Strategies for Energy-Efficient Resource Management of Hybrid Programming Models

Journal Article · 01 January 2013 · IEEE Transactions on Parallel and Distributed Systems

DOI:https://doi.org/10.1109/tpds.2012.95· OSTI ID:1734607

Li, Dong ^[1]; de Supinski, Bronis R. ^[2]; Schulz, Martin ^[2]; Nikolopoulos, Dimitrios S. ^[3]; Cameron, Kirk W. ^[4]

---

1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)
2. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
3. Queen's Univ. Belfast, Ireland (United Kingdom); Foundation for Research and Technology Hellas FORTH, Crete (Greece)
4. Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)

Many scientific applications are programmed using hybrid programming models that use both message passing and shared memory, due to the increasing prevalence of large-scale systems with multicore, multisocket nodes. Previous work has shown that energy efficiency can be improved using software-controlled execution schemes that consider both the programming model and the power-aware execution capabilities of the system. However, such approaches have focused on identifying optimal resource utilization for one programming model, either shared memory or message passing, in isolation. The potential solution space, thus the challenge, increases substantially when optimizing hybrid models since the possible resource configurations increase exponentially. Nonetheless, with the accelerating adoption of hybrid programming models, we increasingly need improved energy efficiency in hybrid parallel applications on large-scale systems. In this work, we present new software-controlled execution schemes that consider the effects of dynamic concurrency throttling (DCT) and dynamic voltage and frequency scaling (DVFS) in the context of hybrid programming models. Specifically, we present predictive models and novel algorithms based on statistical analysis that anticipate application power and time requirements under different concurrency and frequency configurations. Furthermore, we apply our models and methods to the NPB MZ benchmarks and selected applications from the ASC Sequoia codes. Overall, we achieve substantial energy savings (8.74 percent on average and up to 13.8 percent) with some performance gain (up to 7.5 percent) or negligible performance loss.

• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
• Sponsoring Organization: European Commission; National Science Foundation (NSF); USDOE National Nuclear Security Administration (NNSA)
• Grant/Contract Number: AC52-07NA27344
• OSTI ID: 1734607
• Alternate ID(s): OSTI ID: 1048160
• Report Number(s): LLNL-JRNL--521391; 551350
• Journal Information: IEEE Transactions on Parallel and Distributed Systems, Journal Name: IEEE Transactions on Parallel and Distributed Systems Journal Issue: 1 Vol. 24; ISSN 1045-9219
• Publisher: IEEE
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
Power management
dynamic concurrency throttling
dynamic voltage and frequency scaling
hybrid parallel programming models