Welcome to this web page related to `MPI over InfiniBand, 10GigE/iWARP and RDMA over Converged Ethernet (RoCE)' 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 RoCE networking technologies. This software is being used by more than 1,930 organizations world-wide in 68 countries (Current Users) to extract the potential of these emerging networking technologies for modern systems. As of May '12, more than 109,000 downloads have taken place from this project's site. This software is also being distributed by many InfiniBand, 10GigE/iWARP and RoCE 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 November '11 ranking) include:
- 5th, 73,278-core (Tsubame 2.0) at Tokyo Institute of Technology
- 7th, 111,104-core (Pleiades) at NASA
- 25th, 62,976-core (Ranger) at Texas Advanced Computing Center (TACC)
- 39th, 22,656-core (Lonestar) at Texas Advanced Computing Center (TACC)
- 48th, 12,608-core (Gordon) at UCSD/San Diego Supercomputer Center (SDSC)
This project is 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, NVIDIA, QLogic, and Sun Microsystems; and equipment donations from Advanced Clustering , AMD, Appro, Chelsio, Dell, Fulcrum, Fujitsu , Intel, Mellanox, Microway, NetEffect , QLogic and Sun. Other technology partner includes: TotalView Technologies. More details can be found here.
Announcements more
- (NEW) MVAPICH2 1.8
with
high-performance MPI communication from NVIDIA GPU device memory
(to/from other device and host memory) with IPC, collectives
and datatype support; CPU binding granularity at socket
and numanode level, checkpoint-restart and run-through stabilization
with Nemesis, suspend/resume, and
enhanced integration with SLURM
and PBS,
compared to 1.7 is available. [more]
- MVAPICH 1.2RC1 with Network Fault Resiliency (NFR) and multiple enhancements and fixes is available. [more]
- (NEW) OMB 3.6 including extensions for collectives and tests with NVIDIA GPU Device and CUDA support is available.
[more]
Publications more
- Papers at Recent and Upcoming Conferences (ICS '12, ISC '12, IPDPS '12, AsHES '12, SMTPS '12, CCGrid '12, TI-HPCS '12, ISPASS '12, HiPC '11, Cluster '11, PPAC '11, ICPP '11, Resilience '11, PROPER '11, and HotI '11)[more]
- "Intra-MIC MPI Communication using MVAPICH2: Early Experience", TI-HPCS '12, BEST Student Paper Award
Presentations
- (NEW) Upcoming Tutorial on InfiniBand and High-speed Ethernet at CCGrid '12, ISC '12, and ICS '12.
- Past tutorials at
HPCA '12.
- (NEW) Past Keynote Talk at
HPC Council China 2011 Workshop and MPI talks at
HPC Advisory Council Switzerland Workshop.
- (NEW) OpenFabrics Monterey Presentations [more]
-
Supercomputing '11 events.