Programming Environment Research Team

In order to exploit the full potential of the large-scale parallel K computer to carry out advanced computational science, we need parallel programming to coordinate the computer's multiple processors. The Programming Environment Research Team conducts research on parallel programming models and languages for large-scale parallel systems and also on programming tools for performance analysis and tuning. The technologies of programming models, languages and environment play an important role in bridging programmers and systems. Our team will develop practical parallel programming languages and performance tools that will increase the productivity of parallel programming. In addition, we also will explore programming technologies related to next-generation exa-scale computing.

Research Subjects

• Parallel Programming Language
• Parallel Program Tuning tools
• Parallel Performance Analysis
• Parallel Programming Environment

Publications

1. T. Abe, T. Maeda, and M. Sato:
   "Model checking with user-definable abstraction for partitioned global address space languages"
   Proceedings of the 6th Conference on Partitioned Global Address Space Programming Models (PGAS), Online. Santa Barbara, October 2012
2. T. Abe and M. Sato:
   "On-the-fly synchronization checking for interactive programming in XcalableMP."
   Proceedings of the 5th International Workshop on Parallel Programming Models and Systems Software for High-End Computing (P2S2), pages 29--37. Pittsburgh, September 2012
3. T. Abe and M. Sato:
   "Auto-tuning of numerical programs by block multi-color ordering code generation and job-level parallel execution"
   Proceedings of the 7th International Workshop on Automatic Performance Tuning (iWAPT). Kobe, July 2012
4. Swann Perarnau and Mitsuhisa Sato:
   "Discovering Cache Partitioning Optimizations for the K Computer"
   Proceedings of 2nd Asia-Pacific Programming Languages and Compilers Workshop
5. Masahiro Nakao, Hitoshi Murai Takenori Shimosaka Mitsuhisa Sato:
   "XcalableMP for Productivity and Performance"
   2012 HPC Challenge Award Competition Class 2, Salt Lake City, Utah, USA, Nov., 2012