Charm++ parallel programming system

[Phil Miller <mille121 AT illinois.edu>]

With the resolution of the remaining open issues targeted for the 6.6 release of Charm++, I've now tagged a release candidate in our repository, v6.6.0-rc1. Please test and benchmark the code with your applications, and let us know urgently if any issues become apparent. We hope to release 6.6.0 in the next few days.

Some highlights of this release will include

- Machine target files for Cray XC systems ('gni-crayxc')

- Interoperability with MPI code using native communication interfaces on Blue Gene Q (PAMI) and Cray XE/XK/XC (uGNI) systems

- Support for partitioned jobs on all machine types, including TCP/IP and IB Verbs networks using 'netlrts' and 'verbs' machine layers

- A substantially improved version of our asynchronous library, CkIO, for parallel output of large files

- Narrowing the circumstances in which the runtime system will send overhead-inducing ReductionStarting messages

- A new fully distributed load balancing strategy, DistributedLB, that produces high quality results with very low latency

- Queue order randomization to assist in debugging race conditions in application and runtime code

- Numerous bug fixes, performance enhancements, and smaller improvements in the facilities provided

For more detail on changes since the 6.5 release series, see the list of resolved issues in our Redmine instance:
https://charm.cs.illinois.edu/redmine/projects/charm/issues?c[]=tracker&c[]=status&c[]=priority&c[]=subject&c[]=assigned_to&c[]=updated_on&f[]=fixed_version_id&f[]=&group_by=tracker&op[fixed_version_id]=%3D&set_filter=1&sort=id&utf8=%E2%9C%93&v[fixed_version_id][]=4

or the full list of changes via the Git version control history.