Making kernel bypass practical for the cloud with Junction

J Fried, GI Chaudhry, E Saurez, E Choukse… - … USENIX Symposium on …, 2024 - usenix.org
Kernel bypass systems have demonstrated order of magnitude improvements in throughput
and tail latency for network-intensive applications relative to traditional operating systems …

Using cloud functions as accelerator for elastic data analytics

H Bian, T Sha, A Ailamaki - Proceedings of the ACM on Management of …, 2023 - dl.acm.org
Cloud function (CF) services, such as AWS Lambda, have been applied as the new
computing infrastructure in implementing analytical query engines. For bursty and sparse …

[PDF][PDF] Compucache: Remote computable caching using spot vms

Q Zhang, PA Bernstein, DS Berger… - Annual Conference on …, 2022 - par.nsf.gov
Data management systems are hungry for main memory, and cloud data centers are awash
in it. But that memory is not always easily accessible and often too expensive. To bridge this …

{BlockFlex}: Enabling Storage Harvesting with {Software-Defined} Flash in Modern Cloud Platforms

B Reidys, J Sun, A Badam, S Noghabi… - 16th USENIX Symposium …, 2022 - usenix.org
Cloud platforms today make efficient use of storage resources by slicing them among multi-
tenant applications on demand. However, our study discloses that the cloud storage is still …

Snape: Reliable and low-cost computing with mixture of spot and on-demand vms

F Yang, L Wang, Z Xu, J Zhang, L Li, B Qiao… - Proceedings of the 28th …, 2023 - dl.acm.org
Cloud providers often have resources that are not being fully utilized, and they may offer
them at a lower cost to make up for the reduced availability of these resources. However …

Libra: Harvesting idle resources safely and timely in serverless clusters

H Yu, C Fontenot, H Wang, J Li, X Yuan… - Proceedings of the 32nd …, 2023 - dl.acm.org
Serverless computing has been favored by users and infrastructure providers from various
industries, including online services and scientific computing. Users enjoy its auto-scaling …

Anticipatory Resource Allocation for ML Training

T Chugh, S Kandula, A Krishnamurthy… - Proceedings of the …, 2023 - dl.acm.org
Our analysis of a large public cloud ML training service shows that resources remain unused
likely because users statically (over-) allocate resources for their jobs given a desire for …

Last-Level Cache Side-Channel Attacks Are Feasible in the Modern Public Cloud (Extended Version)

ZN Zhao, A Morrison, CW Fletcher… - arXiv preprint arXiv …, 2024 - arxiv.org
Last-level cache side-channel attacks have been mostly demonstrated in highly-controlled,
quiescent local environments. Hence, it is unclear whether such attacks are feasible in a …

Automatically Reasoning About How Systems Code Uses the {CPU} Cache

R Iyer, K Argyraki, G Candea - 18th USENIX Symposium on Operating …, 2024 - usenix.org
We present a technique, called CFAR, that developers can use to reason precisely about
how their code, as well as third-party code, uses the CPU cache. Given a piece of systems …

Translation-optimized Memory Compression for Capacity

G Panwar, M Laghari, D Bears, Y Liu… - 2022 55th IEEE/ACM …, 2022 - ieeexplore.ieee.org
The demand for memory is ever increasing. Many prior works have explored hardware
memory compression to increase effective memory capacity. However, prior works compress …