- xsavecintrin.h - XSAVEC intrinsic ------------------------------------===
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*
*===-----------------------------------------------------------------------===
*/
#ifndef __IMMINTRIN_H
#error "Never use <xsavecintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __XSAVECINTRIN_H
#define __XSAVECINTRIN_H
/* Define the default attributes for the functions in this file. */
#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("xsavec")))
static __inline__ void __DEFAULT_FN_ATTRS
_xsavec(void *__p, unsigned long long __m) {
__builtin_ia32_xsavec(__p, __m);
}
#ifdef __x86_64__
static __inline__ void __DEFAULT_FN_ATTRS
_xsavec64(void *__p, unsigned long long __m) {
__builtin_ia32_xsavec64(__p, __m);
}
#endif
#undef __DEFAULT_FN_ATTRS
#endif

View File

@ -0,0 +1,58 @@
/*===---- xsaveintrin.h - XSAVE intrinsic ------------------------------------===
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*
*===-----------------------------------------------------------------------===
*/
#ifndef __IMMINTRIN_H
#error "Never use <xsaveintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __XSAVEINTRIN_H
#define __XSAVEINTRIN_H
/* 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) {
return __builtin_ia32_xsave(__p, __m);
}
static __inline__ void __DEFAULT_FN_ATTRS
_xrstor(void *__p, unsigned long long __m) {
return __builtin_ia32_xrstor(__p, __m);
}
#ifdef __x86_64__
static __inline__ void __DEFAULT_FN_ATTRS
_xsave64(void *__p, unsigned long long __m) {
return __builtin_ia32_xsave64(__p, __m);
}
static __inline__ void __DEFAULT_FN_ATTRS
_xrstor64(void *__p, unsigned long long __m) {
return __builtin_ia32_xrstor64(__p, __m);
}
#endif
#undef __DEFAULT_FN_ATTRS
#endif

View File

@ -0,0 +1,48 @@
/*===---- xsaveoptintrin.h - XSAVEOPT intrinsic ------------------------------------===
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*
*===-----------------------------------------------------------------------===
*/
#ifndef __IMMINTRIN_H
#error "Never use <xsaveoptintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __XSAVEOPTINTRIN_H
#define __XSAVEOPTINTRIN_H
/* Define the default attributes for the functions in this file. */
#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("xsaveopt")))
static __inline__ void __DEFAULT_FN_ATTRS
_xsaveopt(void *__p, unsigned long long __m) {
return __builtin_ia32_xsaveopt(__p, __m);
}
#ifdef __x86_64__
static __inline__ void __DEFAULT_FN_ATTRS
_xsaveopt64(void *__p, unsigned long long __m) {
return __builtin_ia32_xsaveopt64(__p, __m);
}
#endif
#undef __DEFAULT_FN_ATTRS
#endif

View File

@ -0,0 +1,58 @@
/*===---- xsavesintrin.h - XSAVES intrinsic ------------------------------------===
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*
*===-----------------------------------------------------------------------===
*/
#ifndef __IMMINTRIN_H
#error "Never use <xsavesintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __XSAVESINTRIN_H
#define __XSAVESINTRIN_H
/* Define the default attributes for the functions in this file. */
#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("xsaves")))
static __inline__ void __DEFAULT_FN_ATTRS
_xsaves(void *__p, unsigned long long __m) {
__builtin_ia32_xsaves(__p, __m);
}
static __inline__ void __DEFAULT_FN_ATTRS
_xrstors(void *__p, unsigned long long __m) {
__builtin_ia32_xrstors(__p, __m);
}
#ifdef __x86_64__
static __inline__ void __DEFAULT_FN_ATTRS
_xrstors64(void *__p, unsigned long long __m) {
__builtin_ia32_xrstors64(__p, __m);
}
static __inline__ void __DEFAULT_FN_ATTRS
_xsaves64(void *__p, unsigned long long __m) {
__builtin_ia32_xsaves64(__p, __m);
}
#endif
#undef __DEFAULT_FN_ATTRS
#endif

View File

@ -42,7 +42,7 @@ void f0() {
signed int tmp_i;
unsigned int tmp_Ui;
signed long long tmp_LLi;
// unsigned long long tmp_ULLi;
unsigned long long tmp_ULLi;
float tmp_f;
double tmp_d;
@ -267,6 +267,20 @@ void f0() {
(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);
(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);
(void)__builtin_ia32_xsaves(tmp_vp, tmp_ULLi);
(void)__builtin_ia32_xsaves64(tmp_vp, tmp_ULLi);
tmp_V4f = __builtin_ia32_cvtpi2ps(tmp_V4f, tmp_V2i);
tmp_V2i = __builtin_ia32_cvtps2pi(tmp_V4f);
tmp_i = __builtin_ia32_cvtss2si(tmp_V4f);

View File

@ -0,0 +1,72 @@
// RUN: %clang_cc1 %s -DTEST_XSAVE -O0 -triple=i686-unknown-unknown -target-feature +xsave -emit-llvm -o - -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 - -Werror | FileCheck %s --check-prefix=XSAVE
// RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=i686-unknown-unknown -target-feature +xsave,+xsaveopt -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEOPT
// RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=i686-unknown-unknown -target-feature +xsave,+xsaveopt -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEOPT
// RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=i686-unknown-unknown -target-feature +xsave,+xsavec -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEC
// RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=i686-unknown-unknown -target-feature +xsave,+xsavec -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEC
// RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=i686-unknown-unknown -target-feature +xsave,+xsaves -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVES
// RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=i686-unknown-unknown -target-feature +xsave,+xsaves -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVES
void test() {
unsigned long long tmp_ULLi;
void* tmp_vp;
#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);
#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);
#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);
#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);
#endif
}

View File

@ -0,0 +1,120 @@
// RUN: %clang_cc1 %s -DTEST_XSAVE -O0 -triple=x86_64-unknown-unknown -target-feature +xsave -emit-llvm -o - -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 - -Werror | FileCheck %s --check-prefix=XSAVE
// RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=x86_64-unknown-unknown -target-feature +xsave,+xsaveopt -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEOPT
// RUN: %clang_cc1 %s -DTEST_XSAVEOPT -O0 -triple=x86_64-unknown-unknown -target-feature +xsave,+xsaveopt -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEOPT
// RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=x86_64-unknown-unknown -target-feature +xsave,+xsavec -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEC
// RUN: %clang_cc1 %s -DTEST_XSAVEC -O0 -triple=x86_64-unknown-unknown -target-feature +xsave,+xsavec -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVEC
// RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=x86_64-unknown-unknown -target-feature +xsave,+xsaves -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVES
// RUN: %clang_cc1 %s -DTEST_XSAVES -O0 -triple=x86_64-unknown-unknown -target-feature +xsave,+xsaves -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s --check-prefix=XSAVES
void test() {
unsigned long long tmp_ULLi;
void* tmp_vp;
#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]])
(void)__builtin_ia32_xsave(tmp_vp, tmp_ULLi);
// XSAVE: [[tmp_vp_2:%[0-9a-zA-z]+]] = load i8*, i8** %tmp_vp, align 8
// XSAVE: [[tmp_ULLi_2:%[0-9a-zA-z]+]] = load i64, i64* %tmp_ULLi, align 8
// XSAVE: [[high64_2:%[0-9a-zA-z]+]] = lshr i64 [[tmp_ULLi_2]], 32
// XSAVE: [[high32_2:%[0-9a-zA-z]+]] = trunc i64 [[high64_2]] to i32
// XSAVE: [[low32_2:%[0-9a-zA-z]+]] = trunc i64 [[tmp_ULLi_2]] to i32
// XSAVE: call void @llvm.x86.xsave64(i8* [[tmp_vp_2]], i32 [[high32_2]], i32 [[low32_2]])
(void)__builtin_ia32_xsave64(tmp_vp, tmp_ULLi);
// XSAVE: [[tmp_vp_3:%[0-9a-zA-z]+]] = load i8*, i8** %tmp_vp, align 8
// 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: [[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);
#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);
#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);
#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: 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_2:%[0-9a-zA-z]+]] = load i8*, i8** %tmp_vp, align 8
// XSAVES: [[tmp_ULLi_2:%[0-9a-zA-z]+]] = load i64, i64* %tmp_ULLi, align 8
// XSAVES: [[high64_2:%[0-9a-zA-z]+]] = lshr i64 [[tmp_ULLi_2]], 32
// XSAVES: [[high32_2:%[0-9a-zA-z]+]] = trunc i64 [[high64_2]] to i32
// XSAVES: [[low32_2:%[0-9a-zA-z]+]] = trunc i64 [[tmp_ULLi_2]] to i32
// XSAVES: call void @llvm.x86.xsaves64(i8* [[tmp_vp_2]], i32 [[high32_2]], i32 [[low32_2]])
(void)__builtin_ia32_xsaves64(tmp_vp, tmp_ULLi);
// XSAVES: [[tmp_vp_3:%[0-9a-zA-z]+]] = load i8*, i8** %tmp_vp, align 8
// 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: [[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);
#endif
}