ICPP 2014 Keynotes Summary 09/24

Data Centric Systems: The Next Paradigm in Computing Speaker: Dr. Tilak Agerwala ◦ Vice President, Data Centric Systems ◦ IBM T.J. Watson Research Center 2014/09/09

Data-Centric System HPE (High Performance Environment) ◦ = HPC + HPA Mixed compute capabilities required. ◦ Heterogeneity is important.

IBM Data-Centric Design Principles Minimize data motion Enable compute in all levels of the systems hierarchy Modularity Application design Leverage OpenPOWER

High Performance Computing - Future Directions Speaker: Prof. Jack Dongarra ◦ University of Tennessee, Knoxville 2014/09/10

Top500 Factoids There are 37 systems > Pflop /s (up 6 from November). About 90% of all the systems on the Top500 list are integrated by U.S. vendors, including 65 of the 76 Chinese supercomputers. HP has 182 systems on this list, or more than 36%, followed by IBM with 176, or 35%. Cray has 50 or 10%, SGI at 19 systems, and Dell at 8 systems. Intel processors largest share, 87% followed by AMD, 6%. For the first time, < 50% of Top500 are in the U.S. -- just 233 of the systems are U.S.-based, China #2 w/76. IBM’s BlueGene/Q is still the most popular system in the TOP10 with four entries. Infiniband found in 221 systems, GigE in 202, 10-GigE in 75.

Issue: Memory Transfer Communication bounded operation ◦ Real performance < peak performance ◦ “Its all about data movement” ◦ Ex:  Take two double precision vectors x and y of size n=375,000.  Time to move the vectors from memory to cache:  (6MBytes) / (25.6GBytes/sec) = 0.23ms  Time to perform computation of DOT:  (2n flop) / (56Gflop/sec) = 0.01ms

eBay Storage: from Good to Great Speaker: Farid Yavari ◦ Sr. Storage Architect - Global Platform and Infrastructure (GPI) ◦ eBay Inc. 2014/09/11

Elastic Infrastructure An infrastructure that can spawn, destroy, grow, shrink and move processes dynamically and efficiently within and across data centers. ◦ Automated Control Plane ◦ Resource Pool ◦ Traffic Management

Key Initiatives to Enable an Elastic Infrastructure Separation of Storage and Compute ◦ Hadoop use case Software defined storage, software defined network Cloud, SLA, OLA based services ◦ Standardization ◦ Automation ◦ Show/Chargeback ◦ Self Service