An improved spectral load balancing method
Conference
·
OSTI ID:6691353
We describe an algorithm for the static load balancing of scientific computations that generalizes and improves upon spectral bisection. Through a novel use of multiple eigenvectors, our new spectral algorithm can divide a computation into 4 or 8 pieces at once. This leads to balanced partitions that have lower communication overhead and are less expensive to compute than those of spectral bisection. In addition, our approach automatically works to minimize message contention on a hypercube or mesh architecture.
- Research Organization:
- Sandia National Labs., Albuquerque, NM (United States)
- Sponsoring Organization:
- DOE; USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC04-76DP00789
- OSTI ID:
- 6691353
- Report Number(s):
- SAND-93-0164C; CONF-930331--4; ON: DE93007582
- Country of Publication:
- United States
- Language:
- English
Similar Records
Multidimensional spectral load balancing
Multidimensional spectral load balancing
An improved spectral graph partitioning algorithm for mapping parallel computations
Technical Report
·
Thu Dec 31 23:00:00 EST 1992
·
OSTI ID:6691328
Multidimensional spectral load balancing
Technical Report
·
Thu Dec 31 23:00:00 EST 1992
·
OSTI ID:10135054
An improved spectral graph partitioning algorithm for mapping parallel computations
Technical Report
·
Tue Sep 01 00:00:00 EDT 1992
·
OSTI ID:10183837