Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

A Recursive Hypergraph Bipartitioning Framework for Reducing Bandwidth and Latency Costs Simultaneously

Journal Article · · IEEE Transactions on Parallel and Distributed Systems
 [1];  [1];  [1]
  1. Bilkent Univ., Ankara (Turkey)
+ Show Author Affiliations

Intelligent partitioning models are commonly used for efficient parallelization of irregular applications on distributed systems. These models usually aim to minimize a single communication cost metric, which is either related to communication volume or message count. However, both volume- and message-related metrics should be taken into account during partitioning for a more efficient parallelization. There are only a few works that consider both of them and they usually address each in separate phases of a two-phase approach. In this work, we propose a recursive hypergraph bipartitioning framework that reduces the total volume and total message count in a single phase. In this framework, the standard hypergraph models, nets of which already capture the bandwidth cost, are augmented with message nets. The message nets encode the message count so that minimizing conventional cutsize captures the minimization of bandwidth and latency costs together. Our model provides a more accurate representation of the overall communication cost by incorporating both the bandwidth and the latency components into the partitioning objective. The use of the widely-adopted successful recursive bipartitioning framework provides the flexibility of using any existing hypergraph partitioner. In conclusion, the experiments on instances from different domains show that our model on the average achieves up to 52 percent reduction in total message count and hence results in 29 percent reduction in parallel running time compared to the model that considers only the total volume.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1525129
Journal Information:
IEEE Transactions on Parallel and Distributed Systems, Journal Name: IEEE Transactions on Parallel and Distributed Systems Vol. 28; ISSN 1045-9219
Publisher:
IEEECopyright Statement
Country of Publication:
United States
Language:
English

References (23)

Graph partitioning and parallel solvers: Has the emperor no clothes? book January 1998
Graph partitioning models for parallel computing journal November 2000
Hypergraph partitioning for multiple communication cost metrics: Model and methods journal March 2015
A new metric enabling an exact hypergraph model for the communication volume in distributed-memory parallel applications journal August 2013
Reducing latency cost in 2D sparse matrix partitioning models journal September 2016
Hypergraph-partitioning-based decomposition for parallel sparse-matrix vector multiplication journal July 1999
Multilevel hypergraph partitioning: applications in VLSI domain journal March 1999
A Medium-Grain Method for Fast 2D Bipartitioning of Sparse Matrices conference May 2014
Semi-two-dimensional Partitioning for Parallel Sparse Matrix-Vector Multiplication conference May 2015
Matrix-vector multiplication and conjugate gradient algorithms on distributed memory computers conference August 2002
A Novel Method for Scaling Iterative Solvers: Avoiding Latency Overhead of Parallel Sparse-Matrix Vector Multiplies journal March 2015
Revisiting Hypergraph Models for Sparse Matrix Partitioning journal January 2007
On Two-Dimensional Sparse Matrix Partitioning: Models, Methods, and a Recipe journal January 2010
Sparse Matrix Computations on Parallel Processor Arrays journal May 1993
A Two-Dimensional Data Distribution Method for Parallel Sparse Matrix-Vector Multiplication journal January 2005
Encapsulating Multiple Communication-Cost Metrics in Partitioning Sparse Rectangular Matrices for Parallel Matrix-Vector Multiplies journal January 2004
A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs journal January 1998
An Efficient Parallel Algorithm for Matrix-Vector Multiplication journal March 1995
Distributed memory matrix-vector multiplication and conjugate gradient algorithms conference January 1993
The university of Florida sparse matrix collection journal November 2011
A scalable eigensolver for large scale-free graphs using 2D graph partitioning
  • Yoo, Andy; Baker, Allison H.; Pearce, Roger
  • Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '11 https://doi.org/10.1145/2063384.2063469
conference January 2011
Scalable matrix computations on large scale-free graphs using 2D graph partitioning
  • Boman, Erik G.; Devine, Karen D.; Rajamanickam, Sivasankaran
  • Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '13 https://doi.org/10.1145/2503210.2503293
conference January 2013
Multi-way partitioning using bi-partition heuristics conference January 2000

Cited By (2)

An improved exact algorithm and an NP-completeness proof for sparse matrix bipartitioning journal August 2020
Evolutionary n-level Hypergraph Partitioning with Adaptive Coarsening text January 2018

Figures / Tables (11)

Fig. 1(p. 4)figure Fig. 1
Fig. 2(p. 4)figure Fig. 2
Fig. 3(p. 5)figure Fig. 3
Fig. 4(p. 6)figure Fig. 4
Algorithm 1(p. 7)figure Algorithm 1
Fig. 5(p. 8)figure Fig. 5
Algorithm 2(p. 10)figure Algorithm 2
TABLE 1(p. 11)table TABLE 1
TABLE 2(p. 11)table TABLE 2
Fig. 6(p. 13)figure Fig. 6
TABLE 3(p. 14)table TABLE 3

Similar Records

Reduce Operations: Send Volume Balancing While Minimizing Latency
Journal Article · Tue Dec 31 23:00:00 EST 2019 · IEEE Transactions on Parallel and Distributed Systems · OSTI ID:1595427
Partitioning Models for Scaling Parallel Sparse Matrix-Matrix Multiplication
Journal Article · Tue Jan 02 23:00:00 EST 2018 · ACM Transactions on Parallel Computing · OSTI ID:1525287

Related Subjects

97 MATHEMATICS AND COMPUTING
bandwidth
combinatorial scientific computing
communication cost
hypergraph
latency
load balancing
partitioning
recursive bipartitioning
sparse matrix vector multiplication