This special section explores new foundational and translational research toward enabling exascale computing for emerging scientific and societal challenges. Exascale computing (1,000 times more powerful than petascale) is defined as the capability to perform 1018 operations per second. Productively harnessing such a scale of processing, storage, and networking capabilities for diverse domains—including high-performance computing (HPC) simulations, artificial intelligence (AI), and extreme data-driven computing—relies on not only revitalizing existing parallel and distributed computing technologies but also innovating new solutions. Hence, topics related to applications, programming environments, runtimes, libraries, innovative algorithms, domain-specific frameworks, systems architecture, performance analysis, data processing, and networking technologies, among others, are within the scope of research encompassing parallel, distributed, and heterogeneous systems for exascale.
Paths to exascale have been laid out across various national and international funding programs that are largely characterized by multidisciplinary research spanning from exascale centers of excellence for domain sciences to the development of operational IT infrastructure at scale. Characteristic features of the IT infrastructure technologies include accelerated processors, memory and storage hierarchies, smart networks for workflows, and storage for HPC and AI, among others. Software technologies and applications focus on developing next-generation scalable algorithms and frameworks, enabling performance portability, and enhancing productivity of complex parallel and distributed workflows.
Contributions highlighting fundamental advances in software technologies, hardware, and applications over the current state-of-the art will be considered. Submissions addressing challenges that are unique to exascale computing, from application and algorithm development to reliability and availability of operational IT infrastructure, are within the scope of the special section. Topics of interest include, but are not limited to:
- Efficient hardware for exascale science
- Sustainable software technologies for exascale computing, with emphasis on integration, interoperability, and hardware-software co-design
- Scalable applications (computational science/engineering, data analytics, AI) and algorithms
- Performance measurement, modeling, and tools for exascale
- AI for HPC / HPC for AI
- Scalable IO for HPC and AI workloads
- Libraries and runtimes for exascale
- Systems, compilers, programming models, and languages at scale
- Testing, tuning, debugging, and profiling applications at scale
- Visualization at scale
- Domain-specific libraries and frameworks
- Parallel and distributed workflows
- Availability, reliability, resilience, and fault-tolerance
- Resource management and scheduling
About TPDS special sections
TPDS has recently started a new initiative called “special sections.” Compared with regular submissions to TPDS, special sections have some differences: (1) submissions are focused on special topics of interest (similar to special issues); (2) special sections have fixed deadlines for submission and notifications; and (3) special sections have a standing committee of reviewers similar to conferences.
The timeline for the submission and review process is as follows. All deadlines are 23:59 (11:59pm) anywhere on earth (https://www.worldtimeserver.com/time-zones/aoe/).
- Submission deadline: February 24, 2021
– Please be sure to choose the tag “SS on Innovative R&D toward the Exascale Era’’ when submitting your paper to the ScholarOne system.
- Extended submission deadline: February 24, 2021 (no further extensions)
- First-round review notification: April 7, 2021 (6 weeks for reviews)
- Notification would be one of ACCEPT, REJECT, MAJOR REVISIONS, or MINOR REVISIONS
Round 2a (only for papers that get a minor revision in Round 1):
- Second-round submission deadline: April 21, 2021 (2 weeks for re-submission)
- Second-round review notification: May 5, 2021 (2 weeks for reviews)
- Notification would be one of ACCEPT or REJECT
Round 2b (only for papers that get a major revision in Round 1):
- Second-round submission deadline: May 5, 2021 (4 weeks for re-submission)
- Second-round review notification: June 2, 2021 (4 weeks for reviews)
- Notification would be one of ACCEPT, REJECT, or MINOR REVISIONS
Round 3 (only for papers that got a minor revision in Round 2b):
- Third-round submission deadline: June 16, 2021 (2 weeks for re-submission)
- Third-round review notification: June 30, 2021 (2 weeks for reviews)
- Notification would be one of ACCEPT or REJECT
Submissions to the special section will be received as TPDS regular papers (survey and comment-style papers are not allowed). Please check submission instructions (including page limit, manuscript format, and author templates) on the TPDS Author Information page.
- Please note that review versions of the papers are limited to 12 pages, and overlength page charges are only for the final versions of the papers. Papers longer than 12 pages will not be considered.
- The TPDS reproducibility pilot is not available for submissions to this special section.
- Supplementary materials will not be considered for submissions to this special section.
- Submissions are *NOT* double blind. Authors can disclose their names, and they can freely cite their previous work without referring to it in a third-party fashion.
Authors can submit papers until the deadline through ScholarOne. Once you start the submission process, in Step 1 of the process, you’ll be asked to pick a “Type” for the paper. Please pick “SS on Innovative R&D toward the Exascale Era.”
Extensions of prior papers
All papers need to have sufficient new content and contributions (see examples of extension material below) to warrant a separate publication. While the specific amount of acceptable new content is subjective and depends on the reviewer, we estimate that most reviewers expect new material that represents novel research contributions beyond the original publication. Acceptance of the paper is based on this new content and its contributions. Old content from previous conference papers is mainly to help reviewers understand the context. Old content should be clearly cited from the original source. Furthermore, any content used verbatim from previous publications should be appropriately quoted and cited to avoid self-plagiarism.
Authors submitting an extension of a prior publication should clearly respond to the following questions:
1. What are the novel contributions of the submitted paper (beyond the authors’ previous publication(s))?
2. What is the new content and in which sections does this content appear in the submission?
3. How do the contributions (and content) build on the previous published material?
Examples of Extension Material:
Acceptable new content and contributions: new conceptual extensions, experiments that provide new insights, and new theoretical analysis and/or proofs supporting empirical results
Allowable but insufficient content and contributions: extension to background and/or related work; elaboration on the same points in the introduction, observations, and conclusions; additional figures/plots that merely illustrate already-published content; and additional experimental results without new insights
Unacceptable content and contributions: simple union of content from multiple prior publications
Sadaf Alam (Swiss National Supercomputing Centre, ETH Zürich)
Lois Curfman McInnes (Argonne National Laboratory)
Kengo Nakajima (University of Tokyo, RIKEN Center for Computational Science)
- Vassil Alexandrov, Hartree Centre – STFC
- Rosa M. Badia, Barcelona Supercomputing Center
- Suren Byna, Lawrence Berkeley National Laboratory
- Florina Ciorba, University of Basel
- Guillaume Colin de Verdière, French Alternative Energies and Atomic Energy Commission
- Benjamin Dudson, University of York
- Haohuan Fu, Tsinghua University
- Timothy Germann, Los Alamos National Laboratory
- Yanfei Guo, Argonne National Laboratory
- Georg Hager, University of Erlangen-Nuremberg
- Weicheng Huang, National Center for High-performance Computing, Taiwan
- Takeshi Iwashita, Hokkaido University
- Heike Jagode, University of Tenessee, Knoxville
- Jaejin Lee, Seoul National University
- Seyong Lee, Oak Ridge National Laboratory
- Xiaoye (Sherry) Li, Lawrence Berkeley National Laboratory
- Kenneth Moreland, Sandia National Laboratories
- Kenji Ono, Kyushu University
- Tapasya Patki, Lawrence Livermore National Laboratory
- Tiago Quintino, European Centre for Medium-Range Weather Forecasts
- Siva Rajamanickam, Sandia National Laboratories
- Katherine Riley, Argonne Leadership Computing Facility
- Kentaro Sano, RIKEN Center for Computational Science
- Kento Sato, RIKEN Center for Computational Science
- Olaf Schenk, Università delia Svizzera italiana
- Martin Shulz, Technical University of Munich
- Miroslav Stoyanov, Oak Ridge National Laboratory
- Estela Suarez, Juelich Supercomputing Centre
- Hari Subramoni, Ohio State University
- Shinji Sumimoto, Fujitsu Laboratories
- Guangming Tan, Chinese Academy of Sciences
- Francois Tessier, Inria
- Nicholas Wright, National Energy Research Scientific Computing Center (NERSC)
- Chao Yang, Peking University
- Rio Yokota, Tokyo Institute of Technology
- Stefano Zampini, King Abdullah University of Science and Technology (KAUST)
- Amelie Chi Zhou, Shenzhen University