Skip to content

Add __builtin_fmaf16. #97424

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 3 commits into from
Jul 15, 2024
Merged

Add __builtin_fmaf16. #97424

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
417d72f
Add __builtin_fma16.
zahiraam Jul 2, 2024
36a4c68
Removed Fmaf16 definition since it already exists.
zahiraam Jul 11, 2024
4747dd8
Added text in RN.
zahiraam Jul 12, 2024
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
2 changes: 2 additions & 0 deletions clang/docs/ReleaseNotes.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1098,6 +1098,8 @@ DWARF Support in Clang
Floating Point Support in Clang
-------------------------------

- Add ``__builtin__fmaf16`` builtin for floating point types.

Fixed Point Support in Clang
----------------------------

Expand Down
1 change: 1 addition & 0 deletions clang/lib/CodeGen/CGBuiltin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2587,6 +2587,7 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
case Builtin::BI__builtin_fma:
case Builtin::BI__builtin_fmaf:
case Builtin::BI__builtin_fmal:
case Builtin::BI__builtin_fmaf16:
case Builtin::BIfma:
case Builtin::BIfmaf:
case Builtin::BIfmal: {
Expand Down
6 changes: 5 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 @@ -364,27 +364,31 @@ __builtin_floor(f); __builtin_floorf(f); __builtin_floorl(f); __builtin
// HAS_ERRNO: declare x86_fp80 @llvm.floor.f80(x86_fp80) [[READNONE_INTRINSIC]]
// HAS_ERRNO: declare fp128 @llvm.floor.f128(fp128) [[READNONE_INTRINSIC]]

__builtin_fma(f,f,f); __builtin_fmaf(f,f,f); __builtin_fmal(f,f,f); __builtin_fmaf128(f,f,f);
__builtin_fma(f,f,f); __builtin_fmaf(f,f,f); __builtin_fmal(f,f,f); __builtin_fmaf128(f,f,f); __builtin_fmaf16(f,f,f);

// NO__ERRNO: declare double @llvm.fma.f64(double, double, double) [[READNONE_INTRINSIC]]
// NO__ERRNO: declare float @llvm.fma.f32(float, float, float) [[READNONE_INTRINSIC]]
// NO__ERRNO: declare x86_fp80 @llvm.fma.f80(x86_fp80, x86_fp80, x86_fp80) [[READNONE_INTRINSIC]]
// NO__ERRNO: declare fp128 @llvm.fma.f128(fp128, fp128, fp128) [[READNONE_INTRINSIC]]
// NO__ERRONO: declare half @llvm.fma.f16(half, half, half) [[READNONE_INTRINSIC]]
// HAS_ERRNO: declare double @fma(double noundef, double noundef, double noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare float @fmaf(float noundef, float noundef, float noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare x86_fp80 @fmal(x86_fp80 noundef, x86_fp80 noundef, x86_fp80 noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare fp128 @fmaf128(fp128 noundef, fp128 noundef, fp128 noundef) [[NOT_READNONE]]
// HAS_ERRNO: declare half @fmaf16(half noundef, half noundef, half noundef) [[NOT_READNONE]]

// On GNU or Win, fma never sets errno, so we can convert to the intrinsic.

// HAS_ERRNO_GNU: declare double @llvm.fma.f64(double, double, double) [[READNONE_INTRINSIC:#[0-9]+]]
// HAS_ERRNO_GNU: declare float @llvm.fma.f32(float, float, float) [[READNONE_INTRINSIC]]
// HAS_ERRNO_GNU: declare x86_fp80 @llvm.fma.f80(x86_fp80, x86_fp80, x86_fp80) [[READNONE_INTRINSIC]]
// HAS_ERRNO_GNU: declare half @llvm.fma.f16(half, half, half) [[READNONE_INTRINSIC]]

// HAS_ERRNO_WIN: declare double @llvm.fma.f64(double, double, double) [[READNONE_INTRINSIC:#[0-9]+]]
// HAS_ERRNO_WIN: declare float @llvm.fma.f32(float, float, float) [[READNONE_INTRINSIC]]
// Long double is just double on win, so no f80 use/declaration.
// HAS_ERRNO_WIN-NOT: declare x86_fp80 @llvm.fma.f80(x86_fp80, x86_fp80, x86_fp80)
// HAS_ERRNO_WIN: declare half @llvm.fma.f16(half, half, half) [[READNONE_INTRINSIC]]

__builtin_fmax(f,f); __builtin_fmaxf(f,f); __builtin_fmaxl(f,f); __builtin_fmaxf128(f,f);

Expand Down
3 changes: 2 additions & 1 deletion clang/test/CodeGen/constrained-math-builtins.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,12 +78,13 @@ void foo(double *d, float f, float *fp, long double *l, int *i, const char *c, _
// CHECK: call x86_fp80 @llvm.experimental.constrained.floor.f80(x86_fp80 %{{.*}}, metadata !"fpexcept.strict")
// CHECK: call fp128 @llvm.experimental.constrained.floor.f128(fp128 %{{.*}}, metadata !"fpexcept.strict")

__builtin_fma(f,f,f); __builtin_fmaf(f,f,f); __builtin_fmal(f,f,f); __builtin_fmaf128(f,f,f);
__builtin_fma(f,f,f); __builtin_fmaf(f,f,f); __builtin_fmal(f,f,f); __builtin_fmaf128(f,f,f); __builtin_fmaf16(f,f,f);

// CHECK: call double @llvm.experimental.constrained.fma.f64(double %{{.*}}, double %{{.*}}, double %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
// CHECK: call float @llvm.experimental.constrained.fma.f32(float %{{.*}}, float %{{.*}}, float %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
// CHECK: call x86_fp80 @llvm.experimental.constrained.fma.f80(x86_fp80 %{{.*}}, x86_fp80 %{{.*}}, x86_fp80 %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
// CHECK: call fp128 @llvm.experimental.constrained.fma.f128(fp128 %{{.*}}, fp128 %{{.*}}, fp128 %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
// CHECK: call half @llvm.experimental.constrained.fma.f16(half %{{.*}}, half %{{.*}}, half %{{.*}}, metadata !"fpexcept.strict")

__builtin_fmax(f,f); __builtin_fmaxf(f,f); __builtin_fmaxl(f,f); __builtin_fmaxf128(f,f);

Expand Down
Loading