TY - GEN
T1 - Block tridiagonal solvers on heterogeneous architectures
AU - Valero-Lara, Pedro
AU - Pinelli, Alfredo
AU - Favier, Julien
AU - Matias, Manuel Prieto
PY - 2012
Y1 - 2012
N2 - Modern multi-core and many-core systems offer a very impressive cost/performance ratio. In this paper a set of new parallel implementations for the solution of linear systems with block-tridiagonal coefficient matrix on current parallel architectures is proposed and evaluated: one of them on multi-core, others on many-core and finally, a new heterogeneous implementation on both architectures. The results show a speedup higher than 6 on certain parts of the problem, being the heterogeneous implementation the fastest.
AB - Modern multi-core and many-core systems offer a very impressive cost/performance ratio. In this paper a set of new parallel implementations for the solution of linear systems with block-tridiagonal coefficient matrix on current parallel architectures is proposed and evaluated: one of them on multi-core, others on many-core and finally, a new heterogeneous implementation on both architectures. The results show a speedup higher than 6 on certain parts of the problem, being the heterogeneous implementation the fastest.
KW - Block-tridiagonal linear systems
KW - multi-core and many-core
KW - parallel processing
UR - http://www.scopus.com/inward/record.url?scp=84867275121&partnerID=8YFLogxK
U2 - 10.1109/ISPA.2012.91
DO - 10.1109/ISPA.2012.91
M3 - Conference contribution
AN - SCOPUS:84867275121
SN - 9780769547015
T3 - Proceedings of the 2012 10th IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2012
SP - 609
EP - 616
BT - Proceedings of the 2012 10th IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2012
T2 - 2012 10th IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2012
Y2 - 10 July 2012 through 13 July 2012
ER -