PI Name: Nicolas Denoyelle
PI Institution: argonne-national-laboratory
Collaborating ANL Division: mathematics-and-computer-science-mcs

Description: This project aims at investigating the potential of several memory optimizations on a variety of architectures.
Target optimizations will leverage topology properties of systems to investigate data and threads allocation and
migrations strategies. Furthermore, this project will investigate cross device data movements and
hardware engines to offload host or accelerator burden. Viable optimizations will be integrated into
AML library. AML is a memory management library developed at Argonne National Laboratory. The library provides
customizable base abstractions as well as application level optimizations for memory mapping and data movements.

Testbed: Neddy, witherspoon, gpu_v100_smx2, EPYC, DGX, Skylake, KNL, It, Gomez, Firestone, Petrel v3, Mustang, Maud, Lucie,

© 2020 Joint Laboratory for System Evaluation