-
Notifications
You must be signed in to change notification settings - Fork 39
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
Standalone benchmarking script #365
Conversation
* Script simulates one of several data volumes, chosen based on runtime job size. * Ground scheduler moved into the toast package to support calling directly at the job start without using subprocess. * Several small build system cleanups.
… detectors up to a reasonable size and then increase the observing timespan.
Ok @keskitalo , this is ready for review. In addition to the actual benchmark script this also moves the scheduler into the package and there are some other small tweaks. |
@@ -60,6 +60,6 @@ void init_pixels(py::module & m) { | |||
(tuple): The (local submap, pixel within submap) for each global pixel. | |||
|
|||
)"); | |||
m.def("global_to_local", &global_to_local <int32_t>); | |||
m.def("global_to_local", &global_to_local <int16_t>); | |||
m.def("global_to_local", &global_to_local <int32_t> ); |
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.
Looks like uncrustify
has slightly changed.
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.
Yeah, I am using version 0.69 from ubuntu sources. I see upstream is at version 0.71. If we become too annoyed in the future we could enforce a particular version...
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.
Looks great! Merge away.
This script scales the data volume according to the job size and attempts to use a group size of 4 nodes and a fake focalplane such that every process has a few detectors. This needs more testing.