Non-preconditioned conjugate gradient on cell and FPGA based hybrid supercomputer nodes

Conference · Thu Jan 01 00:00:00 EST 2009

DOI:https://doi.org/10.1109/FCCM.2009.26· OSTI ID:956510

Dubois, David H ^[1]; Dubois, Andrew J ^[1]; Boorman, Thomas M ^[1]; Connor, Carolyn M ^[1]

---

1. Los Alamos National Laboratory

This work presents a detailed implementation of a double precision, non-preconditioned, Conjugate Gradient algorithm on a Roadrunner heterogeneous supercomputer node. These nodes utilize the Cell Broadband Engine Architecture{sup TM} in conjunction with x86 Opteron{sup TM} processors from AMD. We implement a common Conjugate Gradient algorithm, on a variety of systems, to compare and contrast performance. Implementation results are presented for the Roadrunner hybrid supercomputer, SRC Computers, Inc. MAPStation SRC-6 FPGA enhanced hybrid supercomputer, and AMD Opteron only. In all hybrid implementations wall clock time is measured, including all transfer overhead and compute timings.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC52-06NA25396
• OSTI ID: 956510
• Report Number(s): LA-UR-09-00248; LA-UR-09-248; TRN: US201014%%1879
• Resource Relation: Conference: Field-Programmable Custom Computing Machines 2009 (FCCM'09) ; April 5, 2009 ; Napa, CA
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
ACCURACY
ALGORITHMS
COMPUTER ARCHITECTURE
COMPUTERS
PERFORMANCE
SUPERCOMPUTERS