TY - GEN
T1 - Poster abstract
T2 - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012
AU - Arya, Anshu
AU - Gamblin, Todd
AU - Supinski, Bronis R.De
AU - Kale, Laxmikant V.
PY - 2012
Y1 - 2012
N2 - Intelligently mapping applications to machine network topologies has been shown to improve performance, but considerable developer effort is required to find good mappings. Techniques from graph partitioning have the potential to automate topology mapping and relieve the developer burden. Graph partitioning is already used for load balancing parallel applications, but can be applied to topology mapping as well. We show performance gains by using a topology-targeting graph partitioner to map sparse matrix-vector and volumetric 3-D FFT kernels onto a 3-D torus network.
AB - Intelligently mapping applications to machine network topologies has been shown to improve performance, but considerable developer effort is required to find good mappings. Techniques from graph partitioning have the potential to automate topology mapping and relieve the developer burden. Graph partitioning is already used for load balancing parallel applications, but can be applied to topology mapping as well. We show performance gains by using a topology-targeting graph partitioner to map sparse matrix-vector and volumetric 3-D FFT kernels onto a 3-D torus network.
UR - http://www.scopus.com/inward/record.url?scp=84876561442&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84876561442&partnerID=8YFLogxK
U2 - 10.1109/SC.Companion.2012.196
DO - 10.1109/SC.Companion.2012.196
M3 - Conference contribution
AN - SCOPUS:84876561442
SN - 9780769549569
T3 - Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012
SP - 1371
EP - 1372
BT - Proceedings - 2012 SC Companion
Y2 - 10 November 2012 through 16 November 2012
ER -