diff options
| author | Daniil Dudkin <unterumarmung@yandex.ru> | 2023-09-19 22:49:48 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-09-19 22:49:48 +0300 |
| commit | 641124a9b98eef668d8bb3bd3b6da5105a17284e (patch) | |
| tree | 9e30a48f137429a701ebd93a6345e63c11452aea /llvm/docs/CommandGuide | |
| parent | 80c01dd626e05369aa438ca3800bbd5874cfc8e4 (diff) | |
| download | llvm-641124a9b98eef668d8bb3bd3b6da5105a17284e.zip llvm-641124a9b98eef668d8bb3bd3b6da5105a17284e.tar.gz llvm-641124a9b98eef668d8bb3bd3b6da5105a17284e.tar.bz2 | |
[mlir][spirv] Add conversions for Arith's `maxnumf` and `minnumf` (#66696)
This patch is part of a larger initiative aimed at fixing floating-point
`max` and `min` operations in MLIR:
https://discourse.llvm.org/t/rfc-fix-floating-point-max-and-min-operations-in-mlir/72671.
In this commit, we add conversion patterns for the newly introduced
operations `arith.minnumf` and `arith.maxnumf`. When converting to
`spirv.CL`, there is no need to insert additional guards to propagate
non-NaN values when one of the arguments is NaN because `CL` ops do
exactly the same. However, `GL` ops have undefined behavior when one of
the arguments is NaN, so we should insert additional guards to enforce
the semantics of Arith's ops.
This patch addresses the 1.5 task of the mentioned RFC.
Diffstat (limited to 'llvm/docs/CommandGuide')
0 files changed, 0 insertions, 0 deletions