Skip to content

Preliminary support for Ray in Task-Bench#85

Open
rohany wants to merge 4 commits into
StanfordLegion:masterfrom
rohany:ray
Open

Preliminary support for Ray in Task-Bench#85
rohany wants to merge 4 commits into
StanfordLegion:masterfrom
rohany:ray

Conversation

@rohany

@rohany rohany commented Apr 29, 2022

Copy link
Copy Markdown

This PR doesn't make any claims about Ray's performance, but just sets up infrastructure within task-bench to perform further evaluations of Ray.

@rohany

rohany commented Apr 29, 2022

Copy link
Copy Markdown
Author

cc @elliottslaughter

@elliottslaughter elliottslaughter left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry for taking so long to look at this. The implementation looks good. I think the outstanding items are:

  • Build infrastructure: need to fill out get_deps.sh, build_all.sh, test_all.sh so that we can run this in CI (and on supercomputers). You can see Dask as an example.
  • Performance: optional for the first PR, but it would be nice to get to get (a) performance numbers, and (b) a review by the Ray team to make sure everything looks ok.

Comment thread dask/task_bench_core.py
]).decode("utf-8")
ffi = cffi.FFI()
ffi.cdef(core_header)
c = ffi.dlopen("libcore.so")

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think you're trying to modify the Dask implementation, and this seems to work in our CI. Do you need this change?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants