Charm++ techniques enable efficient overdecomposition on multi-vendor GPGPU distributed systems.
LeanMD: A Charm++ framework for high performance molecular dynamics simulation on large parallel machines
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient and Portable Support for Overdecomposition on Distributed Memory GPGPU Platforms
Charm++ techniques enable efficient overdecomposition on multi-vendor GPGPU distributed systems.