maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Implement __emul, __emulu, _mul128 and _umul128 MS intrinsics 

Reviewers: rnk, thakis, majnemer, hans

Subscribers: cfe-commits

Differential Revision: https://reviews.llvm.org/D25353

llvm-svn: 283785
This commit is contained in:
Albert Gutowski 2016-10-10 18:09:27 +00:00
parent 3bfe1093df
commit 7216f17653
6 changed files with 110 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
clang/include/clang/Basic/BuiltinsX86.def
View File

@ -2071,6 +2071,9 @@ TARGET_BUILTIN(__builtin_ia32_selectpd_512, "V8dUcV8dV8d", "", "")
TARGET_BUILTIN(__builtin_ia32_monitorx, "vv*UiUi", "", "mwaitx")
TARGET_BUILTIN(__builtin_ia32_mwaitx, "vUiUiUi", "", "mwaitx")
TARGET_HEADER_BUILTIN(__emul, "LLiii", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
TARGET_HEADER_BUILTIN(__emulu, "ULLiUiUi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
#undef BUILTIN
#undef TARGET_BUILTIN
#undef TARGET_HEADER_BUILTIN

2
clang/include/clang/Basic/BuiltinsX86_64.def
View File

@ -20,6 +20,8 @@
TARGET_HEADER_BUILTIN(__mulh, "LLiLLiLLi", "nch", "intrin.h", ALL_MS_LANGUAGES, "")
TARGET_HEADER_BUILTIN(__umulh, "ULLiULLiULLi", "nch", "intrin.h", ALL_MS_LANGUAGES, "")
TARGET_HEADER_BUILTIN(_mul128, "LLiLLiLLiLLi*", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
TARGET_HEADER_BUILTIN(_umul128, "ULLiULLiULLiULLi*", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
#undef BUILTIN
#undef TARGET_HEADER_BUILTIN

27
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -7576,16 +7576,24 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
case X86::BI__builtin_ia32_cmpordsd:
return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 7);
case X86::BI__emul:
case X86::BI__emulu: {
llvm::Type *Int64Ty = llvm::IntegerType::get(getLLVMContext(), 64);
bool isSigned = (BuiltinID == X86::BI__emul);
Value *LHS = Builder.CreateIntCast(Ops[0], Int64Ty, isSigned);
Value *RHS = Builder.CreateIntCast(Ops[1], Int64Ty, isSigned);
return Builder.CreateMul(LHS, RHS, "", !isSigned, isSigned);
}
case X86::BI__mulh:
case X86::BI__umulh: {
Value *LHS = EmitScalarExpr(E->getArg(0));
Value *RHS = EmitScalarExpr(E->getArg(1));
case X86::BI__umulh:
case X86::BI_mul128:
case X86::BI_umul128: {
llvm::Type *ResType = ConvertType(E->getType());
llvm::Type *Int128Ty = llvm::IntegerType::get(getLLVMContext(), 128);
bool IsSigned = (BuiltinID == X86::BI__mulh);
LHS = Builder.CreateIntCast(LHS, Int128Ty, IsSigned);
RHS = Builder.CreateIntCast(RHS, Int128Ty, IsSigned);
bool IsSigned = (BuiltinID == X86::BI__mulh || BuiltinID == X86::BI_mul128);
Value *LHS = Builder.CreateIntCast(Ops[0], Int128Ty, IsSigned);
Value *RHS = Builder.CreateIntCast(Ops[1], Int128Ty, IsSigned);
Value *MulResult, *HigherBits;
if (IsSigned) {
@ -7595,9 +7603,14 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
MulResult = Builder.CreateNUWMul(LHS, RHS);
HigherBits = Builder.CreateLShr(MulResult, 64);
}
HigherBits = Builder.CreateIntCast(HigherBits, ResType, IsSigned);
if (BuiltinID == X86::BI__mulh || BuiltinID == X86::BI__umulh)
return HigherBits;
Address HighBitsAddress = EmitPointerWithAlignment(E->getArg(2));
Builder.CreateStore(HigherBits, HighBitsAddress);
return Builder.CreateIntCast(MulResult, ResType, IsSigned);
}
}
}

38
clang/lib/Headers/intrin.h
View File

@ -66,7 +66,9 @@ void __cpuid(int[4], int);
static __inline__
void __cpuidex(int[4], int, int);
void __debugbreak(void);
static __inline__
__int64 __emul(int, int);
static __inline__
unsigned __int64 __emulu(unsigned int, unsigned int);
void __cdecl __fastfail(unsigned int);
unsigned int __getcallerseflags(void);
@ -313,8 +315,6 @@ unsigned __int64 __lzcnt64(unsigned __int64);
static __inline__
void __movsq(unsigned long long *, unsigned long long const *, size_t);
static __inline__
__int64 __mulh(__int64, __int64);
static __inline__
unsigned __int64 __popcnt64(unsigned __int64);
static __inline__
unsigned char __readgsbyte(unsigned long);
@ -405,9 +405,6 @@ static __inline__
__int64 _InterlockedXor64(__int64 volatile *_Value, __int64 _Mask);
__int64 _InterlockedXor64_np(__int64 volatile *_Value, __int64 _Mask);
char _InterlockedXor8_np(char volatile *_Value, char _Mask);
static __inline__
__int64 _mul128(__int64 _Multiplier, __int64 _Multiplicand,
__int64 *_HighProduct);
unsigned __int64 _rorx_u64(unsigned __int64, const unsigned int);
__int64 _sarx_i64(__int64, unsigned int);
#if __STDC_HOSTED__
@ -415,34 +412,19 @@ int __cdecl _setjmpex(jmp_buf);
#endif
unsigned __int64 _shlx_u64(unsigned __int64, unsigned int);
unsigned __int64 _shrx_u64(unsigned __int64, unsigned int);
/*
* Multiply two 64-bit integers and obtain a 64-bit result.
* The low-half is returned directly and the high half is in an out parameter.
*/
static __inline__ unsigned __int64 __DEFAULT_FN_ATTRS
_umul128(unsigned __int64 _Multiplier, unsigned __int64 _Multiplicand,
unsigned __int64 *_HighProduct) {
unsigned __int128 _FullProduct =
(unsigned __int128)_Multiplier * (unsigned __int128)_Multiplicand;
*_HighProduct = _FullProduct >> 64;
return _FullProduct;
}
static __inline__
__int64 __mulh(__int64, __int64);
static __inline__
unsigned __int64 __umulh(unsigned __int64, unsigned __int64);
static __inline__
__int64 _mul128(__int64, __int64, __int64*);
static __inline__
unsigned __int64 _umul128(unsigned __int64,
unsigned __int64,
unsigned __int64*);
#endif /* __x86_64__ */
/*----------------------------------------------------------------------------*\
|* Multiplication
\*----------------------------------------------------------------------------*/
static __inline__ __int64 __DEFAULT_FN_ATTRS
__emul(int __in1, int __in2) {
return (__int64)__in1 * (__int64)__in2;
}
static __inline__ unsigned __int64 __DEFAULT_FN_ATTRS
__emulu(unsigned int __in1, unsigned int __in2) {
return (unsigned __int64)__in1 * (unsigned __int64)__in2;
}
/*----------------------------------------------------------------------------*\
|* Bit Counting and Testing
\*----------------------------------------------------------------------------*/

26
clang/test/CodeGen/ms-intrinsics.c
View File

@ -41,32 +41,6 @@ void *test_InterlockedCompareExchangePointer(void * volatile *Destination,
// CHECK: ret i8* %[[RESULT:[0-9]+]]
// CHECK: }
#if defined(__i386__)
long test__readfsdword(unsigned long Offset) {
return __readfsdword(Offset);
}
// CHECK-I386: define i32 @test__readfsdword(i32 %Offset){{.*}}{
// CHECK-I386: [[PTR:%[0-9]+]] = inttoptr i32 %Offset to i32 addrspace(257)*
// CHECK-I386: [[VALUE:%[0-9]+]] = load volatile i32, i32 addrspace(257)* [[PTR]], align 4
// CHECK-I386: ret i32 [[VALUE:%[0-9]+]]
// CHECK-I386: }
#endif
#if defined(__x86_64__)
__int64 test__mulh(__int64 a, __int64 b) {
return __mulh(a, b);
}
// CHECK-X64-LABEL: define i64 @test__mulh(i64 %a, i64 %b)
// CHECK-X64: = mul nsw i128 %
unsigned __int64 test__umulh(unsigned __int64 a, unsigned __int64 b) {
return __umulh(a, b);
}
// CHECK-X64-LABEL: define i64 @test__umulh(i64 %a, i64 %b)
// CHECK-X64: = mul nuw i128 %
#endif
char test_InterlockedExchange8(char volatile *value, char mask) {
return _InterlockedExchange8(value, mask);
}

74
clang/test/CodeGen/ms-x86-intrinsics.c Normal file
View File

@ -0,0 +1,74 @@
// RUN: %clang_cc1 -ffreestanding -fms-extensions -fms-compatibility -fms-compatibility-version=17.00 \
// RUN: -triple i686--windows -Oz -emit-llvm %s -o - \
// RUN: | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-I386
// RUN: %clang_cc1 -ffreestanding -fms-extensions -fms-compatibility -fms-compatibility-version=17.00 \
// RUN: -triple x86_64--windows -Oz -emit-llvm %s -o - \
// RUN: | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-X64
#if defined(__i386__)
long test__readfsdword(unsigned long Offset) {
return __readfsdword(Offset);
}
// CHECK-I386-LABEL: define i32 @test__readfsdword(i32 %Offset){{.*}}{
// CHECK-I386: [[PTR:%[0-9]+]] = inttoptr i32 %Offset to i32 addrspace(257)*
// CHECK-I386: [[VALUE:%[0-9]+]] = load volatile i32, i32 addrspace(257)* [[PTR]], align 4
// CHECK-I386: ret i32 [[VALUE:%[0-9]+]]
// CHECK-I386: }
#endif
__int64 test__emul(int a, int b) {
return __emul(a, b);
}
// CHECK-LABEL: define i64 @test__emul(i32 %a, i32 %b)
// CHECK: [[X:%[0-9]+]] = sext i32 %a to i64
// CHECK: [[Y:%[0-9]+]] = sext i32 %b to i64
// CHECK: [[RES:%[0-9]+]] = mul nsw i64 [[Y]], [[X]]
// CHECK: ret i64 [[RES]]
unsigned __int64 test__emulu(unsigned int a, unsigned int b) {
return __emulu(a, b);
}
// CHECK-LABEL: define i64 @test__emulu(i32 %a, i32 %b)
// CHECK: [[X:%[0-9]+]] = zext i32 %a to i64
// CHECK: [[Y:%[0-9]+]] = zext i32 %b to i64
// CHECK: [[RES:%[0-9]+]] = mul nuw i64 [[Y]], [[X]]
// CHECK: ret i64 [[RES]]
#if defined(__x86_64__)
__int64 test__mulh(__int64 a, __int64 b) {
return __mulh(a, b);
}
// CHECK-X64-LABEL: define i64 @test__mulh(i64 %a, i64 %b)
// CHECK-X64: = mul nsw i128 %
unsigned __int64 test__umulh(unsigned __int64 a, unsigned __int64 b) {
return __umulh(a, b);
}
// CHECK-X64-LABEL: define i64 @test__umulh(i64 %a, i64 %b)
// CHECK-X64: = mul nuw i128 %
__int64 test_mul128(__int64 Multiplier,
__int64 Multiplicand,
__int64 *HighProduct) {
return _mul128(Multiplier, Multiplicand, HighProduct);
}
// CHECK-X64-LABEL: define i64 @test_mul128(i64 %Multiplier, i64 %Multiplicand, i64*{{[a-z_ ]*}}%HighProduct)
// CHECK-X64: = sext i64 %Multiplier to i128
// CHECK-X64: = sext i64 %Multiplicand to i128
// CHECK-X64: = mul nsw i128 %
// CHECK-X64: store i64 %
// CHECK-X64: ret i64 %
unsigned __int64 test_umul128(unsigned __int64 Multiplier,
unsigned __int64 Multiplicand,
unsigned __int64 *HighProduct) {
return _umul128(Multiplier, Multiplicand, HighProduct);
}
// CHECK-X64-LABEL: define i64 @test_umul128(i64 %Multiplier, i64 %Multiplicand, i64*{{[a-z_ ]*}}%HighProduct)
// CHECK-X64: = zext i64 %Multiplier to i128
// CHECK-X64: = zext i64 %Multiplicand to i128
// CHECK-X64: = mul nuw i128 %
// CHECK-X64: store i64 %
// CHECK-X64: ret i64 %
#endif