[clang] [clang] Add sincos builtin using `llvm.sincos` intrinsic (PR #114086)

Benjamin Maxwell via cfe-commits cfe-commits at lists.llvm.org
Wed Oct 30 03:08:01 PDT 2024


https://github.com/MacDue updated https://github.com/llvm/llvm-project/pull/114086

>From 7fd19eefa1d1f61843fe1844a72e14c7f4bae03b Mon Sep 17 00:00:00 2001
From: Benjamin Maxwell <benjamin.maxwell at arm.com>
Date: Mon, 9 Sep 2024 10:15:20 +0000
Subject: [PATCH] [clang] Add sincos builtin using `llvm.sincos` intrinsic

This registers `sincos[f|l]` as a clang builtin and updates GCBuiltin
to emit the `llvm.sincos.*` intrinsic when `-fno-math-errno` is set.
---
 clang/include/clang/Basic/Builtins.td    | 13 +++++++
 clang/lib/CodeGen/CGBuiltin.cpp          | 43 ++++++++++++++++++++++++
 clang/test/CodeGen/AArch64/sincos.c      | 33 ++++++++++++++++++
 clang/test/CodeGen/X86/math-builtins.c   | 35 +++++++++++++++++++
 clang/test/OpenMP/declare_simd_aarch64.c |  4 +--
 5 files changed, 126 insertions(+), 2 deletions(-)
 create mode 100644 clang/test/CodeGen/AArch64/sincos.c

diff --git a/clang/include/clang/Basic/Builtins.td b/clang/include/clang/Basic/Builtins.td
index 9bd67e0cefebc3..27eadf80d623e6 100644
--- a/clang/include/clang/Basic/Builtins.td
+++ b/clang/include/clang/Basic/Builtins.td
@@ -3562,6 +3562,19 @@ 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];
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 65d7f5c54a1913..331b367e63d91b 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -722,6 +722,38 @@ 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 eachother. 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());
@@ -3094,6 +3126,17 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
       return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(
           *this, E, Intrinsic::sinh, Intrinsic::experimental_constrained_sinh));
 
+    case Builtin::BIsincos:
+    case Builtin::BIsincosf:
+    case Builtin::BIsincosl:
+    case Builtin::BI__builtin_sincos:
+    case Builtin::BI__builtin_sincosf:
+    case Builtin::BI__builtin_sincosl:
+    case Builtin::BI__builtin_sincosf128:
+    case Builtin::BI__builtin_sincosf16:
+      emitSincosBuiltin(*this, E, Intrinsic::sincos);
+      return RValue::get(nullptr);
+
     case Builtin::BIsqrt:
     case Builtin::BIsqrtf:
     case Builtin::BIsqrtl:
diff --git a/clang/test/CodeGen/AArch64/sincos.c b/clang/test/CodeGen/AArch64/sincos.c
new file mode 100644
index 00000000000000..240d921b2b7034
--- /dev/null
+++ b/clang/test/CodeGen/AArch64/sincos.c
@@ -0,0 +1,33 @@
+// RUN: %clang_cc1 -triple=aarch64-gnu-linux -emit-llvm %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
+
+void sincos(double, double*, double*);
+void sincosf(float, float*, float*);
+
+// NO-MATH-ERRNO-LABEL: @foo
+//      NO-MATH-ERRNO:    [[SINCOS:%.*]] = 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: @foo
+//      MATH-ERRNO:    call void @sincos(
+//
+void foo(double x, double* dp0, double* dp1) {
+  sincos(x, dp0, dp1);
+}
+
+// NO-MATH-ERRNO-LABEL: @bar
+//      NO-MATH-ERRNO:    [[SINCOS:%.*]] = 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: @bar
+//      MATH-ERRNO:    call void @sincosf(
+//
+void bar(float x, float* fp0, float* fp1) {
+  sincosf(x, fp0, fp1);
+}
diff --git a/clang/test/CodeGen/X86/math-builtins.c b/clang/test/CodeGen/X86/math-builtins.c
index 48465df21cca19..20e86a50e2bf18 100644
--- a/clang/test/CodeGen/X86/math-builtins.c
+++ b/clang/test/CodeGen/X86/math-builtins.c
@@ -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]]
@@ -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]]
diff --git a/clang/test/OpenMP/declare_simd_aarch64.c b/clang/test/OpenMP/declare_simd_aarch64.c
index 21c83c225963f9..e9538e7446eec9 100644
--- a/clang/test/OpenMP/declare_simd_aarch64.c
+++ b/clang/test/OpenMP/declare_simd_aarch64.c
@@ -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)



More information about the cfe-commits mailing list