Skip to content

Hardware-accelerated arithmetic #30

Description

@AntonOresten

add, sub, mul, fma getting added in PTX ISA 9.4 for sm_100a (Blackwell) and sm_103a (Blackwell Ultra):

https://docs.nvidia.com/cuda/developer-preview/13.4/parallel-thread-execution/index.html#alternate-floating-point-instructions

Related: JuliaGPU/cuTile.jl#240

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions