Nikhil Jain comments

Results 7 comments of


                                            Nikhil Jain

Prevent forward events from overtaking cancel events.

Thoughts? @carothersc

Cray XE/XT topology functions should use rca_get_meshtopology() to honestly report mesh/torus

*Original date: 2013-06-07 01:39:45* --- As of now cray does not provide a way to differentiate between mesh and tori. Request Cray for the same.

Cray XE/XT topology functions should use rca_get_meshtopology() to honestly report mesh/torus

*Original date: 2015-02-09 17:49:52* --- Not much progress here. Cray is not changing the API much.

CmiDestroyLocks destroys a lock that the thread (or another) is holding

*Original date: 2014-10-21 18:11:37* --- I think this is called explicitly when we are aborting either due to handing some signal or if explicit die is called. Not sure of...

Optimization of MPI layer

*Original date: 2013-02-11 22:24:31* --- Quoting Ralf's Email on this- As for MPI, we've found something that apparently makes it be as fast as gemini_gni-crayxe, and the same seems to...

Bugfix: fortran with threads

@tgamblin I will give it a second try. Due to presence of non argc/argv arguements in init thread, I dint see an easy way, but let me try once more.

Computation and communication time output

@sappyb Is this update to date with all bug fixes, and does it work correctly?