Title | ||
---|---|---|
Application of a Preconditioned Chebyshev Basis Communication-Avoiding Conjugate Gradient Method to a Multiphase Thermal-Hydraulic CFD Code. |
Abstract | ||
---|---|---|
A preconditioned Chebyshev basis communication-avoiding conjugate gradient method (P-CBCG) is applied to the pressure Poisson equation in a multiphase thermal-hydraulic CFD code JUPITER, and its computational performance and convergence properties are compared against a preconditioned conjugate gradient (P-CG) method and a preconditioned communication-avoiding conjugate gradient (P-CACG) method on the Oakforest-PACS, which consists of 8,208 KNLs. The P-CBCG method reduces the number of collective communications with keeping the robustness of convergence properties. Compared with the P-CACG method, an order of magnitude larger communication-avoiding steps are enabled by the improved robustness. It is shown that the PCBCG method is 1.38x and 1.17x faster than the P-CG and P-CACG methods at 2,000 processors, respectively. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-319-69953-0_15 | Lecture Notes in Computer Science |
DocType | Volume | ISSN |
Conference | 10776 | 0302-9743 |
Citations | PageRank | References |
1 | 0.40 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yasuhiro Idomura | 1 | 57 | 14.27 |
Takuya Ina | 2 | 3 | 2.88 |
Akie Mayumi | 3 | 3 | 1.52 |
Susumu Yamada | 4 | 36 | 9.54 |
Toshiyuki Imamura | 5 | 95 | 22.21 |