XSEDE OpenACC workshop enables Blue Waters Researchers to Accelerate Key Algorithms
Article No.: 28, Pages 1 - 6
Abstract
The Blue Waters system at the National Center for Supercomputing Applications (NCSA) is the largest GPU accelerated system in the NSF's portfolio with greater than (>) 4200 Nvidia K20x accelerators and greater than (>) 22500 compute nodes overall. Using the accelerator nodes effectively is paramount to the system's success as they represent approximately 1/7 of system peak performance. As an XSEDE level 2 service provider, the system is also available to education allocations proposed by XSEDE educators and trainers. The training staff working at Pittsburgh Supercomputing Center (PSC) along with their XSEDE and Nvidia partners have offered multiple OpenACC workshops since 2012. The most recent workshop was conducted on Blue Waters hosting the hands-on sessions and it was very successful. As a direct result of working with PSC on these workshop, NCSA researchers have been able to obtain significant speedups on real-world algorithms using OpenACC in the Cray environment. In this work we will look at two key kernel codes (3D FFT kernel, Laplace 2D MPI benchmark) and the path to obtaining the observed performance gains.
References
[1]
OpenACC, The OpenACCTM Application Programming Interface Version 1.0, Nov 2011.
[2]
NVIDIA, NVIDIA CUDA Programming Guide 2.0, 2008.
[3]
Gropp W., Lusk E., and Skjellum A.: Using MPI: Portable Parallel Programming with the Message Passing Interface, 2nd edition. Cambridge, MA: MIT Press, 1999.
[4]
OpenMP ARB, "OpenMP Application Program Interface V3.0," May 2008.
[5]
Hoshino T., Maruyama N., Matsuoka S., and, Takak R. CUDA vs OpenACC: Performance Case Studies with Kernel Benchmarks and a Memory-Bound CFD Application 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, 2013
[6]
Phillips J., Stone J. Probing bimolecular machines with graphics processor Communications of the ACM, v52(10), 34--41, 2009
[7]
Pennycook, S., J.; Hammond, S., D.; Jarvis, S., A.; Mudalige, G., R. Performance analysis of a hybrid MPI/CUDA implementation of the NASLU benchmark, ACM SIGMETRICS Performance Evaluation Review, March 2011, Vol.38(4), pp.23--29
[8]
Blue Waters. Sustained Petascale Computing, NCSA, University of Illinois; 2014
[9]
Quinn M. J., Parallel programming in C with MPI and OpenMP, McGraw-Hill, 2004.
[10]
NVIDIA, 12 Tips for Maximum Performance with PGI Directives in C; http://www.nvidia.com/docs/IO/117377/directives-tips-for-c.pdf
[11]
Canning A., Wang L.W., Williamson A. and Zunger A., Parallel empirical pseudopotential electronic structure calculations for million atom systems. J. of Comput. Phys. 160, 29 (2000).
[12]
Canning A., Shalf J., Wassermann H. and Gajbe M., A Comparison of Different Communication Structures for Scalable Parallel Three Dimensional FFTs in First Principles Codes. Parallel Computing: From Multicores and GPUs to Petascale, IOS Press, B. Chapman (Eds.) (2010).
[13]
Canning A., Shalf J., Wright N. J., Anderson S., Gajbe M., A Hybrid MPI/OpenMP 3d FFT for Plane Wave First-principles Materials Science Codes. The 9th International Conference on Scientific Computing (CSC'12: July 16-19, 2012, Las Vegas, USA)
[14]
Gajbe M., Canning A., Wang L.W., Shalf J., Wassermann H., Vuduc R., Auto-Tuning Distributed-Memory 3-Dimensional Fast Fourier Transforms on the Cray XT4. Cray User Group Meeting 2009, Atlanta, USA
[15]
Gajbe M., Performance Modelling and Optimization of 3 Dimensional Fast Fourier Transform. IPDPS TCPP PhD Forum, Rome Italy, 2009
Index Terms
- XSEDE OpenACC workshop enables Blue Waters Researchers to Accelerate Key Algorithms
Recommendations
Hybridizing S3D into an exascale application using OpenACC: an approach for moving to multi-petaflops and beyond
SC '12: Proceedings of the International Conference on High Performance Computing, Networking, Storage and AnalysisHybridization is the process of converting an application with a single level of parallelism to an application with multiple levels of parallelism. Over the past 15 years a majority of the applications that run on High Performance Computing systems have ...
Hybridizing S3D into an Exascale application using OpenACC: An approach for moving to multi-petaflops and beyond
SC '12: Proceedings of the 2012 International Conference for High Performance Computing, Networking, Storage and AnalysisHybridization is the process of converting an application with a single level of parallelism to an application with multiple levels of parallelism. Over the past 15 years a majority of the applications that run on High Performance Computing systems have ...
Benchmarking OpenCL, OpenACC, OpenMP, and CUDA: Programming Productivity, Performance, and Energy Consumption
ARMS-CC '17: Proceedings of the 2017 Workshop on Adaptive Resource Management and Scheduling for Cloud ComputingMany modern parallel computing systems are heterogeneous at their node level. Such nodes may comprise general purpose CPUs and accelerators (such as, GPU, or Intel Xeon Phi) that provide high performance with suitable energy-consumption characteristics. ...
Comments
Information & Contributors
Information
Published In
July 2014
445 pages
Copyright © 2014 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- NSF: National Science Foundation
- Drexel University
- Indiana University: Indiana University
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 July 2014
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
XSEDE '14
XSEDE '14: Annual Conference of the Extreme Science and Engineering Discovery Environment
July 13 - 18, 2014
GA, Atlanta, USA
Acceptance Rates
XSEDE '14 Paper Acceptance Rate 80 of 120 submissions, 67%;
Overall Acceptance Rate 129 of 190 submissions, 68%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 66Total Downloads
- Downloads (Last 12 months)1
- Downloads (Last 6 weeks)0
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in