Practical performance portability in the Parallel Ocean Program (POP) Export

@article{citeulike:3517925, abstract = {The design of the Parallel Ocean Program (POP) is described with an emphasis on portability. Performance of POP is presented on a wide variety of computational architectures, including vector architectures and commodity clusters. Analysis of POP performance across machines is used to characterize performance and identify improvements while maintaining portability. A new design of the POP model, including a cache blocking and land point elimination scheme, is described with some preliminary performance results. Published in 2005 by John Wiley \& Sons, Ltd.}, address = {Theoretical Division, Los Alamos National Laboratory, T-3, MS B216, Los Alamos, NM 87545-1663, U.S.A.; Computer Science and Mathematics Division, Oak Ridge National Laboratory, P.O. Box 2008, Oak Ridge, TN 37831-6367, U.S.A.; Central Research Institute of Electric Power Industry, 1646 Abiko Abiko-shi Chiba, 270-1194, Japan; Cray Inc., 411 First Avenue South, Suite 600, Seattle, WA 98104-2860, U.S.A.}, author = {Jones, P. W. and Worley, P. H. and Yoshida, Y. and Iii, White J. B. and Levesque, J.}, citeulike-article-id = {3517925}, citeulike-linkout-0 = {http://dx.doi.org/10.1002/cpe.894}, citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/110432161/ABSTRACT}, doi = {10.1002/cpe.894}, journal = {Concurrency and Computation: Practice and Experience}, keywords = {comparison-ib-mx, hpc-app, pop}, number = {10}, pages = {1317--1327}, posted-at = {2008-11-15 01:38:55}, priority = {2}, title = {Practical performance portability in the Parallel Ocean Program (POP)}, url = {http://dx.doi.org/10.1002/cpe.894}, volume = {17}, year = {2005} }

TY - JOUR ID - citeulike:3517925 L3 - citeulike-article-id:3517925 N2 - The design of the Parallel Ocean Program (POP) is described with an emphasis on portability. Performance of POP is presented on a wide variety of computational architectures, including vector architectures and commodity clusters. Analysis of POP performance across machines is used to characterize performance and identify improvements while maintaining portability. A new design of the POP model, including a cache blocking and land point elimination scheme, is described with some preliminary performance results. Published in 2005 by John Wiley & Sons, Ltd. IS - 10 JF - Concurrency and Computation: Practice and Experience AD - Theoretical Division, Los Alamos National Laboratory, T-3, MS B216, Los Alamos, NM 87545-1663, U.S.A.; Computer Science and Mathematics Division, Oak Ridge National Laboratory, P.O. Box 2008, Oak Ridge, TN 37831-6367, U.S.A.; Central Research Institute of Electric Power Industry, 1646 Abiko Abiko-shi Chiba, 270-1194, Japan; Cray Inc., 411 First Avenue South, Suite 600, Seattle, WA 98104-2860, U.S.A. EP - 1327 TI - Practical performance portability in the Parallel Ocean Program (POP) VL - 17 SP - 1317 KW - comparison-ib-mx KW - hpc-app KW - pop AU - Jones, PW AU - Worley, PH AU - Yoshida, Y AU - Iii, White AU - Levesque, J PY - 2005/// UR - http://dx.doi.org/10.1002/cpe.894 ER -