diff options
| author | Jacob Pratt <jacob@jhpratt.dev> | 2024-12-05 05:50:51 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-05 05:50:51 -0500 |
| commit | f5f8a1f8cee4d853d51d27831427c98c8c6923bb (patch) | |
| tree | 49524918d328509c5aad0691b666129e10fe1130 | |
| parent | b5a7f41a872660196bcb6d1b7af7a4cc6b773a70 (diff) | |
| parent | f4217f42967621c53dbeb1ecdd698c1d17e97b7a (diff) | |
| download | rust-f5f8a1f8cee4d853d51d27831427c98c8c6923bb.tar.gz rust-f5f8a1f8cee4d853d51d27831427c98c8c6923bb.zip | |
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``
| -rw-r--r-- | library/core/src/intrinsics/simd.rs | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/library/core/src/intrinsics/simd.rs b/library/core/src/intrinsics/simd.rs index 0d24b0558c5..f80a60d471c 100644 --- a/library/core/src/intrinsics/simd.rs +++ b/library/core/src/intrinsics/simd.rs @@ -619,7 +619,8 @@ extern "rust-intrinsic" { /// 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 /// 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. #[cfg(not(bootstrap))] |