HPC Programming Framework Research Team

We develop high performance, highly productive software stacks that aim to simplify development of highly optimized, fault-tolerant computational science applications on current and future supercomputers, notably the K computer. Our current focus of work includes large-scale data processing, heterogeneous computing, and fault tolerance. A major ongoing project in our group will deliver a MapReduce runtime that is highly optimized for the intra- and inter-node architectures of the K computer as well as its peta-scale hierarchical storage systems. Another major project focuses on performance and productivity in large-scale heterogeneous systems. See the team website for more details.

Research Subjects

• Scalable software stack for large-scale data-intensive applications
• High performance, highly productive application frameworks for post-petascale supercomputers
• Fault tolerance for large-scale supercomputers

Publications

1. Kento Sato, Naoya Maruyama, Kathryn Mohror, Adam Moody, Todd Gamblin, Bronis R. de Supinski, Satoshi Matsuoka:
   "Design and Modeling of a Non-Blocking Checkpointing System"
   Proceedings of the 2012 ACM/IEEE conference on Supercomputing (SC'12)
2. Naoya Maruyama, Tatsuo Nomura, Kento Sato, Satoshi Matsuoka:
   "Physis: An Implicitly Parallel Programming Model for Stencil Computations on Large-Scale GPU-Accelerated Supercomputers"
   Proceedings of the 2011 ACM/IEEE conference on Supercomputing (SC'11)
3. Leonardo Arturo Bautista Gomez, Dimitri Komatitsch, Naoya Maruyama, Seiji Tsuboi, Franck Cappello, Satoshi Matsuoka, and Takeshi Nakamura:
   "FTI: High Performance Fault Tolerance Interface for Hybrid Systems"
   Proceedings of the 2011 ACM/IEEE conference on Supercomputing (SC'11)
4. Takashi Shimokawabe, Takayuki Aoki, Tomohiro Takaki, Akinori Yamanaka, Akira Nukada, Toshio Endo, Naoya Maruyama, Satoshi Matsuoka:
   "Peta-scale Phase-Field Simulation for Dendritic Solidification on the TSUBAME 2.0 Supercomputer"
   Proceedings of the 2011 ACM/IEEE conference on Supercomputing (SC'11)
5. Naoya Maruyama, Satoshi Matsuoka:
   "Model-based Fault Localization: Finding Behavioral Outliers in Large-scale Computing Systems"
   New Generation Computing
6. Naoya Maruyama, Akira Nukada, Satoshi Matsuoka:
   "A High-Performance Fault-Tolerant Software Framework for Memory on Commodity GPUs"
   Proceedings of the 24th IEEE International Parallel and Distributed Processing Symposium (IPDPS'10)
7. Hitoshi Nagasaka, Naoya Maruyama, Akira Nukada, Toshio Endo, and Satoshi Matsuoka
   "Statistical power modeling of GPU kernels using performance counters"
   Proceedings of International Green Computing Conference (IGCC '10)
8. Alexander V. Mirgorodskiy, Naoya Maruyama, Barton P. Miller:
   "Problem Diagnosis in Large-Scale Computing Environments"
   Proceedings of the 2006 ACM/IEEE conference on Supercomputing (SC'06)