2016 IEEE 23rd International Conference on High Performance Computing Workshops (HiPCW) 2016
DOI: 10.1109/hipcw.2016.027
|View full text |Cite
|
Sign up to set email alerts
|

Towards Understanding Optimal Load-Balancing of Heterogeneous Short-Range Molecular Dynamics

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
2
2
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 40 publications
0
3
0
Order By: Relevance
“…Sec. 2.1.3 [104,208]. We calculate the partition-weight of a cell c k in the FCT w fct i (c k ) as weighted sum over all input grids g,…”
Section: Figure 58mentioning
confidence: 99%
“…Sec. 2.1.3 [104,208]. We calculate the partition-weight of a cell c k in the FCT w fct i (c k ) as weighted sum over all input grids g,…”
Section: Figure 58mentioning
confidence: 99%
“…Note that not every particles simulation suffers from load imbalance created by the particle migration. For example, as suggested by [13], in Brownian motions, the migration of particles does not create load imbalance over time because there are no preferred direction for the particles. Hence, there is no particular gathering of particles in a subset of processing elements.…”
Section: Informed Partitioningmentioning
confidence: 99%
“…Recently, Hirschmann et al [13] studied the behavior of standard partitioning techniques in particle simulation using a load dynamic metric. This metric uses the norm of the difference between the load distribution at two iterations and shows that load balancing techniques are not equal with respect to the load dynamic (i.e., load imbalance growth).…”
Section: Introductionmentioning
confidence: 99%