GAMER with out-of-core computation

被引：1

作者：

Schive, Hsi-Yu ^{[1
]}

Tsai, Yu-Chih ^{[1
]}

Chiueh, Tzihong ^{[1
]}

机构：

[1] Natl Taiwan Univ, Dept Phys, Taipei 106, Taiwan

来源：

COMPUTATIONAL STAR FORMATION | 2011年 / 270期

关键词：

gravitation; hydrodynamics; methods: numerical; ASTROPHYSICS;

D O I：

10.1017/S1743921311000718

中图分类号：

P1 [天文学];

学科分类号：

0704 ;

摘要：

GAMER is a, CPU-accelerated Adaptive-MEsh-Refinement code for astrophysical simulations. In this work, two further extensions of the code are reported. First, we have implemented the MUSCL-Hancock method with the Roe's Riemann solver for the hydrodynamic evolution, by which the accuracy, overall performance and the CPU versus CPU speed-up factor a,re improved. Second, we have implemented the out-of-core computation, which utilizes the large storage space of multiple hard disks as the additional run-time virtual memory and permits an extremely large problem to be solved in a relatively small-size GPU cluster. The communication overhead associated with the data transfer between the parallel hard disks and the main memory is carefully reduced by overlapping it with the CPU/GPU computations.

引用

页码：401 / 405

页数：5

共 50 条

[1] The practice of I/O optimizations for out-of-core computation
Tang, JQ
Fang, BX
Hu, MZ
Zhang, HL
[J]. PARALLEL AND DISTRIBUTED COMPUTING: APPLICATIONS AND TECHNOLOGIES, PROCEEDINGS, 2004, 3320 : 81 - 85
[2] Parallel Out-of-Core computation and updating of the QR factorization
Gunter, BC
Van De Geijn, RA
[J]. ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 2005, 31 (01): : 60 - 78
[3] Out-of-Core Computation of the QR Factorization on Multi-core Processors
Marques, Mercedes
Quintana-Orti, Gregorio
Quintana-Orti, Enrique S.
van de Geijn, Robert
[J]. EURO-PAR 2009: PARALLEL PROCESSING, PROCEEDINGS, 2009, 5704 : 809 - +
[4] RCS COMPUTATION USING A PARALLEL IN-CORE AND OUT-OF-CORE DIRECT SOLVER
Garcia-Donoro, D.
Martinez-Fernandez, I.
Garcia-Castillo, L. E.
Zhang, Y.
Sarkar, T. K.
[J]. PROGRESS IN ELECTROMAGNETICS RESEARCH-PIER, 2011, 118 : 505 - 525
[5] A Flow-Guided File Layout for Out-Of-Core Streamline Computation
Chen, Chun-Ming
Xu, Lijie
Lee, Teng-Yok
Shen, Han-Wei
[J]. IEEE PACIFIC VISUALIZATION SYMPOSIUM 2012, 2012, : 145 - 152
[6] Tools for improving the out-of-core performance of data and computation intensive applications
Valsalam, VK
Reese, DS
[J]. PROCEEDINGS OF 1999 SYMPOSIUM ON PERFORMANCE EVALUATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS, 1999, : 89 - 96
[7] Grid and cluster matrix computation with persistent storage and out-of-core programming
Aouad, Lamine M.
Petiton, Serge G.
Sato, Mitsuhisa
[J]. 2005 IEEE International Conference on Cluster Computing (CLUSTER), 2006, : 372 - 380
[8] An Extension of OpenACC Directives for Out-of-Core Stencil Computation with Temporal Blocking
Miki, Nobuhiro
Ino, Fumihiko
Hagihara, Kenichi
[J]. PROCEEDINGS OF WACCPD 2016: THIRD WORKSHOP ON ACCELERATOR PROGRAMMING USING DIRECTIVES, 2016, : 36 - 45
[9] Developing a user-level middleware for out-of-core computation on grids
Tang, JQ
Fang, BX
Hu, MZ
Zhang, HL
[J]. 2004 IEEE INTERNATIONAL SYMPOSIUM ON CLUSTER COMPUTING AND THE GRID - CCGRID 2004, 2004, : 686 - 690
[10] A flow-guided file layout for out-of-core streamline computation
Ohio State University, OH 43210, United States
[J]. IEEE Symp. Large-Scale Data Anal. Visualization, LDAV 2011 - Proc., 1600, (115-116):

← 1 2 3 4 5 →