Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Idomura, Yasuhiro; Ina, Takuya*; Mayumi, Akie; Yamada, Susumu; Matsumoto, Kazuya*; Asahi, Yuichi*; Imamura, Toshiyuki*
Proceedings of 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA 2017), p.7_1 - 7_8, 2017/11
A communication-avoiding generalized minimal residual (CA-GMRES) method is applied to the gyrokinetic toroidal five dimensional Eulerian code GT5D, and its performance is compared against the original code with a generalized conjugate residual (GCR) method on the JAEA ICEX (Haswell), the Plasma Simulator (FX100), and the Oakforest-PACS (KNL). The CA-GMRES method has higher arithmetic intensity than the GCR method, and thus, is suitable for future Exa-scale architectures with limited memory and network bandwidths. In the performance evaluation, it is shown that compared with the GCR solver, its computing kernels are accelerated by , and the cost of data reduction communication is reduced from to of the total cost at 1,280 nodes.
Idomura, Yasuhiro
no journal, ,
In performing extreme scale CFD simulations on many core platforms with low power consumption such as Oakforest-PACS, we need new computing technologies for accelerating computation on many core processors, and avoiding communications and data I/O, which become bottlenecks with accelerated computation. In order to resolve these issues, we have developed many core optimization techniques, communication latency hiding techniques, communication avoiding algorithms, and In-Situ visualization systems on Oakforest-PACS. In this talk, we present applications of these techniques to five dimensional plasma CFD codes and three dimensional multi-phase thermal hydraulic CFD codes.
Matsumoto, Kazuya*; Idomura, Yasuhiro; Ina, Takuya*; Mayumi, Akie; Yamada, Susumu
no journal, ,
Communication avoiding (CA) Krylov methods are promising solutions for communication bottlenecks on supercomputers based on many core processors or accelerators. In this work, we implemented the CA-GMRES method on a GPU cluster, the HA-PACS, and evaluated its performance on a non-symmetric matrix solver from a nuclear CFD code. The result shows that the CA-GMRES method is significantly faster than the conventional Krylov methods such as the GMRES method and the GCR method.