Rutgers Systems Reading Group

We discuss papers on Computer Architecture, Programming Languages, Operating Systems/Security, and Distributed Systems. Anyone interested in these topics are welcome to join.

Please note that we will give a few questions on the paper before the meeting. There will be donuts for the participants who can answer them. The questions are posted at the bottom of this page.

Meeting time and Location

4:00 pm - 5:00 pm Mondays at CoRE B (Room 305)

Mailing List

https://email.rutgers.edu/mailman/listinfo/systems_grad

Upcoming Topics:

Date Presenter Topic Conference
Sept 22nd 2014 Md Haque The Google file system Sanjay Ghemawat, Howard Bradley Gobioff, and Shuntak Leung SOSP 2003
Sept 29th 2014 Hai Nguyen Secure Web Browsing with the OP Web Browser, Chris Grier, Shuo Tang, Samuel T. King IEEE Symposium on Security and Privacy 2008
Oct 6th 2014 Md Haque A reconfigurable fabric for accelerating large-scale datacenter services, Andrew Putnam et al. ISCA 2014
Oct 13th 2014 Binh Pham Exploiting choice: instruction fetch and issue on an implementable simultaneous multithreading processor, Dean M. Tullsen et al. ISCA 1996
Oct 20th 2014 Bill Design and evaluation of a conit-based continuous consistency model for replicated services Haifeng Yu, Amin M Vahdat ACM Transactions on Computer Systems 2002
Oct 27th 2014 Adarsh Control-flow integrity, Martín Abadi, Mihai Budiu, Úlfar Erlingsson, Jay Ligatti ACM CCS 2005
Nov 3rd 2014 Zi Yan Memory access buffering in multiprocessors, Michel Dubois, Christoph Scheurich, Faye Briggs ISCA 1986
TBD TBD Chord: A scalable peer-to-peer lookup service for internet applications Ion Stoica, Robert Tappan Morris, D. Karger, Frans Kaashoek, Hari Balakrishnan ACM SIGCOMM 2001
TBD TBD Aladdin: A Pre-RTL, Power-Performance Accelerator Simulator Enabling Large Design Space Exploration of Customized Architectures, Yakun Sophia Shao, Brandon Reagen, Gu-Yeon Wei, David Brooks ISCA 2014
TBD TBD The CHERI capability model: Revisiting RISC in an age of risk, Jonathan Woodruff et al. ISCA 2014
TBD TBD DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning, Tianshi Chen et al. ASPLOS 2014
TBD TBD K2: a mobile operating system for heterogeneous coherence domains, Felix Xiaozhu Lin, Zhen Wang, Lin Zhong ASPLOS 2014
TBD TBD Protecting privacy using the decentralized label model, Andrew C Myers, Barbara H. Liskov ACM Transactions on Software Engineering and Methodology 2000

Questions

The Google file system

Why does GFS have one master despite claiming that component failure is norm?

What portion of metadata is stored in the chunkservers?

What are the different ways for a chunkserver to hold stale data?

A reconfigurable fabric for accelerating large-scale datacenter services

What is the benefit of using FPGA for this application over GPU?

Why did the authors try to keep power overhead within 10%?

What data has been routed directly among the FPGAs?