Welcome to this web page related to `MPI over InfiniBand, iWARP and other RDMA-enabled Interconnects' project, lead by Network-Based Computing Laboratory (NBCL) of the Ohio State University.
MVAPICH/MVAPICH2 software delivers best performance, scalability and fault tolerance for high-end computing systems and servers using InfiniBand, iWARP and other RDMA-enabled interconnect networking technologies. This software is being used by more than 660 organizations world-wide (Current Users) to extract the potential of these emerging networking technologies for modern systems. This software is also being distributed by many InfiniBand, iWARP and RDMA-enabled interconnect vendors in their software distributions. MVAPICH and MVAPICH2 are also available with Open Fabrics Enterprise Distribution (OFED) stack.
MVAPICH software is powering several supercomputers in the TOP 500 list. Examples (from the Nov '07 ranking) include:
- 3rd, 14,336-core SGI Altix with Intel Clovertown 3.0 GHz at New Mexico Computing Applications Center (NMCAC)
- 22nd, 5,848-core Dell PowerEdge Intel EM64T 2.66 GHz cluster at Texas Advanced Computing Center/Univ. of Texas
- 29th, 9,216-core Appro Quad Opteron dual Core 2.4 GHz at Lawrence Livermore National Laboratory
This project is currently supported by funding from U.S. National Science Foundation , U.S. DOE Office of Science, Cisco Systems, Intel, Linux Networx, Mellanox, QLogic, and Sun Microsystems; and equipment donations from Advanced Clustering , AMD, Apple, Appro, Chelsio, Dell, Fulcrum Microsystems, Fujitsu , IBM, Intel, Mellanox, Microway, NetEffect , QLogic and Sun. Other technology partner includes: TotalView Technologies. More details can be found here.
- (NEW) OMB 3.1 is available. It includes a new Multi-pair Latency Test. [more]
- (NEW) MVAPICH 1.0 with UD-based design, asynchronous progress, flexible message coalesing, APM support, enhanced mpirun_rsh for scalable launching, optimized collectives, support for ConnectX and design for QLogic/InfiniPath-PSM interface is available. [more]
- (NEW) MVAPICH2 1.0.2p1 with message coalesing, hot-spot avoidance, application-initiated systems-level checkpointing, APM support, multi-rail support for iWARP, RDMA read, and blocking support is available. [more]
- Papers at Recent and Upcoming Conferences (CCGrid '08, CAC '08, IPDPS '08, PDSI '07, SC '07, EuroPVM/MPI '07, SNAPI '07, Cluster '07, ICPP '07, HotI '07, ICS '07, VEE '07, CCGrid '07, ISPASS '07, SMPTPS '07 and HIPS '07)[more]
- "High Performance MPI Design using Unreliable Datagram for Ultra-Scale InfiniBand Clusters...", 21st Int'l ACM Conference on Supercomputing (ICS 07)