USENIX

TriCache: A User-Transparent Block Cache Enabling High-Performance Out-of-Core Processing with In-Memory Programs

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

How ML Breaks: A Decade of Outages for One Large ML Pipeline

Reliable management of continuous or periodic machine learning pipelines at large scale presents significant operational challenges. Using experience from almost 15 years of operating some of the ...
USENIX

InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a ...
USENIX

PARTEMU: Enabling Dynamic Analysis of Real-World TrustZone Software Using Emulation

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Asynchronous I/O Stack: A Low-latency Kernel I/O Stack for Ultra-Low Latency SSDs

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Exploiting a Natural Network Effect for Scalable, Fine-grained Clock Synchronization

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

My ZIP isn't your ZIP: Identifying and Exploiting Semantic Gaps Between ZIP Parsers

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

OptiReduce: Resilient and Tail-Optimal AllReduce for Distributed Deep Learning in the Cloud

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Amazon DynamoDB: A Scalable, Predictably Performant, and Fully Managed NoSQL Database Service

Mostafa Elhemali, Niall Gallagher, Nicholas Gordon, Joseph Idziorek, Richard Krog, Colin Lazier, Erben Mo, Akhilesh Mritunjai, Somu Perianayagam ,Tim Rath, Swami ...
USENIX

SLUBStick: Arbitrary Memory Writes through Practical Software Cross-Cache Attacks within the Linux Kernel

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

A Unified Architecture for Accelerating Distributed DNN Training in Heterogeneous GPU/CPU Clusters

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...