Systems Lacking Originality Workshop (SLOW '05)

Symposium Overview

SLOW '05 is the premier workshop for papers to about computer systems, especially if you are taking the graduate operating systems course here at the University of Wisconsin with Remzi, and he is making you submit your paper to this thing, and if you don't, you know you'll get a D or maybe a C at best.

The 2005 SLOW workshop seeks unoriginal and highly non-innovative papers about the applications, architecture, implementation, and performance of computing systems. Or really, papers about things that interest Remzi. Some topics of interest include:

Continuous Profiling in Linux
Adding Parity Protection to the Linux Ext3 File System
Exploring I/O in a Virtual Machine Environment
Fault Injection under the SGI XFS File System
Thread Detection in a Virtual Machine
Probabilistic Strace
Smarter NFS Server Caching with Semantic Inference
Memory Faults: Injection and Solutions
Memory Sharing in Virtual Machines
SCSI-based Fault Injection
Checksumming Ext2
IDE-based Fault Injection
Energy-Awareness in the Linux Virtual Memory Manager
An NFS Text-Searching Proxy
Lazy Logical Volume Management with Dada

Papers on all other topics will be rejected.

Reviewing of full papers will be done by the SLOW program committee, which consists of me (Remzi). Papers must use a typeface no smaller than 10 point, and be no longer than ten (10) 8.5" by 11" pages including everything EXCEPT references (text and figures must fit onto 10 pages, but references can go on additional pages). All papers must be submitted as PDF.

Program Committee

Remzi H. Arpaci-Dusseau, University of Wisconsin, Madison, (Program Chair, Cookie Provider)

Important Dates and Locations

Paper submissions are due by 11:59pm, Tuesday, May 10, 2005.
Date of workshop: The SLOW Workshop will unfortunately never take place.
That said, if it does, I will definitely call you.

Submitting a Paper

As described above, submitted papers must be no longer than 10 single-spaced 8.5" x 11" pages, including figures, tables (but not references, which can go onto additional pages), using 10 point or larger fonts. Papers longer than 10 pages will be burned by the program chair and automatically receive a very bad grade, like a C or more likely a very strong D. Papers so short as to be considered "much too short" (e.g., 7 pages or less) will not receive full consideration and thus also a bad grade, like a C or if you're lucky, a BC. Papers should be in two-column format. Papers must be submitted in the PDF file format. A good paper will demonstrate that the authors:

are attacking a significant problem

have devised an interesting, compelling solution

have demonstrated the practicality and benefits of the solution

have drawn appropriate conclusions

have clearly described what they have done

have clearly articulated the relation to previous work

Submissions will be judged on originality, significance, interest, clarity, relevance, and correctness. Unlike most other workshops, all papers will be accepted and distributed via the online electronic proceedings. Thus, submit and be guaranteed a place in this SLOW workshop!

Paper Organization

A good paper will likely have the following components:

Title and Author List: should be self-evident.
Abstract: Describe in short what you do, how you do it, and the results.
Introduction: Spend a little more time. Motivate the problem. Start with generalities, and narrow in on your problem. Describe your approach. What is good about it? Potential weaknesses? Summarize results. Give an outline of the rest of the paper.
Related Work: Write about other similiar work. What is different than what you did? What is similar? Try to draw general conclusions about what others have missed.
Description of what you did/built: Use pictures and words to show what you did. Be detailed. Think about how to organize what you are doing.
Results: Graphs and tables, all clear and understandable. Full description of each experiment and the results. What is the point of each graph? What conclusions can you draw from it?
Conclusions: Appropriately drawn from the work described, as general as possible, with a hint of "lessons learned"; what did you get out of the study? Summary is what you did; conclusions are what you learned.

One good way to structure a paper is to find a paper you liked in class and copy its structure (loosely).

If you plan on using latex (which is great for this sort of thing), click here for an example Latex template (in tar format). If you plan on using MS Word (though why would you?), please make sure you know how to generate PDF.

Authors of all papers will be expected to provide an HTML page containing the abstract of and links to their paper, and to the software and experimental data described in their paper. Papers, software, and data will all be collected for inclusion in an electronic version of the symposium.

Deadline and Submission Instructions

Submitted papers must be received by 11:59pm on Tuesday, May 10, 2005. Submission of all papers must be made in electronic form, in PDF format. As stated above, an HTML page, containing the abstract and author information, and including a link to the paper, should be submitted. A template of the abstract page is available. All submissions should be sent to remzi@cs.wisc.edu, and the email should consist of a link to the HTML page and related documents and software.

Best Paper Award

An award will be given for the best paper at the symposium. The award will be a vast sum of CASH MONEY, where if you replace "a vast sum of" with "little or no", you are more likely to be correct.

Sister Conferences

SLOW is the latest in a series of systems conferences based around CS 736. Its sister conferences are BAD , USEDNIX , SOS-Please and OS-DIE. Please feel free to peruse the on-line proceedings of these conferences for examples of previously accepted submissions.