Serverless computing promises an efficient, low-cost compute capability in cloud
environments. However, existing solutions, epitomized by open-source platforms such as …

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 …

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 …

This work presents DIAMOND, a deep neural network computation offloading scheme
consisting of a lightweight client-to-server latency profiling component combined with a …

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 …

摘要实时视频流分析在智能监控, 智慧城市, 自动驾驶等场景中具有重要价值. 然而计算负载高,
带宽需求大, 延迟要求严等特点使得实时视频流分析难以通过传统的云计算范式进行部署 …

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 …