-
Notifications
You must be signed in to change notification settings - Fork 868
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.
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
MPI_T Events #8057
base: main
Are you sure you want to change the base?
MPI_T Events #8057
Conversation
Can one of the admins verify this patch? |
ok to test |
@cchambreau, Hi. Is this desirable for Open MPI v5.0 (not MPI-4.0 compliant)? If so please, rebase it and get it into master and then cherry-pick to v5.0.x branch after it's in master. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you rebase and fix all current conflicts?
Do we have any tests for this MPI_T event functionality?
@cchambreau could you please rebase? thanks. |
Howard will rebase and merge unless objections are raised. |
4b3c70d
to
2400b8a
Compare
The IBM CI (GNU/Scale) build failed! Please review the log, linked below. Gist: https://gist.github.com/d182f369f64bb66a239cbf4b56b1e3ce |
The IBM CI (XL) build failed! Please review the log, linked below. Gist: https://gist.github.com/20f1009df186bd52f322544e39a3595c |
@cchambreau can you fix the conflicts on this PR? Thanks! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In addition to the other comments on this PR, please update this PR to use opal_clock_gettime()
(and, if necessary, opal_clock_getres()
) from #9798.
3ed1cd9
to
14ccc8d
Compare
bot:ompi:retest |
14ccc8d
to
9e35c26
Compare
@jquyres I'm hoping to get back to this in April. |
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
…or fixes. Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
dss.h has been removed since this PR was originally opened Signed-off-by: Howard Pritchard <howardp@lanl.gov>
…cking. Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
…functionality Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
- Correct MPI_T_event_dropped_cb_function arguments - Check for negative event index Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
new profile interface generation method Signed-off-by: Howard Pritchard <howardp@lanl.gov>
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
by fixing some code Signed-off-by: Howard Pritchard <howardp@lanl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
values. Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Chris Chambreau <chambreau1@llnl.gov>
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
b814b33
to
66b29d5
Compare
@cchambreau i'm trying to get this PR fixed up for merging so did a rebase and pushed to your repo. |
Discussed some at the 2024 F2F. Not sure who really needs this. Joseph will ping scorep people about whether they may want/need this feature. |
Is it really a question of who needs this? I.e., isn't this part of conformance to the MPI standard? |
Some tools folks were pinged about use of MPI_T events as part of Open MPI devel f2f meeting 4/2024. ScoreP developer said its on their todo list to use this feature in some future release. Tau may already use events if the MPI being used supports it. Possibly some unreleased version of MPI Advisor can use them. |
It would be nice to have this standard-compliant interface from tools perspective. |
This PR includes Nathan Hjelm's reworking of PERUSE functionality to implement the MPI_T Events API as specified in the MPI 4.0 proposal. Subsequent minor changes to the MPI_T Events API were made and included here. The API and an initial set of events were tested against Marc-André Hermann's MEL tracing tool and other test cases. History, a description of the API and experience with tools can be found in "Enabling callback-driven runtime introspection via MPI_T."