Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Implement cub::DeviceFind::FindIf #2405

Open
wants to merge 13 commits into
base: main
Choose a base branch
from
Open

Implement cub::DeviceFind::FindIf #2405

wants to merge 13 commits into from
+1,190 −0

Commits on Nov 2, 2024

  1. cub::DeviceFind::FindIf dummy implementation and test

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    fd6e836 View commit details
    Browse the repository at this point in the history

  2. Calculate d_temp_storage bytes properly aligned and use grid_size acc… 

    …ording to tile size
    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    afd42cb View commit details
    Browse the repository at this point in the history

  3. Add cub::Device::FindIf nvbench benchmark

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    7610da6 View commit details
    Browse the repository at this point in the history

  4. Introduced tile based loop

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    e683a3d View commit details
    Browse the repository at this point in the history

  5. Use multiple elements per thread

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    b7a6db5 View commit details
    Browse the repository at this point in the history

  6. Optimized solution

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    f69e688 View commit details
    Browse the repository at this point in the history

  7. Add vectorized loads

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    81c676e View commit details
    Browse the repository at this point in the history

  8. Separate benchmarks into different files

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    b8b86dd View commit details
    Browse the repository at this point in the history

  9. Add split implementation that works with both vectorized and non vect… 

    …orized loads
    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    f93ff9b View commit details
    Browse the repository at this point in the history

  10. Add elaborate unit testing

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    50dc8f5 View commit details
    Browse the repository at this point in the history

  11. Add Dispatch and Agent layers

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    c508b99 View commit details
    Browse the repository at this point in the history

  12. Reviews, cleanup

    @gonidelis
    gonidelis committed Nov 2, 2024
    Configuration menu
    Copy the full SHA
    eaa5b75 View commit details
    Browse the repository at this point in the history

Commits on Nov 11, 2024

  1. CacheModifiedInputIterator accepts const 

    Co-authored-by: Bernhard Manfred Gruber <[email protected]>
    @gonidelis @bernhardmgruber
    gonidelis and bernhardmgruber authored Nov 11, 2024
    Configuration menu
    Copy the full SHA
    7c2f2a8 View commit details
    Browse the repository at this point in the history