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

Fix performance degradation of HIP dot #207

Open
wants to merge 3 commits into
base: develop
Choose a base branch
from
Open

Fix performance degradation of HIP dot #207

wants to merge 3 commits into from

Commits on Jul 1, 2024

  1. Fix performance degradation of HIP dot 

    The results did not match between cuda-stream and hip-stream on the same
NVIDIA GPU card (NVIDIA A100 40GB PCIe) when large arraysize is specified.
cuda-stream uses the number of SMs to decide dot_num_blocks, which looks
more sensible than to use arraysize to determine the parameter. It is used
as kernel grid size and iteration count for reduction in the host code.

Link: UoB-HPC@9954b7d
Signed-off-by: Daisuke Matsuda <[email protected]>
    @ddmatsu
    ddmatsu committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    0c72fed View commit details
    Browse the repository at this point in the history

  2. Delete unused parameter from hip-stream 

    Signed-off-by: Daisuke Matsuda <[email protected]>
    @ddmatsu
    ddmatsu committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    580090a View commit details
    Browse the repository at this point in the history

  3. Delete obsolete definitions from hip-stream header 

    Signed-off-by: Daisuke Matsuda <[email protected]>
    @ddmatsu
    ddmatsu committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    be8f70f View commit details
    Browse the repository at this point in the history