GPAW optimized for Blue Gene/P using hybrid programming
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
GPAW optimized for Blue Gene/P using hybrid programming. / Kristensen, Mads Ruben Burgdorff; Happe, Hans Henrik; Vinter, Brian.
Proceedings of the 2009 IEEE International Symposium on Parallel & Distributed Processing. IEEE, 2009. p. 1-6.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - GPAW optimized for Blue Gene/P using hybrid programming
AU - Kristensen, Mads Ruben Burgdorff
AU - Happe, Hans Henrik
AU - Vinter, Brian
N1 - Conference code: 23
PY - 2009
Y1 - 2009
N2 - In this work we present optimizations of a Grid-based projector-augmented wave method software, GPAW for the Blue Gene/P architecture. The improvements are achieved by exploring the advantage of shared and distributed memory programming also known as hybrid programming. The work focuses on optimizing a very time consuming operation in GPAW, the finite-different stencil operation, and different hybrid programming approaches are evaluated. The work succeeds in demonstrating a hybrid programming model which is clearly beneficial compared to the original flat programming model. In total an improvement of 1.94 compared to the original implementation is obtained. The results we demonstrate here are reasonably general and may be applied to other finite difference codes.
AB - In this work we present optimizations of a Grid-based projector-augmented wave method software, GPAW for the Blue Gene/P architecture. The improvements are achieved by exploring the advantage of shared and distributed memory programming also known as hybrid programming. The work focuses on optimizing a very time consuming operation in GPAW, the finite-different stencil operation, and different hybrid programming approaches are evaluated. The work succeeds in demonstrating a hybrid programming model which is clearly beneficial compared to the original flat programming model. In total an improvement of 1.94 compared to the original implementation is obtained. The results we demonstrate here are reasonably general and may be applied to other finite difference codes.
KW - Faculty of Science
KW - HPC
KW - Hybrid parallel programming
KW - Parallel framework
KW - GPAW
U2 - 10.1109/IPDPS.2009.5160936
DO - 10.1109/IPDPS.2009.5160936
M3 - Article in proceedings
SP - 1
EP - 6
BT - Proceedings of the 2009 IEEE International Symposium on Parallel & Distributed Processing
PB - IEEE
Y2 - 23 May 2009 through 29 May 2009
ER -
ID: 16811129