diff options
| author | Jed Brown <jed@jedbrown.org> | 2024-01-05 21:04:41 -0700 |
|---|---|---|
| committer | Jed Brown <jed@jedbrown.org> | 2024-10-11 15:32:56 -0600 |
| commit | 0d8a978e8a55b08778ec6ee861c2c5ed6703eb6c (patch) | |
| tree | 048738de47621c87899e28ba3c90b4c2417b5d3a /compiler/rustc_codegen_llvm | |
| parent | 01e2fff90c7ed19e1d9fb828ebc012e7b9732297 (diff) | |
| download | rust-0d8a978e8a55b08778ec6ee861c2c5ed6703eb6c.tar.gz rust-0d8a978e8a55b08778ec6ee861c2c5ed6703eb6c.zip | |
intrinsics.fmuladdf{16,32,64,128}: expose llvm.fmuladd.* semantics
Add intrinsics `fmuladd{f16,f32,f64,f128}`. This computes `(a * b) +
c`, to be fused if the code generator determines that (i) the target
instruction set has support for a fused operation, and (ii) that the
fused operation is more efficient than the equivalent, separate pair
of `mul` and `add` instructions.
https://llvm.org/docs/LangRef.html#llvm-fmuladd-intrinsic
MIRI support is included for f32 and f64.
The codegen_cranelift uses the `fma` function from libc, which is a
correct implementation, but without the desired performance semantic. I
think this requires an update to cranelift to expose a suitable
instruction in its IR.
I have not tested with codegen_gcc, but it should behave the same
way (using `fma` from libc).
Diffstat (limited to 'compiler/rustc_codegen_llvm')
| -rw-r--r-- | compiler/rustc_codegen_llvm/src/context.rs | 5 | ||||
| -rw-r--r-- | compiler/rustc_codegen_llvm/src/intrinsic.rs | 5 |
2 files changed, 10 insertions, 0 deletions
diff --git a/compiler/rustc_codegen_llvm/src/context.rs b/compiler/rustc_codegen_llvm/src/context.rs index 0a116971e07..c836dd5473f 100644 --- a/compiler/rustc_codegen_llvm/src/context.rs +++ b/compiler/rustc_codegen_llvm/src/context.rs @@ -884,6 +884,11 @@ impl<'ll> CodegenCx<'ll, '_> { ifn!("llvm.fma.f64", fn(t_f64, t_f64, t_f64) -> t_f64); ifn!("llvm.fma.f128", fn(t_f128, t_f128, t_f128) -> t_f128); + ifn!("llvm.fmuladd.f16", fn(t_f16, t_f16, t_f16) -> t_f16); + ifn!("llvm.fmuladd.f32", fn(t_f32, t_f32, t_f32) -> t_f32); + ifn!("llvm.fmuladd.f64", fn(t_f64, t_f64, t_f64) -> t_f64); + ifn!("llvm.fmuladd.f128", fn(t_f128, t_f128, t_f128) -> t_f128); + ifn!("llvm.fabs.f16", fn(t_f16) -> t_f16); ifn!("llvm.fabs.f32", fn(t_f32) -> t_f32); ifn!("llvm.fabs.f64", fn(t_f64) -> t_f64); diff --git a/compiler/rustc_codegen_llvm/src/intrinsic.rs b/compiler/rustc_codegen_llvm/src/intrinsic.rs index 30c6f08e894..bfe623e7fc3 100644 --- a/compiler/rustc_codegen_llvm/src/intrinsic.rs +++ b/compiler/rustc_codegen_llvm/src/intrinsic.rs @@ -86,6 +86,11 @@ fn get_simple_intrinsic<'ll>( sym::fmaf64 => "llvm.fma.f64", sym::fmaf128 => "llvm.fma.f128", + sym::fmuladdf16 => "llvm.fmuladd.f16", + sym::fmuladdf32 => "llvm.fmuladd.f32", + sym::fmuladdf64 => "llvm.fmuladd.f64", + sym::fmuladdf128 => "llvm.fmuladd.f128", + sym::fabsf16 => "llvm.fabs.f16", sym::fabsf32 => "llvm.fabs.f32", sym::fabsf64 => "llvm.fabs.f64", |