USENIX ATC '21 Call for Papers

Sponsored by USENIX, the Advanced Computing Systems Association.

The 2021 USENIX Annual Technical Conference will take place as a virtual event on July 14–16, 2021.

Important Dates

  • Submissions due: Tuesday, January 12, 2021, 11:59 pm UTC (Note: no abstract registration)
  • Beginning of authors' response period: Tuesday, April 6, 2021
  • Authors' response due: Thursday, April 8, 2021
  • Notification to authors: Monday, April 26, 2021
  • Final paper files due: Thursday, June 3, 2021

Conference Organizers

Program Co-Chairs

Irina Calciu, VMware Research
Geoff Kuenning, Harvey Mudd College

Program Committee

Sangeetha Abdu Jyothi, University of California, Irvine, and VMware Research
Reto Achermann, University of British Columbia
Nitin Agrawal, ThoughtSpot
Amogh Akshintala, Facebook
George Amvrosiadis, Carnegie Mellon University
Raja Appuswamy, EURECOM, Sophia Antipolis
Anirudh Badam, Microsoft Research
Antonio Barbalace, University of Edinburgh
Frank Bellosa, Karlsruhe Institute of Technology
Daniel S. Berger, Microsoft Research
Annette Bieniusa, Technische Universität Kaiserslautern
Laurent Bindschaedler, Massachusetts Institute of Technology
Eleanor Birrell, Pomona College
William J. Bolosky, Microsoft Research
James Bottomley, IBM Research
Sara Bouchenak, INSA Lyon
Nathan Bronson, Rockset
Mihai Budiu, VMware Research
Anton Burtsev, University of California, Irvine
Kevin Butler, University of Florida
Marco Canini, KAUST
Lydia Chen, Delft University of Technology
Young-ri Choi, UNIST (Ulsan National Institute of Science and Technology)
Byung-Gon Chun, Seoul National University
David Cock, ETH Zurich
Jon Crowcroft, University of Cambridge
Heming Cui, The University of Hong Kong (HKU)
Dilma da Silva, Texas A&M University
Alex Daglis, Georgia Institute of Technology
Tudor David, Oracle Labs Zurich
Dave Dice, Oracle Labs
Aleksandar Dragojevic, Microsoft Research Cambridge
Abhinav Duggal, Dell EMC
Alexandra Fedorova, University of British Columbia
Pascal Felber, University of Neuchatel
Anja Feldmann, Max Planck Institute for Software Systems (MPI-SWS)
Pedro Fonseca, Purdue University
Jessie Frazelle, Oxide Computer
Jana Giceva, Technische Universität Munich
Ionel Gog, University of California, Berkeley
Justin Gottschlich, Intel Labs and University of Pennsylvania
Tim Harris, Microsoft
Michio Honda, University of Edinburgh
Yu Hua, Huazhong University of Science and Technology
Zsolt Istvan, IMDEA
Bill Jannen, Williams College
Vasiliki Kalavri, Boston University
Anuj Kalia, Microsoft
Sanidhya Kashyap, EPFL
Aasheesh Kolli, Google and The Pennsylvania State University
Michael Kozuch, Intel Labs
John Kubiatowicz, University of California, Berkeley
Youngjin Kwon, Korea Advanced Institute of Science and Technology (KAIST)
Baptiste Lepers, University of Sydney
Heiner Litz, University of California, Santa Cruz
Yunxin Liu, Microsoft Research Asia
Brandon Lucia, Carnegie Mellon University
Xiaosong Ma, Qatar Computing Research Institute
Jonathan Mace, Max Planck Institute for Software Systems (MPI-SWS)
Carlos Maltzahn, University of California, Santa Cruz
Virendra Marathe, Oracle Labs
Marcelo Martins, Apple
Ali Jose Mashtizadeh, University of Waterloo
Alexander Merritt, BedRock Systems
Michael Mesnier, Intel
Ethan Miller, University of California, Santa Cruz, and Pure Storage
Changwoo Min, Virginia Tech
Adam Morrison, Tel Aviv University
Gilles Muller, INRIA
Kiran-Kumar Muniswamy-Reddy, Oracle
Amy Murphy, Bruno Kessler Foundation
Madan Musuvathi, Microsoft Research
Onur Mutlu, ETH Zurich
Dalit Naor, The Academic College of Tel Aviv-Yaffo
Khanh Nguyen, Texas A&M University
Cristina Nita-Rotaru, Northeastern University
Sam H. Noh, UNIST (Ulsan National Institute of Science and Technology)
Amy Ousterhout, University of California, Berkeley
Roberto Palmieri, Lehigh University
Mangpo Phothilimthana, Google
Peter Pietzuch, Imperial College London
Dan Ports, Microsoft Research
Costin Raiciu, Politehnica University of Bucharest
Michael Reiter, Duke University
Larry Rudolph, Two Sigma
Leonid Ryzhyk, VMware Research
Mahadev Satyanarayanan, Carnegie Mellon University
Jiri Schindler, Tranquil Data
Eric Schkfuza, Amazon
Russell Sears, Apple
Sangeetha Seshadri, IBM Research - Almaden
Liuba Shrira, Brandeis University
Mark Silberstein, Technion—Israel Institute of Technology
Michael Spear, Lehigh University
Scott Stoller, Stony Brook University
Patrick Stuedi, LinkedIn
Ryan Stutsman, University of Utah
Swaminathan Sundararaman, Fusion IO
Steve Swanson, University of California, San Diego
Michael Swift, University of Wisconsin—Madison
Adriana Szekeres, VMware Research
Amy Tai, VMware Research
Vasily Tarasov, IBM Research - Almaden
Eno Thereska, Amazon
Vasileios Trigonakis, Oracle Labs Zurich
Dan Tsafrir, Technion—Israel Institute of Technology
Ymir Vigfusson, Emory University
Nandita Vijaykumar, University of Toronto
Haris Volos, University of Cyprus
Keval Vora, Simon Fraser University
Roger Wattenhofer, ETH Zurich
Hakim Weatherspoon, Cornell University
Ric Wheeler, Facebook
Avani Wildani, Emory University
John Wilkes, Google
Youjip Won, Korea Advanced Institute of Science and Technology (KAIST)
Gerd Zellweger, VMware Research
Lin Zhong, Yale University

Submissions Co-Chairs

Alex Conway, VMware Research
Chris Stone, Harvey Mudd College

Preview Session Co-Chairs

Sangeetha Abdu Jyothi, University of California, Irvine, and VMware Research
Deniz Altinbüken, Google
Dilma Da Silva, Texas A&M University
Aurojit Panda, New York University

Mentoring Co-Chairs

Baris Kasikci, University of Michigan
Amy Ousterhout, University of California, Berkeley
Malte Schwarzkopf, Brown University

Networking Session Co-Chairs

Reto Achermann, University of British Columbia
Zsolt István, IT University of Copenhagen
Adriana Szekeres, VMware Research
Vasily Tarasov, IBM Research - Almaden

Awards Committee

David Cock, ETH Zurich
Dilma Da Silva, Texas A&M University
Michio Honda, University of Edinburgh
Yu Hua, Huazhong University of Science and Technology
Liuba Shrira, Brandeis University


The 2021 USENIX Annual Technical Conference (USENIX ATC '21) seeks original, high-quality submissions that improve and further the knowledge of computing systems, with an emphasis on implementations and experimental results. We are interested in systems of all scales, from small embedded mobile devices to data centers and clouds. The scope of USENIX ATC covers all practical aspects related to systems software, including but not limited to: operating systems; runtime systems; parallel and distributed systems; storage; networking; security and privacy; virtualization; software-hardware interactions; performance evaluation and workload characterization; reliability, availability, and scalability; energy and power management; and bug-finding, tracing, analyzing, and troubleshooting.

We also welcome "experience" submissions that clearly articulate lessons learned, as well as submissions that refute prior published results. We value submissions more highly if they are accompanied by clearly defined artifacts not previously available, including traces, original data, source code, or tools developed as part of the submitted work. We particularly encourage new ideas and approaches.


A good submission will typically: motivate a significant problem; propose a practical solution or approach that makes sense; demonstrate the pros and cons of the latter using sound experimental and statistical evaluation methods; disclose what has and has not been implemented; articulate the new contributions beyond previous work; and refrain from over-claiming, focusing the abstract and introduction sections primarily on the difference between the new proposal and what is already available. Submissions will be judged on relevance, novelty, technical merit, and clarity.

Submissions are expected to avoid committing benchmarking crimes.

Authors of resubmitted work will be given the opportunity to describe in a separate note the changes since the previous submission(s). While this description is optional, authors are encouraged to write one, as it helps reviewers who may have reviewed a previous draft of the work to appreciate any improvements to currently submitted work. Such a description should be included as part of the supplemental material for the paper.

Papers must be submitted before the aforementioned submission deadline via the USENIX ATC '21 submission site. Submissions must be in PDF format. No extensions will be given. There is no separate deadline for abstract registration. Submissions must strictly adhere to the policies specified below. By submitting, you agree that if the paper is accepted, at least one of the authors will attend the conference. Virtual presence can be acceptable if conditions prevent in-person attendance. Submissions accompanied by nondisclosure agreement forms will not be considered.

Submission Type: Full vs. Short

USENIX ATC accepts both full and short submissions. Short submissions are limited to roughly half the space of full-length submissions. Both types are reviewed to the same standards and differ primarily in scope. A short paper is not like a workshop "position" paper—it presents a complete idea that does not require full length to be appreciated. The idea should be concisely formulated and evaluated, and conclusions should be drawn from it, just like in a full-length paper. The program committee may, in rare cases, decide to accept a full submission on the condition that it is cut down to fewer pages. Short papers will be included in the proceedings and presented at the conference like full papers during a slightly shorter time slot.


Submissions must contain original unpublished material that is not under review at any other forum, including journals, conferences, and workshops with proceedings. Submissions that extend your own previous work—in a significant way—are welcome, but you must explain the differences between your current USENIX ATC submission and your prior work. You should also relate your current USENIX ATC submission to relevant submissions of your own that are simultaneously under review for this or other venues. The next section discusses how to do so while maintaining anonymity.

Simultaneous submission of the same work to multiple venues, submission of previously published work, or other violations of the above policies constitute plagiarism, dishonesty, or fraud. USENIX prohibits these practices and may take action against authors who have committed them; see the USENIX Conference Submissions Policy for additional details.


USENIX ATC '21 will employ double-blind reviewing, keeping author identities concealed from reviewers. You must therefore make a good-faith attempt to anonymize your submissions by avoiding identifying yourself or your institution, either explicitly or by implication, e.g., through references, acknowledgments, online repositories that are part of the submission, or direct interaction with committee members. Do not say "reference removed for blind review." When it is necessary to cite your own studies, there are only two possibilities: cite them (1) as written by a third party (preferable), or (2) as uploaded anonymized supplemental material (see below). This guideline applies in particular to any of your workshop papers that are being extended by your current USENIX ATC submission. Related submissions of your own that are simultaneously under review or awaiting publication at other venues should typically opt for the second option. Publication as a technical report or in an online repository does not constitute a violation of this policy because those works are not peer-reviewed. Papers that are not properly anonymized may be rejected without review.

Public disclosure of excerpts from submitted papers and/or reviews (e.g., those received during the rebuttal process) prior to the announcement of official decisions constitutes a violation of the anonymity policy. All questions or comments about the reviews should be sent exclusively to

Anonymized Supplemental Material

Supplemental material may be submitted as a single-but-separate anonymized file without page limit. Note that the reviewers are not required to read such material or consider it in making their decision. Any material that should be considered to properly judge the paper for acceptance or rejection is not supplemental and will apply to the page limit.

Declaring and Avoiding Conflicts

When registering a submission, all its co-authors must provide information about conflicts with the USENIX ATC '21 program committee (PC) members and extended review committee (ERC) members. You are conflicted with a member if: (1) you are currently employed at the same institution, have been previously employed at the same institution within the past two years (2019 or later), or are going to begin employment at the same institution; (2) you have a past or present association as thesis advisor or advisee (no time limit); (3) you have collaborated on a project, publication, grant proposal, or editorship within the past two years (2019 or later); or (4) you have spousal or first-degree relative relations.

Do not declare a conflict if you discussed your submission with a PC or ERC member before the USENIX ATC '21 PC and ERC lists were publicized. Do not declare a conflict merely because you wish to avoid a review from a specific committee member; such unethical behavior may result in immediate rejection. All conflicts will be reviewed to ensure the integrity of the reviewing process.

Authors and others are prohibited from directly or indirectly communicating with any ATC '21 PC or ERC member about any potentially submitted paper. All inquiries should be made exclusively to Violations of these guidelines may incur remedies as stipulated in the USENIX Conference Submissions Policy.


Full submissions must not exceed 11 pages, and short submissions must not exceed 5 pages, including all text, figures, tables, footnotes, appendices, etc. Bibliographic references, however, are not included in the page limit. The reviewers will value conciseness, so if you can describe your work with fewer pages than the limit, please do so. Because references do not count against the page limit, they should not be formatted using a smaller font, and the names of all co-authors should be specified. Papers not meeting this requirement may be rejected without a review.

Use US letter paper size, with all text and figures fitting inside a 7" x 9" (178 mm x 229 mm) block centered on the page, using two columns separated by 0.33" (8 mm) of whitespace.

Use a 10-point font (typeface Times Roman, Linux Libertine, etc.) on 12-point (single-spaced) leading. Graphs and figures can use colors but should be readable when printed in monochrome, without magnification. All pages should be numbered, and references within the paper should be hyperlinked. Labels, captions, and other text in figures, graphs, and tables must use reasonable font sizes that, as printed, do not require extra magnification to be legible. Submissions that violate any of these restrictions will not be reviewed. No extensions will be given for reformatting.

USENIX’s LaTeX style files and Word templates are available on the USENIX templates page.

Early Rejection Notifications

USENIX ATC '21 will conduct its reviews in multiple rounds. Papers that pass a given round are assigned additional reviewers to help make a sound decision for each paper. However, some papers may be rejected in an early round. USENIX ATC '21 will send early rejection notifications to such authors at least a month ahead of the date that all remaining notifications are sent (acceptances and additional rejections). These decisions are final and authors of early rejected papers will not be asked to provide a rebuttal (see below). Authors who receive an early rejection notification will not receive another notification later on. Authors of rejected papers at this early stage are therefore free to read their paper's reviews and use the extra time to consider revising and resubmitting the work to a future conference.

Authors' Response Period

USENIX ATC '21 will provide an opportunity for authors to respond to reviews prior to final consideration of the submissions at the program committee meeting according to the schedule detailed above. Authors must limit their response rebuttal to: (1) correcting factual errors in the reviews; and (2) directly addressing questions posed by reviewers. Rebuttals should be limited to clarifying the submitted work. In particular, rebuttals must not include new experiments or data, nor describe additional work completed since submission, nor make promises of additional work to be performed. Rebuttals are optional. Rebuttals are limited to no more than 500 words; excessively long rebuttals might result in the paper's rejection.


All submissions will be treated as confidential prior to publication on the USENIX ATC '21 website. Rejected submissions will be permanently treated as confidential.

Accepted Papers

Submissions selected by the program committee will be conditionally accepted, subject to revision and approval by a program committee member acting as a shepherd. Accepted (long and short) papers will be allowed one additional page in the proceedings. One author of each accepted paper will present the work at the conference in a designated time slot.

By default, all accepted papers will be made available online to registered attendees before the conference. If your accepted paper should not be published prior to the event, please notify before the final paper deadline. Accepted papers, however, will be made available online to everyone beginning on the first day of the conference.

If the conference registration fee will pose a hardship for the presenter of the accepted paper, please contact the Conference Department at If your paper is accepted and you need an invitation letter to apply for a visa to attend the conference, please email as soon as possible. (Visa applications can take at least 30 working days to process; recently, visas have often taken significantly longer.) Please identify yourself as a presenter and include your mailing address in your email.


Please direct any questions to the program co-chairs at or to the USENIX office at