windowshpcoverview.pptx

Phil Pennington
Windows HPC
Microsoft Corporation
High Performance and puting with Windows HPC
puting Reached the Petaflop
IBM RoadRunner atLos Alamos National Lab
HPC at Microsoft
2004 Windows HPC team established
2005 Windows Server 2003 SP1 x64
2005 Microsoft launches HPC entry at SC‘05 in Seattle with Bill Gates keynote
2006 pute Cluster Server 2003 ships
2007 Microsoft named one of the Top panies to watch in HPC at SC’07
2008 Windows HPC Server 2008
Spring 2008, NCSA, #23
9472 cores, TF, %
Fall 2007, Microsoft, #1162048 cores, TF, %
Spring 2007, Microsoft, #1062048 cores, 9 TF, %
Spring 2006, NCSA, #130
896 cores, TF
Spring 2008, Umea, #40
5376 cores, 46 TF, %
30% efficiencyimprovement
Windows HPC Server 2008
pute Cluster 2003
Winter 2005, Microsoft
4 procs, GFlops
Spring 2008, Aachen, #100
2096 cores, TF, %
HPC Clusters in Every Lab
X64 Server
Explosion of Data
Experiments
Archives
Literature
Simulations
Petabytes
Doubling every
2 years
The Data Pipeline
Data Gathering
Discovery and Browsing
Science Exploration
Domain specific analyses
Scientific Output
“Raw” data includes sensor output, data downloaded from agency or collaboration web sites, papers (especially for ancillary data
“Raw” data browsing for discovery (do I have enough data in the right places?), cleaning (does the data look obviously wrong?), and light weight science via browsing
“Science variables” and data summaries for early science exploration and hypothesis testing. Similar to discovery and browsing, but with science puted via gap filling, units conversions, or simple equation.
“Science variables” combined with models, other specialized code, or statistics for deep science understanding.
Scientific results via packages such as MatLab or R2. Special rendering package such as ArcGIS.
Paper preparation.
Courtesy Catherine van Ingen, MSR
New Breed of HPC: Computational Finance
Modern finance differentiates by