Proceedings of the sixteenth international conference on Architectural support for programming languages and operating systems

Abstract

It is our great pleasure to welcome you to the sixteenth edition of ASPLOS and to introduce what we feel will be an outstanding and thought-provoking technical program. This year's conference continues and reinforces the ASPLOS tradition of publishing innovative multidisciplinary research spanning the boundaries of hardware, computer architecture, compilers, languages, operating systems, networking, and applications. We received 152 full paper submissions by the July 28th deadline, which was fewer than last year's record-setting year, but above average over the past three years. (127, 113 and 181 full papers were submitted in 2008, 2009, and 2010, respectively.) 22 submissions had PC members as co-authors. The dominant technical theme this year was parallelism (once again), with more than half of the submissions explicitly indicating a technical keyword specific to parallel processing. There was a nice mixture of submissions spanning the disciplines of operating systems (36%), compilers and programming languages (34%), and architecture (60%), with 38% of submissions spanning multiple of these areas. Regarding the paper reviewing process, we continued with two changes that had been adopted the previous year: we had two rounds of reviews, and we used an External Review Committee that was preselected by the Program Chair. Each paper was initially reviewed by one PC member and two ERC members. The rationale for having two ERC reviews during the first round (as opposed to one, as was the case last year) was that it gave us the most flexibility to match a paper with the experts who were most qualified to review that specific topic. Based upon these reviews (as well as follow-up discussions for any borderline cases), 103 papers were selected for a second round of reviews, where they received two more reviews from PC members. In general, any paper that received at least one vote for acceptance during the first round was selected for second round reviews. Through this two-round mechanism, we were able to limit the reviewing load per PC member to no more than 14 papers, and more importantly we allowed them to spend the bulk of their time on papers with a significant chance of being accepted. We would especially like to thank the ERC members for their hard work and dedication to the reviewing process; the typical ERC member reviewed 5 papers this year. One change that we made to the reviewing form this year was that in addition to evaluation categories that had been used in previous years (e.g., the degree of novelty, whether the paper was convincing, etc.), we added a new category where we asked reviewers to rate the extent to which a paper would be thoughtprovoking. Our goal was to make sure that we paid special attention to submissions that might inspire people to change the way that they think about how they approach their own technical research problems. We are pleased that this emphasis appears to have translated well into a highly thought-provoking technical program. We are also pleased to report that all reviews had been submitted in time for the authors to respond to them during the author rebuttal period. After the rebuttal period, the PC members and ERC members took the rebuttal comments into account as they discussed the papers online and potentially updated their scores accordingly. The PC met in person on the Carnegie Mellon University campus for a one-day meeting on October 21st, 2010. 81 papers were discussed at the meeting. PC-authored papers were handled roughly halfway through the meeting, using the hotseat approach. Jim Larus, Margaret Martonosi, and David Patterson managed the discussion of papers where the PC Chair had a conflict. The PC chose 32 papers to be presented at the conference, for an overall acceptance rate of 21.1%. 7 of the 32 papers have PC members as co-authors. Continuing with another change that was made last year, all papers were assigned a shepherd to ensure that the final papers adequately addressed the concerns of the reviewers.