2. Talk Outline The need for High-Performance Computing (HPC) Trends, Architecture, Systems, Models High-Throughput Computing More on Distributed Computing Grid Computing Cloud Computing Summary and Q&As
3. High-Performance Computing (HPC) Trends, Architecture, Systems, Models High-Throughput Computing More on Distributed Computing Grid Computing Cloud Computing Summary and Q&As
4. HPC ->max(FLOPS) -> Parallel Computing Speed: The problem takes too much time Size: The problem doesn’t fit on my machine The Nature of the Problem is CPU Intensive (CFD, Weather Forecast, Bio Informatics, Signal Processing, …) Cost: Can’t afford the real experiment Risk: The real problem is too dangerous Image source: http://www.symscape.com/node/261
5. !Give me a stronger computer Fact #1: Until 2003 Stronger == Faster by Freq. Since 2003 Stronger == Parallel Fact #2: All present and future processors are and will be Parallel Fact #3: CPU intensive computer codes won’t perform well on future architectures using the traditional “Sequential” programming style Fact #4: The Challenge is in the Software
6. The Free lunch is over Herb Sutter, C++ Architect at Microsoft (March 2005) http://www.gotw.ca/publications/concurrency-ddj.htm
7. Modern High-End Parallel Computers Commodities (Intel+AMD ≈ 100% market share) Open Source (Unix/Linux ≈ 100% market share) High Speed Interconnect (Infiniband ) Mostly running MPI (Distributed Memory) and OpenMP (Shared Memory) A Growing trend: GPGPUs “Many-Many” cores: Multi-Threading
9. Front view of Dawning TC3600 Blade Server. June 2010 Top 3 224,162 cores
10. GPGPU (a demo on my laptop) Source: Fast N-Body Simulation with CUDA. ByLars NylandNVIDIA Corporation, Mark Harris NVIDIA Corporation, Jan Prins University of North Carolina at Chapel Hill.
11. High-Performance Computing (HPC) Trends, Architecture, Systems, Models High-Throughput Computing (HTC) More on Distributed Computing Grid Computing Cloud Computing Summary and Q&As
13. High-Performance Computing (HPC) Trends, Architecture, Systems, Models High-Throughput Computing (HTC) More on Distributed Computing Grid Computing Cloud Computing Summary and Q&As
14. Grid Computing Definition According to Ian Foster* Coordinates resources that are not subject to centralized control Using standard, open, general-purpose protocols and interfaces Delivers nontrivial qualities of service (QoS) * Source: “What is the Grid? A Three Point Checklist” by Ian Foster, Argonne National Laboratory & University of Chicago, July 20, 2002
16. The Production Service infrastructure is a large multi-science Grid infrastructure, federating some 250 resource centers world-wide, providing some 40.000 CPUs and several Petabytes of storage. This infrastructure is used on a daily basis by several thousands of scientists federated in over 200 Virtual Organizations on a daily basis.
17. High-Performance Computing (HPC) Trends, Architecture, Systems, Models High-Throughput Computing (HTC) More on Distributed Computing Grid Computing Cloud Computing Summary and Q&As
19. X as a Service (Xaas) Where X can be any Computing resource: Platform, Software, Infrastructure… A major revolution in the IT Virtualization & Outsourcing Pay Per Use (PPU) However, many challenges unsolved yet QoS Security Legal Issues
22. High-Performance Computing (HPC) Trends, Architecture, Systems, Models High-Throughput Computing (HTC) More on Distributed Computing Grid Computing Cloud Computing Summary and Q&As
23. Summary and Outlook Tera-FLOPs processor by 2015 How about an Israeli Supercomputer? SMP Exa-FLOPs Supercomputer by 2019 HPC Grid Computing Clusters HTC 8.5 cent/hour CPU Open Source Software