250 likes | 412 Views
Javier Delgado Gabriel Gazolla Constantinos Menelaou Lixi Wang Mark Joselli. GPU Performance Prediction. Outline. Motivation Role in Energy Efficiency Performance Modeling GPU programming for Weather Modeling GPU Programming for BLAST Model Testing Conclusion. Benefits.
E N D
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Javier Delgado Gabriel Gazolla Constantinos Menelaou Lixi Wang Mark Joselli GPU Performance Prediction
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Outline • Motivation • Role in Energy Efficiency • Performance Modeling • GPU programming for Weather Modeling • GPU Programming for BLAST • Model Testing • Conclusion
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Benefits • Improves weather simulation software • Maximize resource utilization • Achieve maximum scalability • Maximize resource utilization • Leveraging cross-disciplinary and same-discipline differences in expertise • WRF, GPU, Performance Modeling, Fortran
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. GPU Performance Improvement Over Time Source: nVidia.com
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Sample Speedups Source: nVidia.com
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Outline • Motivation • Role in Energy Efficiency • Performance Modeling • GPU programming for Weather Modeling • GPU Programming for BLAST • Model Testing • Conclusion
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Role in Energy Efficiency • Idle GPU = wasted energy • Maximally-loaded GPU = a lot of power consumption • For example • Nvidia 8800 GTX consumes 137W @ max load • Intel Xeon LS5400 consumes 50W @ max load Source: http://mark.zoomcities.com/images/gfx/GFXpowerchartby3d.png (which is derived from data from http://www.xbitlabs.com)
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Power Consumption http://www.xbitlabs.com/articles/video/display/gf8800gts320MB-roundup_8.html#sect0 http://www.xbitlabs.com/articles/video/display/xfx-gf-gtx285-gtx295_16.html
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. GPU Role in Energy Efficiency • But... More bang for your power-consumption buck Source: John Michalakes and Manish Vachharajani
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. • And ...
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Outline • Motivation • Role in Energy Efficiency • Hurricane Mitigation Overview • Performance Modeling • GPU Programming for BLAST • Model Testing • Conclusion
Motivation • Alarming Statistics • 40% of (small-medium sized) companies shut down within 36 months, if forced closed for 3 or more days after a hurricane • Local communities lose jobs and hundreds of millions of dollars to their economy • If 5% of businesses in South Florida recover one week earlier, then we can prevent $219,300,000 in non-property economic losses • Hurricanes cost coastal regions financial and personal damage • Damage can be mitigated, but • Impact area prediction is inaccurate • Simulation using commodity computers is not precise Hurricane Andrew, Florida 1992 Ike, Cuba 2008 Katrina, New Orleans 2005
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Outline • Motivation • Role in Energy Efficiency • Hurricane Mitigation Overview • Performance Modeling • GPU Programming for BLAST • Model Testing • Conclusion
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Motivation for application profiling and performance prediction • Optimal usage of grid resources through “smarter” meta-scheduling • Many users overestimate job requirements • Reduced idle time for compute resources • Save utility and energy costs • Optimal resource selection for most expedient job return time
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Process
Typical Results on Large Clusters • Input: Marenostrum • 8, 16, and 32 nodes • 1 process per node • Output: Marenostrum • 8, 16, 32, 64, 96, and 128 nodes
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Future Modeling Plans • Model execution time with different GPU configurations • Current GPU project objective: learn how to model GPU performance by porting WRF kernels to CUDA • Test with different cards • Test with different processor configurations • Test with different number of nodes
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Overview of GPU Benchmarking Project Learn WRF Understand Source code of existing CUDA-ported code Learn CUDA Learn CUDA Understand old source code (Fortran) Learn Fortran Learn WRF Port another module Benchmark
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Status • Code has been compiled and executed • Regions of similarity are being identified • Fortran Program: 1729 lines • CUDA (C) Program: 1329 lines (incl init) • Currently figuring out necessary code logic of existing ported kernel • Preliminary documentation/report of findings
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Outline • Motivation • Role in Energy Efficiency • Hurricane Mitigation Overview • Performance Modeling • GPU Programming for BLAST • Model Testing • Conclusion
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Purpose • BLAST used extensively for sequence analysis • Provides a different kind of application for testing GPU performance improvements • Further improve our GPU programming and performance modeling knowledge
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Status • Literature review concerning other sequence analysis work with GPU • Learning how BLAST works
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Long-running, Fault-tolerant Weather Prediction • Slight inaccuracies in initial conditions of domain can cause significant inaccuracies later • Third component of this project: account for this using perturbation analysis • The effects of perturbation on runtime must also be modeled
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Conclusion • GPU’s promise much faster job execution for different applications • In order to maximize resource utilization, application execution time should be predictable • Especially for time-critical applications that take long to execute
GreenLight Education & Outreach Summer Workshop UCSD. La Jolla, California. July 1 – 2, 2009. Thank You • Questions?