ISCA 2026

Guideline on the Use of Generative AI Tools for Authors

We refer authors to ACM's and IEEE's policies on authorship: https://www.acm.org/publications/policies/frequently-asked-questions and https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/submission-and-peer-review-policies/#ai-generated-content, respectively.

1. Authors are allowed to use generative AI tools to prepare their papers with explicit disclosure on how the generative AI tools are used in the Acknowledgement section.
2. Generative AI tools cannot be listed as an author.
3. All the co-authors take full responsibility for the contents of their paper.

The use of AI systems for editing and grammar enhancement is common practice and, as such, is generally outside the intent of the above policy. In this case, disclosure as noted above is not required, but recommended.

Guideline on the Use of Generative AI Tools for Reviewers

We refer reviewers to ACM's policies on reviewers: https://www.acm.org/publications/policies/peer-review-faq. Disclosing submitted paper contents (even indirectly in the form of a draft of a paper review) to a non-confidential AI tool puts unpublished work in jeopardy and reviewers could be held liable for breaching confidentiality. Furthermore, the expectation for program committee members has always been to destroy copies of paper submissions they have reviewed. This, however, would be challenging to enforce when Generative AI / LLM tools are used. Reviewers must therefore not use Generative AI / LLM tools to assist in any way whatsoever with their reviews.

New Policies Regarding Expected Reviewer Service for Authors

To keep high review quality and ensure a productive and pleasant reviewer experience in anticipation of increasing paper submissions, for ISCA-53, we are initiating two new expectations for authors.

PC Service for Authors Submitting More than 6 Abstracts

Any senior author (i.e., holding a PhD or having equivalent level of seniority) registering more than 6 abstracts (regardless of whether any of those abstracts are later withdrawn) may be called upon to serve on the PC and cannot decline. Another other senior author may be nominated in place. Final decisions on this matter will be at the discretion of the PC chairs.

Reserve Reviewers

To prepare for the possibility of a higher volume of submissions, we expect at least one senior author (as defined above) per paper must register as a reserve reviewer (unless exempt under the criteria below). [We thank the OOPSLA program chairs for piloting this practice!]

The goal of this policy is to uphold the high standard of reviews within the TCCA/SIGARCH/SIGMICRO/TCMM community. To achieve this, we must ensure manageable review loads, prevent burnout, and encourage reviewers to stay engaged for future rounds. High-quality reviews are one of the community’s greatest assets, playing a crucial role in elevating the quality of research for everyone.

Our hope is that these reserve reviewers won’t be needed at all! They will only be called upon as ad hoc reviewers if our projections fall significantly short. Even in that case, their review load will be far lighter than that of LPC members, and we will do our best to assign papers that closely match expertise. Those selected to serve as a reviewer will be acknowledged in the proceedings.

When registering a paper in HotCRP, the form will include a field for the designated reserve reviewer. After the final paper submission, we will notify reserve reviewers if their reviewing services will be needed, and they will be expected to enter their areas of expertise in HotCRP in a timely fashion and update their COIs.

We define “senior” authors as those who completed their PhD, or equivalent industry experience. A paper is exempt from the reserve reviewer policy if:

• The paper has no senior authors.
• At least one senior author is already on the program committee.
• At least one senior author is subject to the 6-abstract criterion above.
• Every senior author of the paper satisfies one or more of these criteria:
  • Has never published in a conference sponsored by TCCA, TCMM, SIGARCH, or SIGMICRO.
  • Is (co)chairing a TCCA, TCMM, SIGRACH, or SIGMICRO conference with 150 or more submissions last year, this year, or next year.
  • Has some other exceptional circumstance that didn’t prevent writing the paper but prevents doing any reviewing. This must be cleared at least three days before submission with the PC Chairs.

It is okay for the same person to serve as the reserve reviewer for more than one paper. Please enter their information for each such paper (preferably identically). For cases in which a paper is exempt according to the above criteria, please enter “exempt” in the reserve reviewer field.

Note that these policies mean that authorship cannot be changed after abstract registration and we require paper titles to be finalized at the paper registration time. We hope this will reduce abuse of the abstract registration process to register ghost/placeholder papers.

Topics

Papers are solicited on a broad range of topics, including (but not limited to):

• Processor, memory, and storage systems architecture
• Parallelism: instruction, thread, data, multiprocessor
• Datacenter-scale computing
• IoT, mobile, edge, and embedded architecture
• Verification, testing, and correctness
• Interconnection networks, routers, and network interface architectures
• Power and energy
• Sustainable computing
• Architectures for emerging applications including machine learning and bioinformatics
• Architectural support for programming languages or software development
• Architectural support for interfacing with accelerators
• Architectural support for security, virtual memory, and virtualization
• Dependable processor and system architecture
• Architectures for emerging technologies including novel circuits, memory technologies, etc.
• Quantum computer architecture
• Architecture modeling, simulation methodologies, and tools
• Evaluation and measurement of real computing systems
• Human factors and user studies

Paper Submission Instructions

Guidelines for Determining Authorship

IEEE guidelines dictate that authorship should be based on a substantial intellectual contribution. It is assumed that all authors have had a significant role in the creation of an article that bears their names. In particular, the authorship credit must be reserved only for individuals who have met each of the following conditions:

1. Made a significant intellectual contribution to the theoretical development, system or experimental design, prototype development, and/or the analysis and interpretation of data associated with the work contained in the article;
2. Contributed to drafting the article or reviewing and/or revising it for intellectual content; and
3. Approved the final version of the article as accepted for publication, including references.

A detailed description of the IEEE authorship guidelines and responsibilities is available in the IEEE Ethical Requirements . Per these guidelines, it is not acceptable to award honorary authorship or gift authorship. Please keep these guidelines in mind while determining the author list of your paper.

Declaring Authors

Declare all the authors of the paper upfront. Addition/removal of authors once the paper is accepted will have to be approved by the program chairs, since it potentially undermines the goal of eliminating conflicts for reviewer assignment.

Areas and Topics

Authors should indicate these areas on the submission form as well as specific topics covered by the paper for optimal reviewer match. If you are unsure whether your paper falls within the scope of ISCA, please check with the program chairs — ISCA is a broad, multidisciplinary conference and encourages new topics.

Declaring Conflicts of Interest

Authors must register all their conflicts on the paper submission site. Conflicts are needed to ensure appropriate assignment of reviewers. If a paper is found to have an undeclared conflict that causes a problem OR if a paper is found to declare false conflicts in order to abuse or “game” the review system, the paper may be rejected.

Please declare a conflict of interest with the following people for any author of your paper. A conflict occurs in the following cases:

1. Between advisors and advisees, forever.
2. Between family members, forever (if they might be potential reviewers).
3. Between people who have collaborated in the last FOUR years. This collaboration can consist of a joint research or development project, a joint paper, or when there is direct funding from the potential reviewer (as opposed to company funding) to an author of the paper. Co-participation in professional activities, such as tutorials or studies, is not cause for conflict. When in doubt, the author should check with the program chairs.
4. Between people from the same institution or who were in the same institution in the last FOUR years.
5. Between people whose relationship prevents the reviewer from being objective in his/her assessment.

"Service" collaborations such as co-authoring a report for a professional organization, serving on a program committee, or co-presenting tutorials, do not themselves create a conflict of interest. Co-authoring a paper that is a compendium of various projects with no true collaboration among the projects does not constitute a conflict among the authors of the different projects.

On the other hand, there may be others not covered by the above with whom you believe a COI exists; for example, an ongoing collaboration which has not yet resulted in the creation of a paper or proposal. Please report such COIs; however, you may be asked to justify them. Please be reasonable. For example, you cannot declare a COI with a reviewer just because that reviewer works on topics similar to or related to those in your paper. The program chairs may contact co-authors to explain a COI whose origin is unclear.

Most reviews will be solicited among the members of the program committee and the external review committee but other members from the community may also write reviews. Please declare all your conflicts (not just restricted to the PC and ERC) on the submission form. When in doubt, contact the program chairs.

Concurrent Submissions and Workshops

By submitting a manuscript to ISCA 2026, the authors guarantee that the manuscript has not been previously published or accepted for publication in a substantially similar form in any conference, journal, or the archived proceedings of a workshop (e.g., in the ACM/IEEE digital library) — see exceptions below. In addition, it is important to note that ACM/IEEE prohibit authors from reusing their own text or figures without attribution; doing otherwise either violates rules regarding plagiarism or anonymity.

The authors also guarantee that no paper that contains significant overlap with the contributions of the submitted paper will be under review for any other conference or journal or an archived proceedings of a workshop during the ISCA 2026 review period. Violation of any of these conditions will lead to rejection.

The only exceptions to the above rules are for the authors' own papers in (1) workshops without archived proceedings such as in the ACM/IEEE digital library (or where the authors chose not to have their paper appear in the archived proceedings), or (2) venues such as IEEE CAL or arXiv where there is an explicit policy that such publication does not preclude longer conference submissions. In all such cases, the submitted manuscript may ignore the above work to preserve author anonymity. This information must, however, be provided on the submission form — the PC chair will make this information available to reviewers if it becomes necessary to ensure a fair review.

If you have already put your manuscript on arXiv, in the interest of double blind review, use a different title for the version you submit to ISCA and be aware of these rules regarding reuse of text. As always, if you are in doubt, it is best to contact the program chairs.

Finally, the ACM Plagiarism Policy and the IEEE Plagiarism Policy cover a range of ethical issues concerning the misrepresentation of other works or one's own work.

Additional Rules for Authors

Authors MUST:

1. Abide by the ACM code of ethics and the IEEE code of ethics.
2. Abide by the criterion for authorship laid out by ACM and IEEE. Authorship is reserved only for individuals making substantial intellectual contributions. Gifting authorship is strictly prohibited.
3. List all legitimate CoIs and only legitimate CoIs. Asking someone for feedback on a draft of the paper or discussing the idea with someone does not create a CoI.
4. Abide by the Concurrent Submission Policy (see above).
5. Anonymize their submission for double-anonymous reviewing. This means not having any author names on any submitted documents, including in PDF metadata, except in the space provided on the submission form. If referring to one’s work, authors must do so in the third person and include a full citation for the work in the bibliography. References must not be omitted or anonymized.
6. Fully anonymize any link to artifacts produced by them concerning the submission (e.g., GitHub repository). Remove any links to artifacts that cannot be fully anonymized.
7. Report any allegations of submission or reviewing misconduct to the Program Chairs, who has the responsibility to follow up on them. The only exception is if the complaint is about the Program Chairs; in this case, the Steering Committee should be contacted.
8. Make no assumptions as to whether a particular paper represents a “community paper” and whether its co-authors are or are not conflicted with each other. The decision rests entirely with the Program Chairs, who must be either petitioned explicitly or will be presented with the choice through a conflict-tracking tool. A community paper is defined as a paper presenting a survey, compendium, tool, or artifact to which multiple authors contribute without engaging in an actual project collaboration (e.g., a paper describing an open-source software framework to which the authors have contributed different modules).

Authors MUST NOT:

1. Contact reviewers or PC members about any submission, including their own. This includes asking about the outcome of a submission following the online discussion period and the PC meeting. Similarly, authors are not allowed to ask another party to contact the reviewers on their behalf.
2. List potential reviewers as conflicts of interest based solely on fear or suspicion of a negative bias. If an author believes there exists clear and articulable evidence of a negative bias against their work from a potential reviewer, the author may contact the Program Chairs and present such evidence in support of their case. The Program Chairs must acknowledge receipt and may solicit additional information. The Program Chairs are not required to notify the authors of any decision taken.
3. Attempt to sway a reviewer to review any paper positively or negatively.
4. Contact reviewers or PC members requesting any type of information about the reviewing process, either in general or specifically about submitted papers.
5. Disclose the content of reviews for one’s paper publicly before the results are announced. Any grievances should be directed to the Program Chairs.

Organizers

• General Co-Chairs: James Tuck (North Carolina State University) and Huiyang Zhou (North Carolina State University)
• Program Co-Chairs: Kevin Skadron (University of Virginia) and Carole-Jean Wu (Meta)
• Program Chair (Industry Track): Brad Beckmann (AMD)