- 4 March: Slides from the talks are now online, at the workshop program page.
- 19 February: Information about invited talks by Dean Tullsen and Brian Lewis is now online.
- 13 February: The workshop program is now online.
- 23 December: The notification date is now February 3, 2014 (a bit earlier) to be compatible with the ASPLOS travel grant deadline
- 5 December: The submission site is now open!
Introduction
Simplifying parallel programming and making parallel programs execute correctly are important goals. Support for programmability, correctness and reliability, such as support for determinism and failure tolerance, has moved us toward these goals. We have seen tremendous progress, but deciding what support to provide for which properties remains an active research area with many open questions: What are the performance and programmability trade-offs for providing a particular property? What is the right balance between support for finding or fixing bugs and preventing them with more restrictive programming models? How should we handle programs that violate safety properties for performance or expressivity? How can we accommodate heterogeneous parallel computers? What is the role of each layer of the system stack? These questions are increasingly urgent as more computing goes parallel, from sensors to data centers.
The Workshop on Determinism and Correctness in Parallel Programming (WoDet) is an inclusive, across-the-stack forum to discuss the role of a wide range of correctness properties in parallel and concurrent programming. While determinism is an important theme, the scope of the workshop includes other correctness properties for parallel programs and systems. The workshop will be a full day event with invited talks and technical sessions for short peer-reviewed papers discussing ideas, positions, or preliminary research results.
Topics
In addition to answers to the questions above, topics of interest include:
- Language extensions for disciplined parallelism, e.g., determinism, structured parallelism
- Architecture, OS, runtime, and compiler support for parallel program correctness
- Concurrent program debugging techniques
- New properties of parallel programs
- Limit studies and empirical studies of the cost of safety properties
- Studies of the applicability of correctness properties in parallel programs and algorithms
- Techniques for avoiding/tolerating failures due to concurrency bugs
- Real-world experience with safe parallel programming models, systems, or tools
Important Dates
- Submission deadline: Friday January 10, 2014 at 11:59pm US Eastern Time
- Notification: Monday February 3, 2014
- Final version: Monday February 17, 2014 at 11:59pm US Eastern Time
- Workshop: Sunday March 2, 2014
Submission
Authors are invited to submit original and unpublished work that exposes a new problem, advocates a specific solution, or reports on actual experience. Papers should be submitted using the standard two-column ACM SIG proceedings or SIG alternate template, and are limited to 6 pages (including figures, tables and references). Submissions do not need to be blind, but the authors can choose to do so.
Final papers will be made available to participants electronically at the meeting, but to facilitate resubmission to more formal venues, no archival proceedings will be published, and papers will not be sent to the ACM Digital Library. Authors will be given the option of having their final paper accessible from the workshop website.
Organization
- Brandon Lucia, Microsoft Research
- Joe Devietti, University of Pennsylvania
Program Committee
- Eddie Aftandilian, Google
- Emery Berger, University of Massachusetts, Amherst
- Joe Devietti, University of Pennsylvania
- Jakob Eriksson, University of Illinois at Chicago
- Shan Lu, University of Wisconsin-Madison
- Brandon Lucia, Microsoft Research
- Santosh Nagarakatte, Rutgers University
- Mark Oskin, University of Washington
- Michael Scott, University of Rochester
- Serdar Taşiran, Koç University
- Martin Vechev, ETH Zürich
- Eran Yahav, Technion