3 papers
cs.DC2020
Modeling Data Movement Performance on Heterogeneous Architectures
Amanda Bienz, Luke N. Olson, William D. Gropp +1
The cost of data movement on parallel systems varies greatly with machine architecture, job partition, and nearby jobs. Performance models that accurately capture the cost of data…
cs.DC2019
Node-Aware Improvements to Allreduce
Amanda Bienz, Luke N. Olson, William D. Gropp
The \texttt{MPI\_Allreduce} collective operation is a core kernel of many parallel codebases, particularly for reductions over a single value per process. The commonly used allredu…
cs.DC2018
Improving Performance Models for Irregular Point-to-Point Communication
Amanda Bienz, William D. Gropp, Luke N. Olson
Parallel applications are often unable to take full advantage of emerging parallel architectures due to scaling limitations, which arise due to inter-process communication. Perform…