3f9aa50b70
intrinsics fmuladdf{32,64}: expose llvm.fmuladd.* semantics
Add intrinsics `fmuladd{f32,f64}`. 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
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).
---
This topic has been discussed a few times on Zulip and was suggested, for example, by `@workingjubilee` in [Effect of fma disabled](https://rust-lang.zulipchat.com/#narrow/stream/122651-general/topic/Effect.20of.20fma.20disabled/near/274179331).
|
||
|---|---|---|
| .. | ||
| bootstrap | ||
| ci | ||
| doc | ||
| etc | ||
| gcc@fd3498bff0 | ||
| librustdoc | ||
| llvm-project@dd46457da7 | ||
| rustdoc-json-types | ||
| tools | ||
| README.md | ||
| stage0 | ||
| version | ||
This directory contains some source code for the Rust project, including:
- The bootstrapping build system
- Various submodules for tools, like cargo, tidy, etc.
For more information on how various parts of the compiler work, see the rustc dev guide.