mirror of
https://github.com/rust-lang/rust.git
synced 2025-06-05 11:48:30 +00:00
Rollup merge of #133844 - RalfJung:simd_relaxed_fma-nondet, r=workingjubilee
clarify simd_relaxed_fma non-determinism This is the safer spec in the sense that it is more likely to be satisfied by the backend -- and if people are okay with a non-deterministic result, I assume they don't care whether it's the same choice across all lanes or not? Cc ``@calebzulawski`` ``@workingjubilee``
This commit is contained in:
commit
f5f8a1f8ce
@ -619,7 +619,8 @@ extern "rust-intrinsic" {
|
|||||||
/// set has support for a fused operation, and that the fused operation is more efficient
|
/// set has support for a fused operation, and that the fused operation is more efficient
|
||||||
/// than the equivalent, separate pair of mul and add instructions. It is unspecified
|
/// than the equivalent, separate pair of mul and add instructions. It is unspecified
|
||||||
/// whether or not a fused operation is selected, and that may depend on optimization
|
/// whether or not a fused operation is selected, and that may depend on optimization
|
||||||
/// level and context, for example.
|
/// level and context, for example. It may even be the case that some SIMD lanes get fused
|
||||||
|
/// and others do not.
|
||||||
///
|
///
|
||||||
/// `T` must be a vector of floats.
|
/// `T` must be a vector of floats.
|
||||||
#[cfg(not(bootstrap))]
|
#[cfg(not(bootstrap))]
|
||||||
|
Loading…
Reference in New Issue
Block a user