Latency, bandwidth, and concurrent issue limitations in high-performance CFD.

Conference · Fri Nov 10 00:00:00 EST 2000

DOI:https://doi.org/10.1016/B978-008043944-0/50783-6· OSTI ID:768614

Gropp, W D; Kaushik, D K; Keyes, D E; Smith, B F

To achieve high performance, a parallel algorithm needs to effectively utilize the memory subsystem and minimize the communication volume and the number of network transactions. These issues gain further importance on modern architectures, where the peak CPU performance is increasing much more rapidly than the memory or network performance. In this paper, we present some performance enhancing techniques that were employed on an unstructured mesh implicit solver. Our experimental results show that this solver adapts reasonably well to the high memory and network latencies.

• Research Organization: Argonne National Lab., IL (US)
• Sponsoring Organization: US Department of Energy (US)
• DOE Contract Number: W-31109-ENG-38
• OSTI ID: 768614
• Report Number(s): ANL/MCS/CP-103358; TRN: US200223%%640
• Resource Relation: Conference: First M.I.T. Conference on Computational Fluid and Solid Mechanics, Cambridge, MA (US), 06/12/2001--06/14/2001; Other Information: PBD: 10 Nov 2000; PBD: 10 Nov 2000
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
ALGORITHMS
COMMUNICATIONS
PERFORMANCE