Daniel Hernandez-Juarez 64f67f870d [mlir][AMDGPU] Enable emulating vector buffer_atomic_fadd for bf16 on gfx942 (#129029) ...

- Change to make sure architectures < gfx950 emulate bf16
buffer_atomic_fadd
- Add tests for bf16 buffer_atomic_fadd and architectures: gfx12, gfx942
and gfx950

---------

Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>

2025-03-13 14:30:45 -05:00

8.9 KiB

Raw Blame History

View Raw