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.
|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|
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?
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?