Skip to content
GitLab
Commit deefda70 authored by Matt Arsenault's avatar Matt Arsenault
Browse files

AMDGPU: Use exp2 and log2 intrinsics directly for f16/f32 

These codegen correctly but f64 doesn't. This prevents losing fast
math flags on the way to the underlying intrinsic.

https://reviews.llvm.org/D158997
parent dac8f974
Expand all Hide whitespace changes
Inline Side-by-side
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment