Novel Memory Technologies for Multi-Tenant Exploratory Programming
The current deep learning trend has given new popularity to the Exploratory Programming style, which often comes with high and exclusive-use demands on compute hardware and memory resources. Yet, the underlying system software is unaware of the memory semantics within applications---inhibiting optimization and use of emerging technologies. Due to over-abstraction, hardware utilization is low, resource waste (including energy) is high, and development cycles in shared scenarios are slow since users have to wait for others to give up their locks.
Authors
- Felix Grzelka (ORCID: https://orcid.org/0000-0003-3408-1868)
- Andreas Polze (ORCID: https://orcid.org/0000-0002-3423-8602)
- Sven Köhler (ORCID: https://orcid.org/0009-0003-9999-1595)
Institutions
- Hasso Plattner Institute (DE)
- University of Potsdam (DE)
Publication Details
- Published
- 2024-10-24
- DOI
- https://doi.org/10.1145/3698783.3699379
- Primary Topic
- Parallel Computing and Optimization Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Deutsche Forschungsgemeinschaft
- Bundesministerium für Bildung und Forschung