Dashdavaa Khureltulga1, Baatarsuren Munkhdorj1, Yoshiyuki Kido1, Susumu Date1, Hiroaki Yamanaka2, Eiji Kawai2 and Shinji Shimojo2 Osaka University1, National Institute of Information Communications Technology2
a computer cluster architecture. • Due to the recent rapid scale-out in node number, the cost and complexity of HPC interconnects are getting increasingly high. • MPI (Message Passing Interface) is the de facto standard library to develop parallel distributed applications on clusters. Interconnect of HPC systems 2
MPI+ Applica5on MPI+Library MPI+ Applica5on MPI+Library Applica5on+Informa5on MPI+Applica5on$ aware+control+of+ interconnect Network+Informa5on Leverage SDN architecture to realize tight integration between MPI application and network interconnect; MPI application- aware dynamic interconnect control. Several PoCs: • Offloading MPI broadcast to the network • Dynamic load balancing of traffic load using MPI-layer information