ppOpen-HPC: open source infrastructure for development and execution of large-scale scientific applications on post-peta-scale supercomputers with automatic tuning (AT)

We propose an open source infrastructure for development and execution of optimized and reliable simulation codes on post-peta-scale (pp) parallel computers with heterogeneous computing nodes which consist of multicore CPU's and accelerators., named "ppOpen-HPC". ppOpen-HPC consists of various types of libraries, which covers various types of procedures for scientific computations. Source code developed on a PC with a single processor is linked with these libraries, and generated parallel code is optimized for post-peta-scale system. Capability of automatic tuning is important and critical technology for further development on new architectures and maintenance of the framework.

[1]  Kengo Nakajima.  Automatic Tuning of Parallel Multigrid Solvers Using OpenMP/MPI Hybrid Parallel Programming Models , 2012, VECPAR.

[2]  Takahiro Inoue,et al.  Performance Evaluation and Case Study of a Coupling Software ppOpen-MATH/MP , 2014, ICCS.

[3]  Takahiro Katagiri,et al.  Implementation and Evaluation of an AMR Framework for FDM Applications , 2014, ICCS.

[4]  Kengo Nakajima.  New strategy for coarse grid solvers in parallel multigrid methods using OpenMP/MPI hybrid programming models , 2012, PMAM '12.

[5]  Masaharu Matsumoto,et al.  Performance Optimization of the 3D FDM Simulation of Seismic Wave Propagation on the Intel Xeon Phi Coprocessor Using the ppOpen-APPL/FDM Library , 2014, VECPAR.

[6]  Takahiro Katagiri,et al.  Auto-tuning of Computation Kernels from an FDM Code with ppOpen-AT , 2014, 2014 IEEE 8th International Symposium on Embedded Multicore/Manycore SoCs.

[7]  Takahiro Katagiri,et al.  FIBER: A Generalized Framework for Auto-tuning Software , 2003, ISHPC.

[8]  Kengo Nakajima.  Optimization of serial and parallel communications for parallel geometric multigrid method , 2014, 2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS).

[9]  Mitsuhisa Sato,et al.  Grid-Oriented Process Clustering System for Partial Message Logging , 2014, 2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks.

[10]  Takemasa Miyoshi,et al.  The Non-hydrostatic Icosahedral Atmospheric Model: description and development , 2014, Progress in Earth and Planetary Science.

[11]  Daisuke Nishiura,et al.  ppohDEM: Computational performance for open source code of the discrete element method , 2014, Comput. Phys. Commun..

[12]  Arutyun Avetisyan,et al.  Automatically Tuning Sparse Matrix-Vector Multiplication for GPU Architectures , 2010, HiPEAC.

[13]  Philip W. Jones.  First- and Second-Order Conservative Remapping Schemes for Grids in Spherical Coordinates , 1999 .

[14]  Yasuhito Takahashi,et al.  Parallel Hierarchical Matrices with Adaptive Cross Approximation on Symmetric Multiprocessing Clusters , 2014, J. Inf. Process..