Jim Phillips

  • Email:
  • Registered on: 01/23/2014
  • Last connection: 04/26/2019





11:11 PM Charm++ Bug #2062 (New): Don't force -lcudart just because cuda.h was found during configure
If CUDA supposed is detected by configure it not only builds the CUDA features, but also modifies the link options fo...


09:15 PM Charm++ Bug #2059: Inconsistent CPU affinity options for running SMP programs
The verbs builds should *not* report running mpi.
09:04 PM Charm++ Bug #2059: Inconsistent CPU affinity options for running SMP programs
You need to at least show the options with which you submitted the job, since mpirun often picks up environment varia...


10:12 AM Charm++ Bug #2045: Chare array broadcast messages don't appear to be freed by the runtime
Perhaps spring cleaning could be triggered by the number of accumulated broadcasts (and/or amount of memory used by a...


02:06 PM Charm++ Bug #2026: charm-6.8.2 breaks linking process of NAMD if it's patched with shared version of PLUMED


03:16 PM Charm++ Support #2041: charmrun with mpirun instead of srun?
For the mpi-... builds of Charm++ you can run the binary with mpirun/mpiexec/srun directly rather than via charmrun. ...


04:55 PM Charm++ Bug #1165: avoid -lm with Intel compiler
It's really hard to tell. Does the -lm get inserted before or after the user-provided libraries? Assuming first-mat...
01:23 PM Charm++ Bug #1332: assumes remote shell is OpenSSH
I don't think this is worth trying to fix as it's easy enough to do a wrapper script or use ++mpiexec if the user ins...
01:17 PM Charm++ Documentation #1302: pass arbitrary arguments to mpiexec via charmrun
Yes, that does work.
Please add to the docs at
01:05 PM Charm++ Bug #1165: avoid -lm with Intel compiler
This may have been old advice. Intel's meager docs say to use mathifm.h and even then I need -limf to get any Intel ...

Also available in: Atom