Fisc: a large-scale cloud-native-oriented file system

Q Li, L Chen, X Wang, S Huang, Q Xiang… - … USENIX Conference on …, 2023 - usenix.org
The wide adoption of Cloud Native shifts the boundary between cloud users and CSPs
(Cloud Service Providers) from VM-based infrastructure to container-based applications …

RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Caching and Sharing

H Yu, R Basu Roy, C Fontenot, D Tiwari, J Li… - Proceedings of the 29th …, 2024 - dl.acm.org
Serverless computing has grown rapidly as a new cloud computing paradigm that promises
ease-of-management, cost-efficiency, and auto-scaling by shipping functions via self …

Flashpoint: A Low-latency Serverless Platform for Deep Learning Inference Serving

JDQ San Juan - 2023 - uwspace.uwaterloo.ca
Recent breakthroughs in Deep Learning (DL) have led to high demand for executing
inferences in interactive services such as ChatGPT and GitHub Copilot. However, these …

WarmSwap: Sharing Dependencies for Accelerating Cold Starts in Serverless Functions

R Li, D Tiwari, G Cooperman - arXiv preprint arXiv:2409.09202, 2024 - arxiv.org
This work presents WarmSwap, a novel provider-side cold-start optimization for serverless
computing. This optimization reduces cold-start time when booting and loading …

[PDF][PDF] Pre-Warming is Not Enough: Accelerating Serverless Inference With Opportunistic Pre-Loading

Y Sui, H Yu, Y Hu, J Li, H Wang - 2024 - intellisys.haow.us
Serverless computing has rapidly prospered as a new cloud computing paradigm with agile
scalability, pay-as-you-go pricing, and ease-to-use features for Machine Learning (ML) …

[PDF][PDF] Is It Time To Put Cold Starts In The Deep Freeze?

C Segarra, I Durev, P Pietzuch - 2024 - lsds.doc.ic.ac.uk
Cold-start times have been the “end-all, be-all” metric for research in serverless cloud
computing over the past decade. Reducing the impact of cold starts matters, because they …

[PDF][PDF] Making the Most of Serverless Accelerators

A Ramkumar - 2022 - eecs.berkeley.edu
The increased performance of specialized computer hardware such as GPUs and TPUs
over the past few years has led to orders of magnitude more powerful machine learning …

Serverless Computing: A Systematic Literature Review of Challenges and Opportunities

C Huang, X Du, Y Huang, R Zhang, M Yan… - Available at SSRN … - papers.ssrn.com
Serverless computing has gained widespread recognition for its lightweight and easy-to-
manage characteristics. Users only need to focus on the implementation of functions, while …