MPICH
MPICH is a robust and flexible implementation of the MPI (Message Passing Interface). MPI is often used with parallel or distributed computing projects. MPICH is a multi-platform, configurable system (development, execution, libraries, etc) for MPI. It can acheive parallelism using networked machines or using mulitasking on a single machine.
| Tags | Software Development Libraries Clustering/Distributed Networks |
|---|
Recent releases
- 10 Oct 2008 22:36
Changes: This version adds a new multi-pair latency benchmark.
- 02 Jul 2008 17:52
Changes: This release adds message coalescing, hot-spot avoidance, application-initiated systems-level checkpointing, APM support, multi-rail support for iWARP, RDMA read, and blocking support. Assorted bugfixes.
- 02 May 2008 07:19
Changes: This release adds RDMA CM-based on-demand connection management for OpenFabrics Gen2-* interfaces, uDAPL on-demand connection management, message coalescing support to enable reduction of per Queue-pair send queues, a Hot-Spot Avoidance Mechanism (HSAM) for alleviating network-congestion in large scale clusters, RDMA Read utilization for increased overlap of computation and communication for OpenFabrics devices, and support for an OpenFabrics Gen2-iWARP interface and RDMA CM.
- 02 May 2008 10:42
Changes: This release adds an initial ROMIO device for BlueGene/P. It has major cleanup for the propagation of user-defined and other MPICH2 flags throughout the code. It adds support for the STI Cell Broadband Engine. It adds datatype free hooks to be used by devices independently. It adds device-specific timer support. "make uninstall" works cleanly now. Support has been added to take hints from a config file. There are more tests and bugfixes for non-blocking I/O. Support has been added for using the PMI Clique functionality for process managers that support it.
- 29 Mar 2008 03:20
Changes: This version adds a new multi-pair latency benchmark.
