Evaluating adaptive and predictive power management strategies for optimizing visualization performance on supercomputers

Brink, Stephanie; Larsen, Matthew; Childs, Hank; Rountree, Barry

doi:10.1016/j.parco.2021.102782

Title: Evaluating adaptive and predictive power management strategies for optimizing visualization performance on supercomputers

Journal Article · Thu Apr 15 00:00:00 EDT 2021 · Parallel Computing

DOI:https://doi.org/10.1016/j.parco.2021.102782· OSTI ID:1834504

^[1]; Larsen, Matthew ^[1];

^[2]; Rountree, Barry ^[1]

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Univ. of Oregon, Eugene, OR (United States)

Power is becoming an increasingly scarce resource on the next generation of supercomputers, and should be used wisely to improve overall performance. One strategy for improving power usage is hardware overprovisioning, i.e., systems with more nodes than can be run at full power simultaneously without exceeding the system-wide power limit. With this study, we compare two strategies for allocating power throughout an overprovisioned system – adaptation and prediction – in the context of visualization workloads. While adaptation has been suitable for workloads with more regular execution behaviors, it may not be as suitable on visualization workloads, since they can have variable execution behaviors. This study considers a total of 104 experiments, which vary the rendering workload, power budget, allocation strategy, and node concurrency, including tests processing data sets up to 1 billion cells and using up to 18,432 cores across 512 nodes. Overall, we find that prediction is a superior strategy for this use case, improving performance up to 27% compared to an adaptive strategy.

View Accepted Manuscript (DOE)

View Accepted Manuscript (Publisher)

Cite

Export

Save

Research Organization:: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC52-07NA27344; LLNL-JRNL-782698

OSTI ID:: 1834504

Alternate ID(s):: OSTI ID: 1894380

Report Number(s):: LLNL-JRNL-782698; 977642

Journal Information:: Parallel Computing, Vol. 104-105; ISSN 0167-8191

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (15)

Priority research directions for in situ data management: Enabling scientific discovery from diverse data sources Peterka, Tom; Bard, Deborah; Bennett, Janine C. The International Journal of High Performance Computing Applications, Vol. 34, Issue 4 https://doi.org/10.1177/1094342020913628	journal	March 2020
Power Tuning HPC Jobs on Power-Constrained Systems Gholkar, Neha; Mueller, Frank; Rountree, Barry PACT '16: International Conference on Parallel Architectures and Compilation, Proceedings of the 2016 International Conference on Parallel Architectures and Compilation https://doi.org/10.1145/2967938.2967961	conference	September 2016
Just-in-time dynamic voltage scaling: Exploiting inter-node slack to save energy in MPI programs Freeh, Vincent W.; Kappiah, Nandini; Lowenthal, David K. Journal of Parallel and Distributed Computing, Vol. 68, Issue 9 https://doi.org/10.1016/j.jpdc.2008.04.007	journal	September 2008
On the Greenness of In-Situ and Post-Processing Visualization Pipelines Adhinarayanan, Vignesh; Feng, Wu-Chun; Woodring, Jonathan 2015 IEEE International Parallel and Distributed Processing Symposium Workshop (IPDPSW) https://doi.org/10.1109/IPDPSW.2015.132	conference	May 2015
Evaluation of In-Situ Analysis Strategies at Scale for Power Efficiency and Scalability Rodero, Ivan; Parashar, Manish; Landge, Aaditya G. 2016 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) https://doi.org/10.1109/CCGrid.2016.95	conference	May 2016
VTK-m: Accelerating the Visualization Toolkit for Massively Threaded Architectures Moreland, Kenneth; Sewell, Christopher; Usher, William IEEE Computer Graphics and Applications, Vol. 36, Issue 3 https://doi.org/10.1109/MCG.2016.48	journal	May 2016
Trapped Capacity: Scheduling under a Power Cap to Maximize Machine-Room Throughput Zhang, Ziming; Lang, Michael; Pakin, Scott 2014 Energy Efficient Supercomputing Workshop (E2SC) https://doi.org/10.1109/E2SC.2014.10	conference	November 2014
Cinema image-based in situ analysis and visualization of MPAS-ocean simulations O’Leary, Patrick; Ahrens, James; Jourdain, Sébastien Parallel Computing, Vol. 55 https://doi.org/10.1016/j.parco.2015.10.005	journal	July 2016
Energy-Aware Framework for Virtual Machine Consolidation in Cloud Computing Cao, Zhibo; Dong, Shoubin 2013 IEEE International Conference on High Performance Computing and Communications (HPCC) & 2013 IEEE International Conference on Embedded and Ubiquitous Computing (EUC), 2013 IEEE 10th International Conference on High Performance Computing and Communications & 2013 IEEE International Conference on Embedded and Ubiquitous Computing https://doi.org/10.1109/HPCC.and.EUC.2013.271	conference	November 2013
Dynamic power sharing for higher job throughput Ellsworth, Daniel A.; Malony, Allen D.; Rountree, Barry SC15: The International Conference for High Performance Computing, Networking, Storage and Analysis, Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1145/2807591.2807643	conference	November 2015
CPU MISER: A Performance-Directed, Run-Time System for Power-Aware Clusters Ge, Rong; Feng, Xizhou; Feng, Wu-chun 2007 International Conference on Parallel Processing (ICPP 2007) https://doi.org/10.1109/ICPP.2007.29	conference	September 2007
Exploring tradeoffs between power and performance for a scientific visualization algorithm Labasan, Stephanie; Larsen, Matthew; Childs, Hank 2015 IEEE 5th Symposium on Large Data Analysis and Visualization (LDAV) https://doi.org/10.1109/LDAV.2015.7348074	conference	October 2015
In Situ Visualization for Computational Science Childs, Hank; Bennett, Janine; Garth, Christoph IEEE Computer Graphics and Applications, Vol. 39, Issue 6 https://doi.org/10.1109/MCG.2019.2936674	journal	November 2019
In Situ Methods, Infrastructures, and Applications on High Performance Computing Platforms Bauer, A. C.; Abbasi, H.; Ahrens, J. Computer Graphics Forum, Vol. 35, Issue 3 https://doi.org/10.1111/cgf.12930	journal	June 2016
Performance Modeling of In Situ Rendering Larsen, Matthew; Harrison, Cyrus; Kress, James SC16: International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1109/SC.2016.23	conference	November 2016

Similar Records

A visual analytics system for optimizing the performance of large-scale networks in supercomputing systems

Conference · Thu Mar 01 00:00:00 EST 2018 · OSTI ID:1834504

Fujiwara, Takanori; Li, Jianping Kelvin; Mubarak, Misbah; +4 more

Communication Characterization and Optimization of Applications Using Topology-Aware Task Mapping on Large Supercomputers

Conference · Fri Jan 01 00:00:00 EST 2016 · OSTI ID:1834504

Sreepathi, Sarat; D'Azevedo, Ed; Philip, Bobby; +1 more

Communication Characterization and Optimization of Applications Using Topology-Aware Task Mapping on Large Supercomputers

Conference · Fri Jan 01 00:00:00 EST 2016 · OSTI ID:1834504

Sreepathi, Sarat; D'Azevedo, Eduardo; Philip, Bobby; +1 more

Related Subjects

97 MATHEMATICS AND COMPUTING
computer science
high performance computing
parallel systems
power management
scientific visualization
power-constrained computing
runtime systems

Title: Evaluating adaptive and predictive power management strategies for optimizing visualization performance on supercomputers

Citation Formats

References (15)

Similar Records

Related Subjects