1. 1 Advanced Storage Technologies for High Performance Computing Sorin, Faibish EMC NAS Senior Technologist IDC HPC User Forum, April 14-16, Norfolk, VA

2. 2 IDC HPC User Forum 2008 New HPC Storage Intensive Applications Storage Challenges*  New algorithms that can scale to search and process massive datasets;  New metadata management of distributed data sources;  New platforms provide uniform high-speed memory access to multi terabyte data structures;  Hybrid interconnect architectures to process and filter multi gigabyte data streams from scientific instruments;  High-performance, high-reliability, petascale distributed file systems;  New approaches to software mobility, so that algorithms can execute on nodes where the data resides;  Flexible and high-performance software integration technologies running on diverse computing platforms;  Data signature generation techniques for data reduction and rapid processing. *Computer Magazine: http://www.computer.org/portal/cms_docs_computer/computer/homepage/0408/R4gei.pdf

3. 3 IDC HPC User Forum 2008 New Storage Technologies for HPC Storage Technologies  Virtualization to address the multi- core problem  CDP and memory snapshots to address storage failures during computation  DR and distributed cache appliances to address computation across geographies  SSD disk technology to address Data Intensive Super Computing tasks as well as decrease power consumption of storage  pNFS and RDMA technologies to increase the I/O speeds and reduce computation cycles Storage at Previous HPC User Forum

4. 4 IDC HPC User Forum 2008 New Concept – Better Utilization of multi-cores  Current Implementation –Application split on multiple single core SMP HW –Use middleware SW (Platform)

5. 5 IDC HPC User Forum 2008 New Concept – Better Utilization of multi-cores  Dual-core support added –Application modified to support SMP dual core –CPU used: 4x 100% (100%) –Licenses paid: 4 –Licenses used: 4

6. 6 IDC HPC User Forum 2008 New Concept – Better Utilization of multi-cores  Quad-core chips appear –CPU used: 4x 100% (4/8=50%) –Licenses paid: 8 –Licenses used: 4 –Application must be modified or

7. 7 IDC HPC User Forum 2008 New Concept – Better Utilization of multi-cores  Quad-core chips appear –CPU used: 4x 100% (50%) –Licenses paid: 8 –Licenses used: 4 –Application must be modified or –Use VM with CPU affinity –CPU used: 8x80% (80%) –Licenses used: 8

8. 8 IDC HPC User Forum 2008 New Concept – Better Utilization of multi-cores  N-cores chips are coming –Use VM with VT support –CPU used: 2xNx90% (90%) –Licenses paid=used: 2xN

9. 9 IDC HPC User Forum 2008 New Concept – Better Utilization of multi-cores  Core agnostic Middleware will work with as many cores as available –Enabled by pNFS access to shared storage

10. 10 IDC HPC User Forum 2008 CDP + Memory Snapshots in HPC applications SAN SunIBM HPHDS EMC HPC Application platform support CDP Journal + Memory Snapshots CDP Appliance  CDP Technology will work with Real and Virtual Infrastructures –VM snapshots on central storage repository –VM and HW hosts memory snapshots –Any SAN or NAS storage –Recover HPC job at any point in time (last minute failure after 2 weeks run)

11. 11 IDC HPC User Forum 2008 HPC Application remote platform HPC Application platform support Continuous Remote Replication in HPC Site A Site B SAN SunIBM HPHDS EMC SunIBM HPHDS EMC Heterogeneous storage Cache Appliance Cache Appliance Heterogeneous Blades; VM+HW  Distributed cache engines allow distributed access to shared storage –Remote Compute Nodes accessing the shared storage

12. 12 IDC HPC User Forum 2008 SSD Disks in HPC applications  Solid State Disks will replace Disk Drives –Today HPC workloads are mostly compute intensive –Data intensive Super Computing (DISC) applications start to appear (see: IEEE Computer Magazine, April 2008) –SSD will balance performance between DISC and compute intensive HPC applications –EMC DMX has SSD today (25 SSD = 800K iops or 5 GB/sec) SAN EMC HPC Application platform support DMX + SSD

13. 13 IDC HPC User Forum 2008 pNFS addresses the storage access issues –Remove servers layer between CE and shared storage –Separates MD traffic from Data Traffic –Asymmetric storage architectures increase scalability –SSD increase I/O speed HPC Architecture SSD STORAGE CONNECTIVITY MIDDLEWARE NFS S E R V E R S HPC Jobs Storage must be Networked Compute Engines CONNECTIVITY pNFS pNFS will deliver very high I/O speeds to HPC

14. 14 IDC HPC User Forum 2008  MD is directed to the single MD server  Data is served by storage servers or storage arrays directly from host to storage  Storage access controlled by iSCSI  I/O to native IB or 10G storage redirected via RDMA in HW iSCSI (iSER) NFS (pNFS) Storage array NFS/pNFS File systems Data path Control path Native IB Storage Array Cache MetaData Cache CE Cache RDMA pNFS with Infiniband RDMA value added to HPC

15. 15 IDC HPC User Forum 2008