-
Notifications
You must be signed in to change notification settings - Fork 14
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
Reimplementation of distributed band-to-tridiagonal #946
Conversation
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 reasonable to me from a superficial look. Nice work!
FIY [3]
36.1356
14.3168
46.0902
93.3744
36.7428
[3] 228.214s dL (30097, 30097) (512, 512) 128 (2, 2) 18 MC
[4]
35.683
Rank 0 [Mon Jul 24 18:55:14 2023] [c0-0c0s5n2] Fatal error in PMPI_Test: Message truncated, error stack:
PMPI_Test(178)...................: MPI_Test(request=0x1553dadf0d70, flag=0x1553dadf0dc0, status=0x1) failed
MPIR_Test_impl(67)...............:
MPID_nem_gni_lmt_start_recv(1667): Message from rank 1 and tag 234 truncated; 147456 bytes received but buffer size is 2048
srun: error: nid00022: task 0: Exited with exit code 255
srun: launch/slurm: _step_signal: Terminating StepId=47929378.2
slurmstepd: error: *** STEP 47929378.2 ON nid00022 CANCELLED AT 2023-07-24T18:55:16 *** |
cscs-ci run |
Codecov Report
❗ Your organization is not using the GitHub App Integration. As a result you may experience degraded service beginning May 15th. Please install the Github App Integration for your organization. Read more. @@ Coverage Diff @@
## master #946 +/- ##
==========================================
+ Coverage 93.35% 94.81% +1.46%
==========================================
Files 143 129 -14
Lines 8605 7809 -796
Branches 1103 1055 -48
==========================================
- Hits 8033 7404 -629
+ Misses 388 238 -150
+ Partials 184 167 -17
|
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.
Not much to say, I'm not able to fully understand all the changes happening here.
Co-authored-by: Alberto Invernizzi <[email protected]>
cscs-ci run |
cscs-ci run |
Similar improvement as local.
Scaling remains the same.
@msimberg can you have a quick look?
I would like to use this PR for the benchmarks.