-
Notifications
You must be signed in to change notification settings - Fork 798
[Benchmarks] Bump Compute Benchmarks #19857
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
base: sycl
Are you sure you want to change the base?
Conversation
54505c2
to
505b727
Compare
505b727
to
a94c5af
Compare
- stabilize results with a small sleep between binary runs - add combo profiler functionality to allow for choosing between time and cpu count measurement
These scenarios where meant to be ran on BMG systems, not on PVC.
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.
lgtm
@@ -295,12 +318,15 @@ def parse_unit_type(compute_unit): | |||
|
|||
|
|||
class ComputeBenchmark(Benchmark): | |||
def __init__(self, bench, name, test, runtime: RUNTIMES = None): |
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.
Will the benchmark labels be unique with the two different profilers?
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.
No, the logic for extracting stays the same for now, meaning that results are still grepped for instructions count and with this information appropriate charts are generated.
Uh oh!
There was an error while loading. Please reload this page.