132 citations
- Massachusetts Institute of TechnologyUS4 papers
- University of LübeckDE4 papers
- University of WashingtonUS4 papers
- Assumption CollegeUS3 papers
- Lehigh UniversityUS3 papers
- University of California San DiegoUS3 papers
- University of IowaUS3 papers
- University of MichiganUS3 papers
- University of Southern MississippiUS3 papers
- Virginia TechUS3 papers
- California University of PennsylvaniaUS2 papers
- Carnegie Mellon UniversityUS2 papers
Showing 2021 · cs.DCShow all
3 papers · 2 filters
cs.DC2021
Characterizing Concurrency Mechanisms for NVIDIA GPUs under Deep Learning Workloads
Guin Gilman, Robert J. Walls
We investigate the performance of the concurrency mechanisms available on NVIDIA's new Ampere GPU microarchitecture under deep learning training and inference workloads. In contras…
cs.DC2021★ 3 cited
Enabling Sustainable Clouds: The Case for Virtualizing the Energy System
Noman Bashir, Tian Guo, Mohammad Hajiesmaili +5
Cloud platforms' growing energy demand and carbon emissions are raising concern about their environmental sustainability. The current approach to enabling sustainable clouds focuse…
cs.DC2021★ 2 cited
Sync-Switch: Hybrid Parameter Synchronization for Distributed Deep Learning
Shijian Li, Oren Mangoubi, Lijie Xu +1
Stochastic Gradient Descent (SGD) has become the de facto way to train deep neural networks in distributed clusters. A critical factor in determining the training throughput and mo…