TY - GEN
T1 - Improving performance models for irregular point-to-point communication
AU - Bienz, Amanda
AU - Gropp, William D.
AU - Olson, Luke N.
N1 - Funding Information:
Applications. This material is based in part upon work supported by the National Science Foundation Graduate Research Fellowship Program under Grant Number DGE-1144245. This material is based in part upon work supported by the Department of Energy, National Nuclear, under Award Number DE-NA0002374.
Funding Information:
This research is part of the Blue Waters sustained-petascale computing project, which is supported by the National Science Foundation (awards OCI-0725070 and ACI-1238993) 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 material is based in part upon work supported by the National Science Foundation Graduate Research Fellowship Program under Grant Number DGE-1144245. This material is based in part upon work supported by the Department of Energy, National Nuclear, under Award Number DE-NA0002374.
Funding Information:
This research is part of the Blue Waters sustained-petascale computing project, which is supported by the National Science Foundation (awards OCI-0725070 and ACI-1238993) 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
Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/9/23
Y1 - 2018/9/23
N2 - Parallel applications are often unable to take full advantage of emerging parallel architectures due to scaling limitations, which arise due to inter-process communication. Performance models are used to analyze the sources of communication costs. However, traditional models for point-to-point communication fail to capture the full cost of many irregular operations, such as sparse matrix methods. In this paper, a node-aware based model is presented. Furthermore, the model is extended to include communication queue search time as well as an additional parameter estimating network contention. The resulting model is applied to a variety of irregular communication patterns throughout matrix operations, displaying improved accuracy over traditional models.
AB - Parallel applications are often unable to take full advantage of emerging parallel architectures due to scaling limitations, which arise due to inter-process communication. Performance models are used to analyze the sources of communication costs. However, traditional models for point-to-point communication fail to capture the full cost of many irregular operations, such as sparse matrix methods. In this paper, a node-aware based model is presented. Furthermore, the model is extended to include communication queue search time as well as an additional parameter estimating network contention. The resulting model is applied to a variety of irregular communication patterns throughout matrix operations, displaying improved accuracy over traditional models.
KW - MPI
KW - Network contention
KW - Performance modeling
KW - Point-to-point communication
KW - Queue search
UR - http://www.scopus.com/inward/record.url?scp=85055445048&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85055445048&partnerID=8YFLogxK
U2 - 10.1145/3236367.3236368
DO - 10.1145/3236367.3236368
M3 - Conference contribution
AN - SCOPUS:85055445048
T3 - ACM International Conference Proceeding Series
BT - EuroMPI 2018 - Proceedings of the 25th European MPI Users' Group Meeting
PB - Association for Computing Machinery
T2 - 25th European MPI Users' Group Meeting, EuroMPI 2018
Y2 - 23 September 2018 through 26 September 2018
ER -