Welcome to this web page related to `MPI over InfiniBand, 10GigE/iWARP and RDMA over Ethernet (RDMAoE)' 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, 10GigE/iWARP and RDMAoE networking technologies. This software is being used by more than 1,050 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, 10GigE/iWARP and RDMAoE vendors in their software distributions. MVAPICH and MVAPICH2 are also available with Open Fabrics Enterprise Distribution (OFED) stack. MVAPICH/MVAPICH2 software is powering several supercomputers in the TOP 500 list. Examples (from the Nov '09 ranking) include:
- 5th, 71,680-core (Tianhe-1) at NUDT, China
- 9th, 62,976-core (Ranger) at Texas Advanced Computing Center (TACC)
- 27th, 18,224-core (Juno) at Lawrence Livermore National Laboratory (LLNL)
- 48th, 18,176-core (Chinook) at Pacific Northwest National Laboratory (PNNL)
This project is currently supported by funding from U.S. National Science Foundation , U.S. DOE Office of Science, Ohio Board of Regents, ODOD , Cisco Systems, Intel, Linux Networx, Mellanox, QLogic, and Sun Microsystems; and equipment donations from Advanced Clustering , AMD, Apple, Appro, Chelsio, Dell, Fulcrum Microsystems, Fujitsu , Intel, Mellanox, Microway, NetEffect , QLogic and Sun. Other technology partner includes: TotalView Technologies. More details can be found here.
Announcements more
- MVAPICH 1.2RC1 with Network Fault Resiliency (NFR), RDMA over Ethernet (RDMAoE) and multiple other support, enhancements and fixes is available. [more]
- MVAPICH2 1.4 with XRC support, Dynamic Process Management (DPM) support, support for RDMAoE (LLE), native support for QLogic InfiniPath, enhancement to job start-up, scalable checkpoint-restart with mpirun_rsh framework and intra-node shared memory (kernel-level with LiMIC2) support is available. [more]
- OMB 3.1 is available. It includes a new Multi-pair Latency Test. [more]
Publications more
- Papers at Recent and Upcoming Conferences (CAC '10, CCGrid '10, SNAPI '10, HiPC '09, ICPP '09, P2S2 '09, EuroPVM/MPI '09, Cluster '09, HPI-DC '09, HotI '09, and ISC '09)[more]
- "Designing Next Generation Clusters: Evaluation of InfiniBand DDR/QDR on Intel Computing Platforms", Hot Interconnect (HOTI '09)
- "RDMA over Ethernet - A Preliminary Study", HPIDC '09
Presentations
- (NEW) Upcoming Tutorial on InfiniBand and High-speed Ethernet at
ISC '10 in Hamburg, Germany
and
ICS '10 in Tsukuba, Japana.
Past tutorials at Hot Interconnect '09, Cluster '09, Supercomputing '09 (S07 and S14), and HPCA '10
- OpenFabrics Sonoma Presentation [more]

