Proceedings of the Workshop on Hot Topics in Operating Systems最新文献_第7页

Unikernels: The Next Stage of Linux's Dominance Unikernels: Linux统治的下一个阶段

Proceedings of the Workshop on Hot Topics in Operating Systems Pub Date : 2019-05-13 DOI: 10.1145/3317550.3321445

A. Raza, Parul Sohal, James Cadden, J. Appavoo, Ulrich Drepper, Richard Jones, O. Krieger, R. Mancuso, Larry Woodman

引用次数: 60

A Case for Managed and Model-less Inference Serving 管理和无模型推理服务的案例

Proceedings of the Workshop on Hot Topics in Operating Systems Pub Date : 2019-05-13 DOI: 10.1145/3317550.3321443

N. Yadwadkar, Francisco Romero, Qian Li, C. Kozyrakis

{"title":"A Case for Managed and Model-less Inference Serving","authors":"N. Yadwadkar, Francisco Romero, Qian Li, C. Kozyrakis","doi":"10.1145/3317550.3321443","DOIUrl":"https://doi.org/10.1145/3317550.3321443","url":null,"abstract":"The number of applications relying on inference from machine learning models, especially neural networks, is already large and expected to keep growing. For instance, Facebook applications issue tens-of-trillions of inference queries per day with varying performance, accuracy, and cost constraints. Unfortunately, today's inference serving systems are neither easy to use nor cost effective. Developers must manually match the performance, accuracy, and cost constraints of their applications to a large design space that includes decisions such as selecting the right model and model optimizations, selecting the right hardware architecture, selecting the right scale-out factor, and avoiding cold-start effects. These interacting decisions are difficult to make, especially when the application load varies over time, applications evolve over time, and the available resources vary over time. If we want an increasing number of applications to use machine learning, we must automate issues that affect ease-of-use, performance, and cost efficiency for both users and providers. Hence, we define and make the case for managed and model-less inference serving. In this paper, we identify and discuss open research directions to realize this vision.","PeriodicalId":224944,"journal":{"name":"Proceedings of the Workshop on Hot Topics in Operating Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124865505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 24

I/O Is Faster Than the CPU: Let's Partition Resources and Eliminate (Most) OS Abstractions I/O比CPU快:让我们划分资源并消除(大多数)操作系统抽象

Proceedings of the Workshop on Hot Topics in Operating Systems Pub Date : 2019-05-13 DOI: 10.1145/3317550.3321426

Pekka Enberg, Ashwin Rao, S. Tarkoma

引用次数: 9

Proceedings of the Workshop on Hot Topics in Operating Systems 操作系统热点专题研讨会论文集

Proceedings of the Workshop on Hot Topics in Operating Systems Pub Date : 2019-05-13 DOI: 10.1145/3317550

引用次数: 2

Can We Prove Time Protection? 我们能证明时间保护吗?

Proceedings of the Workshop on Hot Topics in Operating Systems Pub Date : 2019-01-24 DOI: 10.1145/3317550.3321431

G. Heiser, G. Klein, Toby C. Murray

引用次数: 12