Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems

Abstract

Welcome to the seventeenth edition of the ASPLOS conference series, and the first to be held outside of North America. We have assembled what we believe to be an outstanding technical program, and are delighted to be presenting it in the historic chambers of the Royal Society in the UK. The program 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 172 full paper submissions, which was 13% higher than last year's 152, and 5% lower than the record of 181 set in 2010. 14 submissions had program committee members as co-authors. Once again, the dominant technical theme was parallelism: 70% of both the submitted and accepted papers explicitly indicated a technical keyword specific to parallel processing. The single most popular keyword was "multicore systems," selected by 35% of both the submitted and accepted papers. Interestingly, not one of the 172 submissions selected "VLSI or process technology." There was a nice mixture of submissions across operating systems (34%), compilers and programming languages (28%), and core topics in computer architecture (37%), with 23% of submissions spanning more than one of these. (Most submissions had something to do with computer architecture; the characterization of "core areas" is somewhat arbitrary.) As in recent years, we employed two rounds of reviewing. An External Review Committee, preselected by the Program Chair, assisted in round one. All submissions received at least three round one reviews. Based on these, we eliminated 71 papers whose average overall score was below 3.5 (on a scale of 1-6), and whose maximum score was below 5 (i.e., no better than "weak accept"). The remaining 101 papers received two additional (PC-only) reviews in round two. This process allowed the program committee to focus the bulk of its attention on papers with a significant chance of being accepted. The typical member of the External Review Committee completed six reviews; the typical Program Committee member did 14. Almost all reviews were completed by early October, at which point authors had several days to compose a formal response, if they desired (most did). After this rebuttal period, PC members took the author comments into account as they discussed the papers online and, in some cases, updated their scores accordingly. The PC gathered in Rochester, NY, for a full-day meeting on October 20th, 2011. 74 papers were discussed at the meeting. PC authors stepped out of the room for discussion of their papers; those with conflicts of interest remained in the room, but did not participate in discussion. Papers on which the Program Chair had a conflict of interest (4 in number) had been reviewed in a separate process managed by Jim Larus, and were discussed when the Chair was not present. At the end of the day, 37 papers were accepted for presentation at the conference, for an acceptance rate of 21.5% --- a slightly larger number than last year, but almost the same percentage. Four of the accepts have PC members as co-authors. Nine papers were assigned a "shepherd" to make sure that final versions addressed issues (not necessarily weaknesses) of concern to the program committee. The logistics behind organizing this conference have been handled by the tireless effort of a team of volunteers: Luis Ceze (University of Washington), Alexandra Fedorova (Simon Fraser University), Steven Hand (University of Cambridge), Timothy Jones (University of Cambridge), Paul Kelly (Imperial College), Mikel Luján (University of Manchester), Robert Mullins (University of Cambridge), Onur Mutlu (Carnegie Mellon University), and Derek Murray (Microsoft Research). Each member of this team played an important role in making ASPLOS a success. The ASPLOS Steering Committee gave us valuable assistance over the last year, and Todd Mowry (CMU) was particularly generous with his advice from ASPLOS 2010 and ASPLOS 2011. In addition, Jean Bacon (University of Cambridge), Andrew Herbert, Graham Hutton (University of Nottingham), and Joe Sventek (University of Glasgow) provided advice on organizing a conference in the UK. As always, the support and guidance of the ACM staff was very valuable.