Nitin Bhat

ChaNGa crashes/hangs with UCX machine layer (in SMP mode) on Frontera

45

The 64 node run with the h148 cosmo dataset caused assertion failures at different places. [ChaNGa_6.10_debug_64nodes_h148_run.txt](https://github.com/UIUC-PPL/charm/files/3923647/ChaNGa_6.10_debug_64nodes_h148_run.txt) is the run output. The most common assertion failures was: ``` [3536] Stack Traceback:...

mpi-smp autobuild doesn't complete successfully

4

http://charm.cs.illinois.edu/autobuild/old.2020_10_22__01_06/mpi-linux-x86_64-smp.txt

user-driven-interop fails at exit on mpi-linux-*

1

This seems like a non-recurring bug that I ran into once but didn't see during the second rerun of the Travis CI. ``` make[3]: Entering directory '/home/travis/build/UIUC-PPL/charm/mpi-linux-ppc64le/examples/charm++/user-driven-interop' ../../../bin/testrun +p2 ./hello_user...

NAMD occasionally crashes on Frontera with mpi-smp builds

1

v6.10.1 runs successfully. However, in the master branch, it looks commit (dd8b5a2df5c0822e3c398fc069e852fba1385189) introduces this bug. The bug is caused because of a message that has an incorrect `zcMsgType`, because of...

http://charm.cs.illinois.edu/autobuild/old.2020_11_04__01_07/ofi-linux-x86_64-smp.txt ``` ../../../../bin/testrun +p4 ./pup_buffer +balancer RotateLB +noCMAForZC +setcpuaffinity +CmiSleepOnIdle Running on 4 processors: ./pup_buffer +balancer RotateLB +noCMAForZC +setcpuaffinity +CmiSleepOnIdle charmrun> /usr/bin/setarch x86_64 -R mpirun -np 4 ./pup_buffer +balancer RotateLB...

Incorrect values returned by CmiRankOf and CmiNodeOf on the comm thread

2

Adding the following line to the end of `ConverseCommonInit` shows that `CmiRankOf` and `CmiNodeOf` return incorrect values. Line to add: ` CmiPrintf("[PE:%d][Node:%d][Rank:%d] ConverseCommonInit CmiMyNodeSize()=%d, CmiNodeOf(CmiMyPe()) = %d, CmiRankOf(CmiMyPe()) =%d\n", CmiMyPe(),...

Currently, only an example of BlockMap is mentioned. This could probably be addressed after the conversion of array maps from charm objects to regular C++ objects.

*Original issue: https://charm.cs.illinois.edu/redmine/issues/1931* --- No body.