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

[OpenCL] Add vectorization to cuda conv2d_nhwc schedule #8636

Merged
merged 5 commits into from
Sep 30, 2021
Merged

[OpenCL] Add vectorization to cuda conv2d_nhwc schedule #8636

merged 5 commits into from
Sep 30, 2021

Commits on Sep 23, 2021

  1. Add vectorization to cuda conv2d_nhwc schedule 

    Adding vectorization significantly improved performance. About 6-7x
boost.
    @echuraev
    echuraev committed Sep 23, 2021
    Configuration menu
    Copy the full SHA
    b66ac7f View commit details
    Browse the repository at this point in the history

  2. Apply comment

    @echuraev
    echuraev committed Sep 23, 2021
    Configuration menu
    Copy the full SHA
    66135c9 View commit details
    Browse the repository at this point in the history

  3. Move schedule to topi/gpu dir

    @echuraev
    echuraev committed Sep 23, 2021
    Configuration menu
    Copy the full SHA
    d8cf61f View commit details
    Browse the repository at this point in the history

  4. Add vectorization to inner loop

    @echuraev
    echuraev committed Sep 23, 2021
    Configuration menu
    Copy the full SHA
    8014e80 View commit details
    Browse the repository at this point in the history

  5. Update values of vectorization factor

    @echuraev
    echuraev committed Sep 23, 2021
    Configuration menu
    Copy the full SHA
    828cdfa View commit details
    Browse the repository at this point in the history