TY - JOUR
T1 - Scalable, Multi-Constraint, Complex-Objective Graph Partitioning
AU - Slota, George M.
AU - Root, Cameron
AU - Devine, Karen
AU - Madduri, Kamesh
AU - Rajamanickam, Sivasankaran
N1 - Funding Information:
This research is part of the Blue Waters sustained-petascale computing project, which was supported by the National Science Foundation (awards OCI-0725070, ACI-1238993, and ACI-1444747) and the state of Illinois. Blue Waters is a joint effort of the University of Illinois at Urbana-Champaign and its National Center for Supercomputing Applications. This work was supported in part by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, Scientific Discovery through Advanced Computing (SciDAC) program through the FASTMath Institute under Contract No. DE-AC02-05CH11231 at Rensselaer Polytechnic Institute and Sandia National Laboratories. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology and Engineering Solutions of Sandia, LLC., a wholly owned subsidiary of Hon-eywell International, Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA-0003525. This work was also supported by NSF Grants ACI-1253881 and CCF-1439057.
Publisher Copyright:
© 1990-2012 IEEE.
PY - 2020/12/1
Y1 - 2020/12/1
N2 - We introduce XtraPuLP, a distributed-memory graph partitioner designed to process irregular trillion-edge graphs. XtraPuLP is based on the scalable label propagation community detection technique, which has been demonstrated in various prior works as a viable means to produce high quality partitions of skewed and small-world graphs with minimal computation time. Our XtraPuLP implementation can also be generalized to compute partitions with an arbitrary number of constraints, and it can compute partitions with balanced communication load across all parts. On a collection of large sparse graphs, we show that XtraPuLP partitioning is considerably faster than state-of-the-art partitioning methods, while also demonstrating that XtraPuLP can produce partitions of real-world graphs with billion+ vertices and over a hundred billion edges in minutes. Additionally, we demonstrate XtraPuLP on a variety of applications, including large-scale graph analytics and sparse matrix-vector multiplication.
AB - We introduce XtraPuLP, a distributed-memory graph partitioner designed to process irregular trillion-edge graphs. XtraPuLP is based on the scalable label propagation community detection technique, which has been demonstrated in various prior works as a viable means to produce high quality partitions of skewed and small-world graphs with minimal computation time. Our XtraPuLP implementation can also be generalized to compute partitions with an arbitrary number of constraints, and it can compute partitions with balanced communication load across all parts. On a collection of large sparse graphs, we show that XtraPuLP partitioning is considerably faster than state-of-the-art partitioning methods, while also demonstrating that XtraPuLP can produce partitions of real-world graphs with billion+ vertices and over a hundred billion edges in minutes. Additionally, we demonstrate XtraPuLP on a variety of applications, including large-scale graph analytics and sparse matrix-vector multiplication.
UR - http://www.scopus.com/inward/record.url?scp=85087777593&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85087777593&partnerID=8YFLogxK
U2 - 10.1109/TPDS.2020.3002150
DO - 10.1109/TPDS.2020.3002150
M3 - Article
AN - SCOPUS:85087777593
VL - 31
SP - 2789
EP - 2801
JO - IEEE Transactions on Parallel and Distributed Systems
JF - IEEE Transactions on Parallel and Distributed Systems
SN - 1045-9219
IS - 12
M1 - 9115834
ER -