-
Notifications
You must be signed in to change notification settings - Fork 66
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
#8672: Reduce profiler global memory usage #8675
Conversation
5d8c11d
to
1a83bbf
Compare
ce08c57
to
d2beeb4
Compare
d2beeb4
to
fa912d8
Compare
fa912d8
to
d132a6c
Compare
d132a6c
to
18248e8
Compare
DEVICE PERF CI is only failing on resnet with slight improvement on fps. Profile infra is fixed and it runs multi-op on GS: https://github.com/tenstorrent/tt-metal/actions/runs/9180493014/job/25245030244 TK3 Passing : https://github.com/tenstorrent/tt-metal/actions/runs/9176794301 Microbenchmark passing: https://github.com/tenstorrent/tt-metal/actions/runs/9176808113/job/25232961616 All post commit passing with the new GS profiler smoke tests: https://github.com/tenstorrent/tt-metal/actions/runs/9176781976/job/25232870593 |
Reduce profiler lookup table type from
uint32_t
touint8_t
and add GS profiler smoke tests as part of post commit that does not require reset.