検索対象:     
報告書番号:
※ 半角英数字
 年 ~ 
 年

Xeon Phiによる共有メモリ型計算手法の数理モデルを含む船舶周り流れへの適用

Numerical study on applicability of the shared memory type computing with the Xeon Phi processor for flows around a ship including physical models

大橋 訓英*; 小野寺 直幸   

Ohashi, Kunihide*; Onodera, Naoyuki

海上技術安全研究所で開発している船舶抵抗解析のCFDコードに対して、メニーコア型のプロセッサであるIntel Xeon Phi Knights Landingに対してのポーティングおよび性能測定を実施した。2方程式モデルのRANSコードに対して重合格子を適用した計算体系の解析では、Intel Xeon Phiを利用することでコア数に応じて、スレッド並列性能が増加していくことを確認した。

The applicability of shared memory type computing with Xeon Phi Knights Landing processor is examined with the flow solver which is dedicated to the flow computation around a ship hull. The computations at the high Reynolds number with the one- or two-equation turbulence models and the free surface model, additionally, the over-set grid method are selected as the test cases. The processing speeds of the Xeon Broadwell and the Skylake processors show better results than the speed of the Xeon Phi processors. The speed up ratio is smoothly increasing until the maximum number of the core with using the Xeon Phi processor.

Access

:

- Accesses

InCites™

:

Altmetrics

:

[CLARIVATE ANALYTICS], [WEB OF SCIENCE], [HIGHLY CITED PAPER & CUP LOGO] and [HOT PAPER & FIRE LOGO] are trademarks of Clarivate Analytics, and/or its affiliated company or companies, and used herein by permission and/or license.