A new preview release of MPICH, 3.3b1, is now available for download. MPICH 3.3 contains a new (non-default) device layer implementation – CH4. CH4 is designed for low software overheads to better exploit next-generation hardware. An OFI (http://libfabric.org) or UCX (http://openucx.org) library is required to build CH4. Example configure lines:
./configure --with-device=ch4:ofi --with-libfabric=<path/to/ofi/install>
./configure --with-device=ch4:ucx --with-ucx=<path/to/ucx/install>
CH4 is still in beta stages, meaning there are known build issues and bugs, but most tests and common benchmarks will complete on 64-bit Linux systems. Since 3.3a3, there have been more stability improvements, bug fixes, and code cleanup.
Also in this release is a reorganization of MPI collectives to make it easier to integrate new algorithms. A new framework is added to enable collective algorithms to be issued either on generic or device-specific functionality using a C++-template style system. Support is added for creating communicators based on hardware topology hints, and SLURM integration in Hydra is updated to work with the latest node list format. You can find the release on our downloads page.