ATC 2017 July 12, 2017 to July 14, 2017, santa clara,usa

Event Page


Tell us about missing data
Title Speakers Summary Topic Types
Opening Remarks and Awards Bryan Ford , Dilma Da Silva N/A
Computer Systems Research in the Post-Virtualization Era Ed Bugnion The evolution of computing technology has led to the centralization into mega-computing resources, the disruption ...
Lock-in-Pop: Securing Privileged Operating System Kernels by Keeping on the Beaten Path Justin Cappos , Brendan Dolan-gavitt , Yiwen Li , Sam Weber Virtual machines (VMs) that try to isolate untrusted code are widely used in practice. However, ...
Fast and Precise Retrieval of Forward and Back Porting Information for Linux Device Drivers Gilles Muller , Julia Lawall , Derek Palinski , Lukas Gnirke Porting Linux device drivers to target more recent and older Linux kernel versions to compensate ...
Optimizing the TLB Shootdown Algorithm with Page Access Tracking Nadav Amit The operating system is tasked with maintaining the coherency of per-core TLBs, necessitating costly synchronization ...
Falcon: Scaling IO Performance in Multi-SSD Volumes H. Howie Huang , Pradeep Kumar With the high throughput offered by solid-state drives (SSDs), multi-SSD volumes have become an attractive ...
deTector: a Topology-aware Monitoring System for Data Center Networks Chengchen Hu , Yanghua Peng , Ji Yang , Chuan Wu , Chuanxiong Guo , Zongpeng Li Troubleshooting network performance issues is a challenging task especially in large-scale data center networks. This ...
Pricing Intra-Datacenter Networks with Over-Committed Bandwidth Guarantee Tao Wang , Jian Guo , John C.s. Lui , Fangming Liu Current IaaS clouds provide performance guarantee on CPU and memory but no quantitative network performance ...
Unobtrusive Deferred Update Stabilization for Efficient Geo-Replication Chathuri Gunawardhana , Manuel Bravo , Luis Rodrigues In this paper, we propose a novel approach to manage the throughput vs visibility latency ...
Don't cry over spilled records: Memory elasticity of data-parallel applications and its application to cluster scheduling Florin Dinu , Calin Iorgulescu , Willy Zwaenepoel , Aunn Raza , Wajih Ul Hassan Understanding the performance of data-parallel workloads when resource-constrained has significant practical importance but unfortunately has ...
Popularity Prediction of Facebook Videos for Higher Quality Streaming Wyatt Lloyd , Linpeng Tang , Ymir Vigfusson , Qi Huang , Amit Puntambekar , Kai Li Streaming video algorithms dynamically select between different versions of a video to deliver the highest ...
Squeezing out All the Value of Loaded Data: An Out-of-core Graph Processing System with Reduced Disk I/O Yongwei Wu , Zhiyuan Ai , Mingxing Zhang , Xuehai Qian , Kang Chen , Weimin Zheng The current primary concern of out-of-core graph processing systems is improving disk I/O locality, which ...
Ending the Anomaly: Achieving Low Latency and Airtime Fairness in WiFi Anna Brunstrom , Toke Høiland-jørgensen , Michał Kazior , Dave Täht , Per Hurtig With more devices connected, delays and jitter at the WiFi hop become more prevalent, and ...
Persona: A High-Performance Bioinformatics Framework Christos Kozyrakis , Edouard Bugnion , Stuart Byma , Sam Whitlock , Laura Flueratoru , Ethan Tseng , James Larus Next-generation genome sequencing technology has reached a point at which it is becoming cost-effective to ...
SPIN: Seamless Operating System Integration of Peer-to-Peer DMA Between SSDs and GPUs Mark Silberstein , Shai Bergman , Tanya Brokhman , Tzachi Cohen Recent GPUs enable Peer-to-Peer Direct Memory Access (P2P) from fast peripheral devices like NVMe SSDs ...
Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters Hao Zhang , Qirong Ho , Jinliang Wei , Wei Dai , Eric P. Xing , Zeyu Zheng , Shizhen Xu , Xiaodan Liang , Zhiting Hu , Pengtao Xie Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling ...
Garaph: Efficient GPU-accelerated Graph Processing on a Single Machine with Balanced Replication Yafei Dai , Jilong Xue , Lingxiao Ma , Zhi Yang , Han Chen Recent advances in storage (e.g., DDR4, SSD, NVM) and accelerators (e.g., GPU, Xeon-Phi, FPGA) provide ...
GPU Taint Tracking Kai Shen , Ari B. Hayes , Lingda Li , Mohammad Hedayati , Jiahuan He , Eddy Z. Zhang Dynamic tainting tracks the influence of certain inputs (taint sources) through execution and it is ...
Optimizing the Design and Implementation of the Linux ARM Hypervisor Jason Nieh , Christoffer Dall , Shih-wei Li Modern hypervisor designs for both ARM and x86 virtualization rely on running an operating system ...
Multi-Hypervisor Virtual Machines: Enabling an Ecosystem of Hypervisor-level Services Daniel nathan Williams , Yaohui Hu , Kartik Gopalan , Nilton Bila , Rohit Kugve , Hardik Bagdi Public cloud software marketplaces already offer users a wealth of choice in operating systems, database ...
Preemptive, Low Latency Datacenter Scheduling via Lightweight Virtualization Wei Chen , Jia Rao , Xiaobo Zhou Data centers are evolving to host heterogeneous workloads on shared clusters to reduce the operational ...
The RCU-Reader Preemption Problem in VMs Aravinda Prasad , K Gopinath , Paul E. Mckenney When synchronization primitives such as locking and read-copy update (RCU) execute within virtual machines (VMs), ...
Bunshin: Compositing Security Mechanisms through Diversification Taesoo Kim , Wenke Lee , Kangjie Lu , Meng Xu A number of security mechanisms have been proposed to harden programs written in unsafe languages, ...
Glamdring: Automatic Application Partitioning for Intel SGX Peter Pietzuch , Florian Kelbert , Christof Fetzer , Christian Priebe , Divya Muthukumaran , Dan O'keeffe , David Eyers , Joshua Lind , Pierre-louis Aublin , Tobias Reiher , David Goltzsche , Rudiger Kapitza Trusted execution support in modern CPUs, as offered by Intel SGX enclaves, can protect applications ...
High-Resolution Side Channels for Untrusted Operating Systems Weidong Cui , Marcus Peinado , Marcus Hähnel Feature-rich mass-market operating systems have large trusted computing bases (TCBs) and a long history of ...
Understanding Security Implications of Using Containers in the Cloud Canturk Isci , Nilton Bila , Byungchul Tak , Sastry Duri , Shripad Nadgowda , James Doran Container technology is being adopted as a mainstream platform for IT solutions because of high ...
Memshare: a Dynamic Multi-tenant Key-value Cache Stephen M. Rumble , Ryan Stutsman , Asaf Cidon , Daniel Rushton Web application performance heavily relies on the hit rate of DRAM key-value caches. Current DRAM ...
Replication-driven Live Reconfiguration for Fast Distributed Transaction Processing Haibo Chen , Rong Chen , Xingda Wei , Sijie Shen Recent in-memory database systems leverage advanced hardware features like RDMA to provide transactional processing at ...
HiKV: A Hybrid Index Key-Value Store for DRAM-NVM Memory Systems Fei Xia , Ninghui Sun , Dejun Jiang , Jin Xiong Hybrid memory systems consisting of DRAM and Non-Volatile Memory are promising to persist data fast. ...
TRIAD: Creating Synergies Between Memory, Disk and Log in Log Structured Key-Value Stores Willy Zwaenepoel , Aashray Arora , Karan Gupta , Oana Balmau , Diego Didona , Rachid Guerraoui , Huapeng Yuan , Pavan Konka We present TRIAD, a new persistent key-value (KV) store based on Log-Structured Merge (LSM) trees. ...
Visualizing Performance with Flame Graphs Brendan Gregg Flame graphs are a simple stack trace visualization that helps answer an everyday problem: how ...
Performance Superpowers with Enhanced BPF Brendan Gregg The Berkeley Packet Filter (BPF) in Linux has been enhanced in very recent versions to ...
Engineering Record and Replay for Deployability Nimrod Partush , Chris Jones , Robert O’callahan , Nathan Froyd , Kyle Huey , Albert Noll The ability to record and replay program executions with low overhead enables many applications, such ...
Proactive error prediction to improve storage system reliability Bianca Schroeder , Ioan Stefanovici , Farzaneh Mahdisoltani This paper proposes the use of machine learning techniques to make storage systems more reliable ...
Towards Production-Run Heisenbugs Reproduction on Commercial Hardware Shiyou Huang , Bowen Cai , Jeff Huang We present a new technique, H3, for reproducing Heisenbugs in production runs on commercial hardware. ...
A DSL Approach to Reconcile Equivalent Divergent Program Executions Luís Pina , Daniel Grumberg , Anastasios Andronidis , Cristian Cadar Multi-Version Execution (MVE) deploys multiple versions of the same program, typically synchronizing their execution at ...
Titan: Fair Packet Scheduling for Commodity Multiqueue NICs Aditya Akella , Michael M. Swift , Brent Stephens , Arjun Singhvi , Uw The performance of an OS’s networking stack can be measured by its achieved throughput, CPU ...
MopEye: Opportunistic Monitoring of Per-app Mobile Network Performance Debin Gao , Rocky Chang , Daoyuan Wu , Eric Cheng , Weichao Li Crowdsourcing mobile user’s network performance has become an effective way of understanding and improving mobile ...
Emu: Rapid Prototyping of Networking Services Paolo Costa , Jon Crowcroft , Marcin Wojcik , Peter Pietzuch , Richard Mortier , Luo Mai , Nik Sultana , Salvator Galea , David Greaves , And Jonny Shipton , Richard Clegg , Pietro Bressana , Robert Soule , Andrew W Moore , Noa Zilberman Due to their performance and flexibility, FPGAs are an attractive platform for the execution of ...
Protego: Cloud-Scale Multitenant IPsec Gateway Sue Moon , Jeongseok Son , Yongqiang Xiong , Kun Tan , Paul Wang , Ze Gan Virtual cloud network services let users have their own private networks in the public cloud. ...
Cache Modeling and Optimization using Miniature Simulations Carl Waldspurger , Irfan Ahmad , Trausti Saemundson , Nohhyun Park Recent approximation algorithms (e.g., CounterStacks, SHARDS and AET) make lightweight, continuously-updated miss ratio curves (MRCs) ...
Hyperbolic Caching: Flexible Caching for Web Applications Michael J. Freedman , Siddhartha Sen , Aaron Blankstein Today’s web applications rely heavily on caching to reduce latency and backend load, using services ...
Execution Templates: Caching Control Plane Decisions for Strong Scaling of Data Analytics Philip Levis , Chinmayee Shah , Omid Mashayekhi , Hang Qu Control planes of cloud frameworks trade off between scheduling granularity and performance. Centralized systems schedule ...
cHash: Detection of Redundant Compilations via AST Hashing Christian Dietrich , Daniel Lohmann , Valentin Rothberg , Ludwig Füracker , Andreas Ziegler Software projects that use a compiled language are built hundreds of thousands of times during ...
Application Crash Consistency and Performance with CCFS Andrea C. Arpaci-dusseau , Remzi H. Arpaci-dusseau , Vijay Chidambaram , Lanyue Lu , Thanumalayan Sankaranarayana Pillai , Ramnatthan Alagappan Best Paper at FAST '17: Link to Paper Recent research has shown that applications often ...
Push-Button Verification of File Systems via Crash Refinement Xi Wang , Helgi Sigurbjarnarson , James Bornholt , Emina Torlak Best Paper at OSDI '16: Link to Paper The file system is an essential operating ...
Early Detection of Configuration Errors to Reduce Failure Damage Yuanyuan Zhou , Peng Huang , Xinxin Jin , Shan Lu , Tianyin Xu , Long Jin , Shankar Pasupathy Best Paper at OSDI '16: Link to Paper Early detection is the key to minimizing ...
Fast, Lean, and Accurate: Modeling Password Guessability Using Neural Networks Lorrie Faith Cranor , Lujo Bauer , Nicolas Christin , Blase Ur , Saranga Komanduri , William Melicher , Sean M. Segreti Best Paper at USENIX Security '16: Link to Paper Human-chosen text passwords, today’s dominant form ...
Giza: Erasure Coding Objects across Global Data Centers Jin Li , Jinyang Li , Aaron Ogus , Shuai Mu , Cheng Huang , Yu Lin Chen , Douglas Phillips Microsoft Azure Storage is a global cloud storage system with a footprint in 38 geographic ...
SmartCuckoo: A Fast and Cost-Efficient Hashing Index Scheme for Cloud Storage Systems Song Jiang , Yu Hua , Yuanyuan Sun , Qiuyu Li , Shunde Cao , Pengfei Zuo Fast query services are important to improve overall per- formance of large-scale storage systems when ...
Repair Pipelining for Erasure-Coded Storage Patrick Lee , Runhui Li , Xiaolu Li , Qun Huang We propose repair pipelining, a technique that speeds up the repair performance in general erasure-coded ...
PARIX: Speculative Partial Writes in Erasure-Coded Systems Huiba Li , Yiming Zhang , Zhiming Zhang , Shengyun Liu , Dongsheng Li , Xiaohui Liu , Yuxing Peng Erasure coding (EC) has been widely used in cloud storage systems because it effectively reduces ...
E-Team: Practical Energy Accounting for Multi-Core Systems Marcus Hähnel , Till Smejkal , Thomas Ilsche , Michael Roitzsch , Wolfgang E. Nagel , Hermann Härtig Energy-based billing as well as energy-efficient software require accurate knowledge of energy consumption. Model-based energy ...
Scalable NUMA-aware Blocking Synchronization Primitives Taesoo Kim , Changwoo Min , Sanidhya Kashyap Application scalability is a critical aspect to efficiently use NUMA machines with many cores. To ...
StreamBox: Modern Stream Processing on a Multicore Machine Myeongjae Jeon , Hongyu Miao , Heejin Park , Gennady Pekhimenko , Kathryn S. Mckinley , Felix Xiaozhu Lin Stream analytics on real-time events has an insatiable demand for throughput and latency. Its performance ...
Everything you always wanted to know about multicore graph processing but were afraid to ask Baptiste Lepers , Willy Zwaenepoel , Jasmina Malicevic Graph processing systems are used in a wide variety of fields, ranging from biology to ...
Graphene-SGX: A Practical Library OS for Unmodified Applications on SGX Chia-che Tsai , Donald E. Porter , Mona Vij Intel SGX hardware enables applications to protect themselves from potentially-malicious OSes or hypervisors. In cloud ...
PrivApprox: Privacy-Preserving Stream Analytics Ruichuan Chen , Pramod Bhatotia , Martin Beck , Thorsten Strufe , Christof Fetzer , Do Le Quoc How to preserve users’ privacy while supporting high-utility analytics for low-latency stream processing? To answer ...
Mercury: Bandwidth-Effective Prevention of Rollback Attacks Against Community Repositories Justin Cappos , Trishank Karthik Kuppusamy , Vladimir Diaz A popular community repository such as Docker Hub, PyPI, or RubyGems distributes tens of thousands ...
CAB-Fuzz: Practical Concolic Testing Techniques for COTS Operating Systems Su Yong Kim , Taesoo Kim , Byoungyoung Lee , Sangho Lee , Wen Xu , Insu Yun , Youngtae Yun Discovering the security vulnerabilities of commercial off-the-shelf (COTS) operating systems (OSes) is challenging because they ...
Log-Structured Non-Volatile Main Memory Thomas Moscibroda , Jiwu Shu , Anirudh Badam , Jinglei Ren , Qingda Hu Emerging non-volatile main memory (NVMM) unlocks the performance potential of applications by storing persistent data ...
Soft Updates Made Simple and Fast on Non-volatile Memory Haibo Chen , Mingkai Dong Fast, byte-addressable NVM promises near cache latency and near memory bus throughput for file system ...
SmartMD: A High Performance Deduplication Engine with Mixed Pages Song Jiang , John C.s. Lui , Fan Guo , Yongkun Li , Yinlong Xu In hypervisor-based virtualization environments, translation lookaside buffers (TLBs) misses may induce two-dimensional page table walks, ...
Elastic Memory Management for Cloud Data Analytics Jingjing Wang , Magdalena Balazinska We develop an approach for the automatic and elastic management of memory in shared clusters ...
Improving File System Performance of Mobile Storage Systems Using a Decoupled Defragmenter Sangwook Shane Hahn , Sungjin Lee , Jihong Kim , Liang Shi , Chun Jason Xue , Cheng Ji , Li-pin Chang , Inhyuk Yee In this paper, we comprehensively investigate the file fragmentation problem on mobile flash storage. From ...
Octopus: an RDMA-enabled Distributed Persistent Memory File System Youyou Lu , Jiwu Shu , Tao Li , Youmin Chen Non-volatile memory (NVM) and remote direct memory access (RDMA) provide extremely high performance in storage ...
iJournaling: Fine-Grained Journaling for Improving the Latency of Fsync System Call Dongkun Shin , Daejun Park For data durability, many applications rely on synchronous operations such as an fsync() system call. ...
Scaling Distributed File Systems in Resource-Harvesting Datacenters Ricardo Bianchini , Pulkit A. Misra , Íñigo Goiri , Jason Kace Datacenters can use distributed file systems to store data for batch processing on the same ...