Please note: All times listed below are in Central Time Zone
Single Root I/O Virtualization (SR-IOV) technology has been steadily gaining momentum for high-performance interconnects such as InfiniBand. SR-IOV can deliver near native performance but lacks locality-aware communication support. This talk presents an efficient approach to build HPC clouds based on MVAPICH2 over OpenStack with SR-IOV. We discuss the high-performance design of virtual machine-aware MVAPICH2 library over OpenStack-based HPC Clouds with SR-IOV. A comprehensive performance evaluation with micro-benchmarks and HPC applications has been conducted on an experimental OpenStack-based HPC cloud and Amazon EC2. The evaluation results show that our design can deliver near bare-metal performance. The MVAPICH2 over OpenStack software package presented in this talk is publicly available from http://mvapich.cse.ohio-state.edu.
The attendees can learn from following aspects:
1. What are the performance benefits of SR-IOV and its limitations on locality-aware inter-VM communication within the same physical node?
2. How to design a high-performance MPI library to efficiently take advantage of novel features such as SR-IOV and IVShmem provided in HPC clouds?
3. How to build an HPC Cloud to deliver near-native performance for MPI applications over SR-IOV enabled InfiniBand clusters?
4. How much performance improvement can be achieved by our proposed design on MPI point-to-point operations, collective operations and applications in HPC clouds?