EJ Alcántara Suárez, V Monzon Baeza - Machine Learning and …, 2023 - mdpi.com
Machine learning (ML) has become a critical technology in the defense sector, enabling the development of advanced systems for threat detection, decision making, and autonomous …
C Zhao, W Gao, F Nie, H Zhou - IEEE Transactions on Parallel …, 2021 - ieeexplore.ieee.org
The ability to support multitasking becomes more and more important in the development of graphic processing unit (GPU). GPU multitasking methods are classified into three types …
J Ahn, Y Lee, J Ahn, JG Ko - Internet of Things, 2023 - Elsevier
This work presents DIAMOND, a deep neural network computation offloading scheme consisting of a lightweight client-to-server latency profiling component combined with a …
A Dhakal, P Raith, L Ward, RP Hong Enriquez… - Proceedings of the SC' …, 2023 - dl.acm.org
Function-as-a-service (FaaS) is a promising execution environment for high-performance computing (HPC) and machine learning (ML) applications as it offers developers a simple …
S Qi, L Monis, Z Zeng, IC Wang… - … /ACM Transactions on …, 2024 - ieeexplore.ieee.org
Serverless computing promises an efficient, low-cost compute capability in cloud environments. However, existing solutions, epitomized by open-source platforms such as …
Autotuning DNN models prior to their deployment is an essential but time-consuming task. Using expensive (and power-hungry) GPU and TPU accelerators efficiently is also key …
With GPUs increasingly shared by DNN models at the edge, a crucial tradeoff arises between high GPU utilization and the ability of fast preemption when a high-priority request …