Skip to content

[clang] Add sincos builtin using llvm.sincos intrinsic #114086

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Jan 6, 2025
Merged

[clang] Add sincos builtin using llvm.sincos intrinsic #114086

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
5a5495d
[clang] Add sincos builtin using `llvm.sincos` intrinsic
MacDue Sep 9, 2024
85dbd5c
Fix typo
MacDue Oct 30, 2024
86b028b
Fixups
MacDue Dec 16, 2024
974fe16
Fixups
MacDue Dec 16, 2024
2884e95
Fixups
MacDue Dec 17, 2024
6614b4f
Limit to __builtin calls
MacDue Jan 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions clang/include/clang/Basic/Builtins.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3568,6 +3568,19 @@ def Frexp : FPMathTemplate, LibBuiltin<"math.h"> {
let AddBuiltinPrefixedAlias = 1;
}

def Sincos : FPMathTemplate, GNULibBuiltin<"math.h"> {
let Spellings = ["sincos"];
let Attributes = [NoThrow];
let Prototype = "void(T, T*, T*)";
let AddBuiltinPrefixedAlias = 1;
}

def SincosF16F128 : F16F128MathTemplate, Builtin {
let Spellings = ["__builtin_sincos"];
let Attributes = [FunctionWithBuiltinPrefix, NoThrow];
let Prototype = "void(T, T*, T*)";
}

def Ldexp : FPMathTemplate, LibBuiltin<"math.h"> {
let Spellings = ["ldexp"];
let Attributes = [NoThrow, ConstIgnoringErrnoAndExceptions];
Expand Down
40 changes: 40 additions & 0 deletions clang/lib/CodeGen/CGBuiltin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -835,6 +835,38 @@ static Value *emitFrexpBuiltin(CodeGenFunction &CGF, const CallExpr *E,
return CGF.Builder.CreateExtractValue(Call, 0);
}

static void emitSincosBuiltin(CodeGenFunction &CGF, const CallExpr *E,
llvm::Intrinsic::ID IntrinsicID) {
llvm::Value *Val = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Dest0 = CGF.EmitScalarExpr(E->getArg(1));
llvm::Value *Dest1 = CGF.EmitScalarExpr(E->getArg(2));

llvm::Function *F = CGF.CGM.getIntrinsic(IntrinsicID, {Val->getType()});
llvm::Value *Call = CGF.Builder.CreateCall(F, Val);

llvm::Value *SinResult = CGF.Builder.CreateExtractValue(Call, 0);
llvm::Value *CosResult = CGF.Builder.CreateExtractValue(Call, 1);

QualType DestPtrType = E->getArg(1)->getType()->getPointeeType();
LValue SinLV = CGF.MakeNaturalAlignAddrLValue(Dest0, DestPtrType);
LValue CosLV = CGF.MakeNaturalAlignAddrLValue(Dest1, DestPtrType);

llvm::StoreInst *StoreSin =
CGF.Builder.CreateStore(SinResult, SinLV.getAddress());
llvm::StoreInst *StoreCos =
CGF.Builder.CreateStore(CosResult, CosLV.getAddress());

// Mark the two stores as non-aliasing with each other. The order of stores
// emitted by this builtin is arbitrary, enforcing a particular order will
// prevent optimizations later on.
llvm::MDBuilder MDHelper(CGF.getLLVMContext());
MDNode *Domain = MDHelper.createAnonymousAliasScopeDomain();
MDNode *AliasScope = MDHelper.createAnonymousAliasScope(Domain);
MDNode *AliasScopeList = MDNode::get(Call->getContext(), AliasScope);
StoreSin->setMetadata(LLVMContext::MD_alias_scope, AliasScopeList);
StoreCos->setMetadata(LLVMContext::MD_noalias, AliasScopeList);
}

/// EmitFAbs - Emit a call to @llvm.fabs().
static Value *EmitFAbs(CodeGenFunction &CGF, Value *V) {
Function *F = CGF.CGM.getIntrinsic(Intrinsic::fabs, V->getType());
Expand Down Expand Up @@ -3232,6 +3264,14 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(
*this, E, Intrinsic::sinh, Intrinsic::experimental_constrained_sinh));

case Builtin::BI__builtin_sincos:
case Builtin::BI__builtin_sincosf:
case Builtin::BI__builtin_sincosf16:
case Builtin::BI__builtin_sincosl:
case Builtin::BI__builtin_sincosf128:
emitSincosBuiltin(*this, E, Intrinsic::sincos);
return RValue::get(nullptr);

case Builtin::BIsqrt:
case Builtin::BIsqrtf:
case Builtin::BIsqrtl:
Expand Down
44 changes: 44 additions & 0 deletions clang/test/CodeGen/AArch64/sincos.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
// RUN: %clang_cc1 -triple=aarch64-gnu-linux -emit-llvm -O1 %s -o - | FileCheck --check-prefix=NO-MATH-ERRNO %s
// RUN: %clang_cc1 -triple=aarch64-gnu-linux -emit-llvm -fmath-errno %s -o - | FileCheck --check-prefix=MATH-ERRNO %s

// NO-MATH-ERRNO-LABEL: @sincos_f32
// NO-MATH-ERRNO: [[SINCOS:%.*]] = tail call { float, float } @llvm.sincos.f32(float {{.*}})
// NO-MATH-ERRNO-NEXT: [[SIN:%.*]] = extractvalue { float, float } [[SINCOS]], 0
// NO-MATH-ERRNO-NEXT: [[COS:%.*]] = extractvalue { float, float } [[SINCOS]], 1
// NO-MATH-ERRNO-NEXT: store float [[SIN]], ptr {{.*}}, align 4, !alias.scope [[SINCOS_ALIAS_SCOPE:![0-9]+]]
// NO-MATH-ERRNO-NEXT: store float [[COS]], ptr {{.*}}, align 4, !noalias [[SINCOS_ALIAS_SCOPE]]
//
// MATH-ERRNO-LABEL: @sincos_f32
// MATH-ERRNO: call void @sincosf(
//
void sincos_f32(float x, float* fp0, float* fp1) {
__builtin_sincosf(x, fp0, fp1);
}

// NO-MATH-ERRNO-LABEL: @sincos_f64
// NO-MATH-ERRNO: [[SINCOS:%.*]] = tail call { double, double } @llvm.sincos.f64(double {{.*}})
// NO-MATH-ERRNO-NEXT: [[SIN:%.*]] = extractvalue { double, double } [[SINCOS]], 0
// NO-MATH-ERRNO-NEXT: [[COS:%.*]] = extractvalue { double, double } [[SINCOS]], 1
// NO-MATH-ERRNO-NEXT: store double [[SIN]], ptr {{.*}}, align 8, !alias.scope [[SINCOS_ALIAS_SCOPE:![0-9]+]]
// NO-MATH-ERRNO-NEXT: store double [[COS]], ptr {{.*}}, align 8, !noalias [[SINCOS_ALIAS_SCOPE]]
//
// MATH-ERRNO-LABEL: @sincos_f64
// MATH-ERRNO: call void @sincos(
//
void sincos_f64(double x, double* dp0, double* dp1) {
__builtin_sincos(x, dp0, dp1);
}

// NO-MATH-ERRNO-LABEL: @sincos_f128
// NO-MATH-ERRNO: [[SINCOS:%.*]] = tail call { fp128, fp128 } @llvm.sincos.f128(fp128 {{.*}})
// NO-MATH-ERRNO-NEXT: [[SIN:%.*]] = extractvalue { fp128, fp128 } [[SINCOS]], 0
// NO-MATH-ERRNO-NEXT: [[COS:%.*]] = extractvalue { fp128, fp128 } [[SINCOS]], 1
// NO-MATH-ERRNO-NEXT: store fp128 [[SIN]], ptr {{.*}}, align 16, !alias.scope [[SINCOS_ALIAS_SCOPE:![0-9]+]]
// NO-MATH-ERRNO-NEXT: store fp128 [[COS]], ptr {{.*}}, align 16, !noalias [[SINCOS_ALIAS_SCOPE]]
//
// MATH-ERRNO-LABEL: @sincos_f128
// MATH-ERRNO: call void @sincosl(
//
void sincos_f128(long double x, long double* ldp0, long double* ldp1) {
__builtin_sincosl(x, ldp0, ldp1);
}
36 changes: 35 additions & 1 deletion clang/test/CodeGen/X86/math-builtins.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,31 @@ void foo(double *d, float f, float *fp, long double *l, int *i, const char *c) {
// NO__ERRNO-NEXT: [[FREXP_F128_0:%.+]] = extractvalue { fp128, i32 } [[FREXP_F128]], 0


// NO__ERRNO: [[SINCOS_F64:%.+]] = call { double, double } @llvm.sincos.f64(double %{{.+}})
// NO__ERRNO-NEXT: [[SINCOS_F64_0:%.+]] = extractvalue { double, double } [[SINCOS_F64]], 0
// NO__ERRNO-NEXT: [[SINCOS_F64_1:%.+]] = extractvalue { double, double } [[SINCOS_F64]], 1
// NO__ERRNO-NEXT: store double [[SINCOS_F64_0]], ptr %{{.+}}, align 8
// NO__ERRNO-NEXT: store double [[SINCOS_F64_1]], ptr %{{.+}}, align 8

// NO__ERRNO: [[SINCOS_F32:%.+]] = call { float, float } @llvm.sincos.f32(float %{{.+}})
// NO__ERRNO-NEXT: [[SINCOS_F32_0:%.+]] = extractvalue { float, float } [[SINCOS_F32]], 0
// NO__ERRNO-NEXT: [[SINCOS_F32_1:%.+]] = extractvalue { float, float } [[SINCOS_F32]], 1
// NO__ERRNO-NEXT: store float [[SINCOS_F32_0]], ptr %{{.+}}, align 4
// NO__ERRNO-NEXT: store float [[SINCOS_F32_1]], ptr %{{.+}}, align 4

// NO__ERRNO: [[SINCOS_F80:%.+]] = call { x86_fp80, x86_fp80 } @llvm.sincos.f80(x86_fp80 %{{.+}})
// NO__ERRNO-NEXT: [[SINCOS_F80_0:%.+]] = extractvalue { x86_fp80, x86_fp80 } [[SINCOS_F80]], 0
// NO__ERRNO-NEXT: [[SINCOS_F80_1:%.+]] = extractvalue { x86_fp80, x86_fp80 } [[SINCOS_F80]], 1
// NO__ERRNO-NEXT: store x86_fp80 [[SINCOS_F80_0]], ptr %{{.+}}, align 16
// NO__ERRNO-NEXT: store x86_fp80 [[SINCOS_F80_1]], ptr %{{.+}}, align 16

// NO__ERRNO: [[SINCOS_F128:%.+]] = call { fp128, fp128 } @llvm.sincos.f128(fp128 %{{.+}})
// NO__ERRNO-NEXT: [[SINCOS_F128_0:%.+]] = extractvalue { fp128, fp128 } [[SINCOS_F128]], 0
// NO__ERRNO-NEXT: [[SINCOS_F128_1:%.+]] = extractvalue { fp128, fp128 } [[SINCOS_F128]], 1
// NO__ERRNO-NEXT: store fp128 [[SINCOS_F128_0]], ptr %{{.+}}, align 16
// NO__ERRNO-NEXT: store fp128 [[SINCOS_F128_1]], ptr %{{.+}}, align 16


// HAS_ERRNO: declare double @fmod(double noundef, double noundef) [[NOT_READNONE:#[0-9]+]]
// HAS_ERRNO: declare float @fmodf(float noundef, float noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare x86_fp80 @fmodl(x86_fp80 noundef, x86_fp80 noundef) [[NOT_READNONE]]
Expand Down Expand Up @@ -665,6 +690,16 @@ __builtin_sinh(f); __builtin_sinhf(f); __builtin_sinhl(f); __builtin_
// HAS_ERRNO: declare x86_fp80 @sinhl(x86_fp80 noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare fp128 @sinhf128(fp128 noundef) [[NOT_READNONE]]

__builtin_sincos(f,d,d); __builtin_sincosf(f,fp,fp); __builtin_sincosl(f,l,l); __builtin_sincosf128(f,l,l);
// NO__ERRNO: declare { double, double } @llvm.sincos.f64(double) [[READNONE_INTRINSIC]]
// NO__ERRNO: declare { float, float } @llvm.sincos.f32(float) [[READNONE_INTRINSIC]]
// NO__ERRNO: declare { x86_fp80, x86_fp80 } @llvm.sincos.f80(x86_fp80) [[READNONE_INTRINSIC]]
// NO__ERRNO: declare { fp128, fp128 } @llvm.sincos.f128(fp128) [[READNONE_INTRINSIC]]
// HAS_ERRNO: declare void @sincos(double noundef, ptr noundef, ptr noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare void @sincosf(float noundef, ptr noundef, ptr noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare void @sincosl(x86_fp80 noundef, ptr noundef, ptr noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare void @sincosf128(fp128 noundef, ptr noundef, ptr noundef) [[NOT_READNONE]]

__builtin_sqrt(f); __builtin_sqrtf(f); __builtin_sqrtl(f); __builtin_sqrtf128(f);

// NO__ERRNO: declare double @llvm.sqrt.f64(double) [[READNONE_INTRINSIC]]
Expand Down Expand Up @@ -733,4 +768,3 @@ __builtin_trunc(f); __builtin_truncf(f); __builtin_truncl(f); __builtin

// HAS_ERRNO_GNU: attributes [[READNONE_INTRINSIC]] = { {{.*}}memory(none){{.*}} }
// HAS_ERRNO_WIN: attributes [[READNONE_INTRINSIC]] = { {{.*}}memory(none){{.*}} }

4 changes: 2 additions & 2 deletions clang/test/OpenMP/declare_simd_aarch64.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
// REQUIRES: aarch64-registered-target
// -fopemp and -fopenmp-simd behavior are expected to be the same.

// RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +neon -fopenmp -x c -emit-llvm %s -o - -femit-all-decls | FileCheck %s --check-prefix=AARCH64
// RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +neon -fopenmp-simd -x c -emit-llvm %s -o - -femit-all-decls | FileCheck %s --check-prefix=AARCH64
// RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +neon -fmath-errno -fopenmp -x c -emit-llvm %s -o - -femit-all-decls | FileCheck %s --check-prefix=AARCH64
// RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +neon -fmath-errno -fopenmp-simd -x c -emit-llvm %s -o - -femit-all-decls | FileCheck %s --check-prefix=AARCH64

#pragma omp declare simd
#pragma omp declare simd simdlen(2)
Expand Down
Loading