Accepted Posters

The following posters will be presented at the Poster Session and Happy Hour on Thursday, June 23, 2016, 6:30 p.m.–8:00 p.m. Many of the USENIX ATC '16 refereed papers will also be presented as posters during the session.

SHRD: Improving Spatial Locality in Flash Storage Accesses by Sequentializing in Host and Randomizing in Device
Hyukjoong Kim and Dongkun Shin, Sungkyunkwan University; Yun Ho Jeong and Kyung Ho Kim, Samsung Electronics

xBalloon: Bridging the Gap between Physical and Virtual Environments in I/O Prioritization
Kun Suo and Jia Rao, University of Colorado Colorado Springs; Luwei Cheng, Facebook; Xiaobo Zhou, University of Colorado Colorado Springs; Francis C. M. Lau, The University of Hong Kong

TagIt: An Integrated Search and Discovery Service for Extreme-Scale File Systems
Hyogi Sim, Oak Ridge National Laboratory and Virginia Polytechnic Institute and State University; Youngjae Kim, Ajou University; Sudharshan S. Vazhkudai, Geoffroy R. Vallée, and Seung-Hwan Lim, Oak Ridge National Laboratory; Ali R. Butt, Virginia Polytechnic Institute and State University

Barista: A Highly Composable NOS Brewing Framework for Software-Defined Networks
Jaehyun Nam, Hyeonseong Jo, Yeonkeun Kim, and Seungwon Shin, Korea Advanced Institute of Science and Technology (KAIST); Phillip Porras and Vinod Yegneswaran, SRI International

Expeditus: Distributed Congestion-aware Load Balancing in Clos Data Center Networks
Peng Wang, Hong Xu, and Zhixiong Niu, City University of Hong Kong; Dongsu Han, Korea Advanced Institute of Science and Technology (KAIST)

A Closer Look at Eclipse Attacks against Tor Hidden Services
Qingfeng Tan and Yue Gao, Institute of Information Engineering, Chinese Academy of Sciences, National Engineering Laboratory for Information Security Technologies, and University of Chinese Academy of Sciences; Jinqiao Shi, Xuebin Wang, and Binxing Fang, Institute of Information Engineering, Chinese Academy of Sciences, and National Engineering Laboratory for Information Security Technologies

Safe Inspection and Customization of Live Virtual Machines
Sahil Suneja, University of Toronto; Ricardo Kollerr and Canturk Isci, IBM Research; Eyal de Lara, Ali Hashemi, Arnamoy Bhattacharyya, and Crsitiana Amza, University of Toronto

Omid: Hope for Scalable and Highly-Available Transaction Processing
Edward Bortnikov and Eshcar Hillel, Yahoo Labs; Idit Keidar, Technion—Israel Institute of Technology and Yahoo Labs; Ivan Kelly, Midokura; Matthieu Morel, Skyscanner; Sameer Paranjpye, Adatao; Francisco Perez-Sorrosal, Yahoo; Ohad Shacham, Yahoo Labs

Detecting Specification Noncompliance in Network Protocol Implementations
Endadul Hoque, Purdue University and Northeastern University; Omar Chowdhury and Sze Yiu Chau, Purdue University; Cristina Nita-Rotaru, Purdue University and Northeastern University; Ninghui Li, Purdue University

Trifest: Automated Inference for Probabilistic Systems
James Bornholt, University of Washington; Na Meng, Virginia Polytechnic Institute and State University; Todd Mytkowicz and Kathryn S. McKinley, Microsoft Research

Poseidon: A System Architecture for Efficient GPU-based Deep Learning on Multiple Machines
Hao Zhang, Zhiting Hu, Jinliang Wei, and Pengtao Xie, Carnegie Mellon University; Gunhee Kim, Seoul National University; Qirong Ho, Institute for Infocomm Research; Eric P. Xing, Carnegie Mellon University

Ultra KSM: A Real Time Main Memory Deduplication Scanner with Two Level Random Sampling
Nai Xia and Xiaoliang Wang, Nanjing University

FRD: A Buffer Cache Algorithm considering both Frequency and Reuse Distance
Sejin Park and Chanik Park, Pohang University of Science And Technology (POSTECH)

Building Ephemeral CDNs with MiniCache
Simon Kuenzer, Anton Ivanov, Filipe Manco, Jose Mendes, Iurii Volchkov, Florian Schmidt, and Felipe Huici, NEC Europe Ltd.

Navigating the Public Cloud Labyrinth: A Study of Price, Capacity, and Scaling Granularity Trade-offs
Cheng Wang and Bhuvan Urgaonkar, The Pennsylvania State University; Aayush Gupta, IBM Almaden Research Center; Qianlin Liang, The Pennsylvania State University

clfB-tree: Cacheline Friendly Persistent B-tree for NVRAM
Wook-Hee Kim and Jihye Seo, Ulsan National Institute of Science and Technology (UNIST); Youjip Won, Hanyang University; Beomseok Nam, Ulsan National Institute of Science and Technology (UNIST)

Ako: Decentralised Deep Learning with Partial Gradient Exchange
Pijika Watcharapichat and Victoria Lopez Morales, Imperial College London; Raul Castro Fernandez, Massachusetts Institute of Technology; Peter Pietzuch, Imperial College London