Skip to content

[FEA] Specify L2 cache eviction in TMA copy #2528

@tridao

Description

@tridao

Which component requires the feature?

CuTe DSL

Feature Request

I'd love to be able to control L2 cache eviction when doing TMA load and TMA store (e.g. evict_first, evict_last)

Additional context
This is important for some attention kernels, as we used it in FA3, e.g. here:
https://github.com/Dao-AILab/flash-attention/blob/413d07e9deef1e3c793c7de59d7146b43ae4d558/hopper/mainloop_fwd_sm90_tma_gmma_ws.hpp#L753

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions