ScalAH22: 13th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Heterogeneous Systems
Novel hybrid scalable scientific algorithms are needed with the advent of
variety of novel accelerators including graphics processing units (GPUs),
field-programmable gate arrays (FPGAs) as well as with the growth of the size
of quantum computing devices and neuromorphic chips and various artificial
intelligence (AI) specific processors. This myriad of devices requires an
unified hybrid approach that allows efficient and scalable hybrid approaches
combining classical and novel computing paradigms to be implemented at scale.
These extreme-scale heterogeneous systems require novel scientific algorithms
to hide the complexity, hide network and memory latency, have advanced
communication, and have no synchronization points where possible. With the
advent of AI in the past few years the need of such scalable mathematical
methods and algorithms for such hybrid architectures that are able to handle
data and compute intensive applications at scale becomes even more important.
Scientific algorithms for multi-petaflop and exa-flop systems also need to be
fault tolerant and fault resilient, since the probability of faults increases
with scale. Resilience at the system software and at the algorithmic level is
needed as a crosscutting effort. Key science applications require novel
mathematics and mathematical models and system software that address the
scalability and resilience challenges of current- and future-generation
extreme-scale heterogeneous high performance computing (HPC) systems.
Submission Guidelines
Authors are invited to submit manuscripts in English structured as technical
papers at a length of at least 6 letter size (8.5in x 11in) pages and not
exceeding 8 pages, including figures, tables, and references using the IEEE
format for conference proceedings. Reference style files are available at
http://www.ieee.org/conferences_events/conferences/publishing/templates.html.
Submitted papers must represent original unpublished research that is
not currently under review for any other conference or journal. Papers not
following these guidelines will be rejected without review and further action
may be taken, including (but not limited to) notifications sent to the heads of
the institutions of the authors and sponsors of the conference. Submissions
received after the due date, exceeding length limit, or not appropriately
structured may also not be considered. Papers should be submitted electronically
at https://submissions.supercomputing.org.
All manuscripts will be peer-reviewed and judged on correctness,
originality, technical strength, and significance, quality of presentation, and
interest and relevance to the workshop attendees. Accepted papers will be
published with the IEEE Computer Society in the IEEE Xplore Digital Library.
At least one author of an accepted paper must register for and present the paper
at the workshop (in-person live, remote live or pre-recorded video):
https://sc22.supercomputing.org/submit/in-person-presentations/.
Authors may contact the workshop program chair, Christian
Engelmann at engelmannc@ornl.gov,
for more information.
Reproducibility Initiative
As part of a major initiative that aims to increase the level of reproducibility
and replicability of results, ScalAH22 invites authors of technical papers to
submit optional appendix information that can promote better reproducibility of
computational results. Submitted Artifact Description (AD) and Artifact
Evaluation (AE) appendices will follow the SC22 conference model and review
process. Learn more about the Reproducibility Initiative.
Important Dates
- Notification of acceptance: September 13, 2022
- Pre-recorded video submission (firm): September 30, 2022
- Final paper submission (firm): October 14, 2022
- Workshop/conference early registration: October 14, 2022
- Workshop: November 13, 2022
Topics
Topics of interest include, but are not limited to:
- Novel scientific algorithms that improve performance, scalability, resilience and power efficiency on hybrid architectures
- Porting scientific algorithms and applications to hybrid and heterogeneous architectures (with different accelerators, hybrid classical/quantum, classical/AI accelerated, etc.)
- Crosscutting approaches (system software and applications) in addressing scalability challenges on hybrid architectures
- Naturally fault tolerant, self-healing or fault oblivious scientific algorithms for hybrid architectures
- Methods and algorithms for silent data corruption with systems at scale
- Ensuring algorithms scalability over various accelerator partitions/islands, and taking advantage where the system itself has different kinds of specialized compute nodes
Workshop Chairs
- Vassil Alexandrov, Hartree Centre, Science and Technology Facilities Council, UK
- Jack Dongarra, University of Tennessee, Knoxville, USA
- Al Geist, Oak Ridge National Laboratory, USA
- Dieter Kranzlmueller, Leibniz Supercomputing Centre and Ludwig-Maximilians-University Munich, Germany
- Ivano Tavernelli, IBM Zurich, Switzerland
Program Committee
- Hartwig Anzt, University of Tennessee, Knoxville, USA, and Karlsruher Institute for Technology (KIT), Germany
- Rick Archibald, Oak Ridge National Laboratory, USA
- Hans-Joachim Bungartz, Technical University of Munich, Germany
- James Elliott, Sandia National Laboratories, USA
- Nahid Emad, University of Versailles SQ, France
- Wilfried Gansterer, University of Vienna, Austria
- Yasuhiro Idomura, Japan Atomic Energy Agency, Japan
- Kirk E. Jordan, IBM T.J. Watson Research, USA
- Aneta Karaivanova, Bulgarian Academy of Sciences, Bulgaria
- Alison Kennedy, Hartree Centre, Science and Technology Facilities Council, UK
- Dieter Kranzlmueller, Ludwig-Maximilians-University Munich, Germany
- Sriram Krishnamoorthy, Google, USA
- Ignacio Laguna, Lawrence Livermore National Laboratory, USA
- Paul Lin, Lawrence Berkeley National Laboratory, USA
- Kengo Nakajima, RIKEN, Japan
- Ron Perrot, University of Oxford, UK
- Yves Robert, ENS Lyon, France
- Stuart Slattery, Oak Ridge National Laboratory, USA
- Valerie Taylor, Argonne National Laboratory, USA
- Keita Teranishi, Sandia National Laboratories, USA
Program (Dallas Local Time - US Central Standard Time Zone)
The workshop program will also be listed in the SC online program.
- 8:30 - 10:05 Session 1
- 8:30 - 9:15 Invited Talk 1:
"Opportunities for Neuromorphic Computing Co-Processors",
Prof. Catherine Schuman (University of Tennessee)
(Presentation)
- 9:15 - 9:40 Paper 1:
"Implementing Asynchronous Jacobi Iteration on GPUs",
Yu-Hsiang Tsai, Pratik Nayak, Edmond Chow, and Hartwig Anzt
(Presentation)
- 9:40 - 10:05 Paper 2:
"GPU Optimization of Lattice Boltzmann Method with Local Ensemble Transform Kalman Filter",
Yuta Hasegawa, Toshiyuki Imamura, Takuya Ina, Naoyuki Onodera, Yuuichi Asahi, and Yasuhiro Idomura
(Presentation)
- 10:05 - 10:30 Coffee break (coffee provided onsite)
- 10:30 - 12:05 Session 2
- 10:30 - 11:15 Invited Talk 2:
"Heterogeneous Computing Challenges and Opportunities",
Dr. Kirk E. Jordan (IBM T.J. Watson Research Center)
- 11:15 - 11:40 Paper 3:
"Scalable Finite-Element Viscoelastic Crustal Deformation Analysis Accelerated with Data-Driven Method",
Kohei Fujita, Sota Murakami, Tsuyoshi Ichimura, Takane Hori, Muneo Hori, Lalith Maddegedara, and Naonori Ueda
(Presentation)
- 11:40 - 12:05 Paper 4:
"MARs: Memory Access Rearrangements in Open MPI",
Yicheng Li, Joseph Schuchart, and George Bosilca
(Presentation)
- 12:05 - 13:30 Lunch break (lunch on your own)
- 13:30 - 15:05 Session 3
- 13:30 - 14:15 Invited Talk 3:
"Hybrid AI/HPC Approaches for Next Generation Multi-Trillion-Parameter Models",
Dr. Phil Brown (Graphcore)
(Presentation)
- 14:15 - 14:40 Paper 5:
"Threshold Pivoting for Dense LU Factorization",
Neil Lindquist, Mark Gates, Piotr Luszczek, and Jack Dongarra
(Presentation)
- 14:40 - 15:05 Paper 6:
"Mixed-Precision Algorithm for Finding Selected Eigenvalues and Eigenvectors of Symmetric and Hermitian Matrices",
Yaohung Tsai, Piotr Luszczek, and Jack Dongarra
(Presentation)
- 15:05 - 15:30 Coffee break (coffee provided onsite)
- 15:30 - 17:00 Session 4
- 15:30 - 16:15 Invited Talk 4:
"Scalable deep learning algorithms for scientific applications on leadership class computing systems",
Brian Van Essen (Lawrence Livermore National Laboratory)
- 16:15 - 17:00 Invited Talk 5:
"Hybrid AI/HPC Approaches and Linear Algebra",
Prof. Nahid Emad (University of Paris Saclay/Versailles)
(Presentation)