Apologies for the multiple copies of this.
Call for Participation
Workshop on Hierarchical Parallelism for Exascale Computing
Held in conjunction with SC20 - virtual event
In cooperation with: IEEE and TCHPC.
High Performance Computing (HPC) platforms are evolving towards having fewer but more powerful nodes,
driven by the increasing number of physical cores in multiple sockets and accelerators.
The boundary between nodes and networks is starting to blur, with some nodes now containing tens of
compute elements and memory sub-systems connected via a memory fabric. The immediate consequence is an
increase in complexity due to ever more complex architectures (e.g., memory hierarchies), novel
accelerator designs, and energy constraints. Spurred largely by this trend, hierarchical parallelism
is gaining momentum. This approach embraces, rather than avoiding, the intrinsic complexity of current
and future HPC systems by exploiting parallelism at all levels: compute, memory and network. This
workshop focuses on hierarchical parallelism. It aims to bring together application, hardware,
and software practitioners proposing new strategies to fully exploit computational hierarchies, and
examples to illustrate their benefits to achieve extreme scale parallelism.
Scope and Aims
HiPar20 is designed to showcase new studies, approaches, and cutting-edge ideas on hierarchical
parallelism for extreme-scale computing. We welcome papers and talks from the HPC community
addressing the use of emerging architectures — focusing particularly on those characterized by fewer
but more powerful nodes as well as systems with hierarchical network with tiered communication semantics.
Specifically, the emphasis is on the design, implementation, and application of programming models for
multi-level parallelism, including abstractions for hierarchical memory access, heterogeneity,
multi-threading, vectorization, and energy efficiency, as well as scalability and performance studies thereof.
Of particular interest are models addressing these concerns portably: providing ease of programming
and maintaining performance in the presence of varied accelerators, hardware configurations,
and execution models. Studies that explore the merits of specific approaches to addressing these concerns,
such as generic programming or domain specific languages, are also in scope.
The workshop is not limited to the traditional HPC software community.
As one example, another key topic is the use of hierarchical parallelism in dealing with the challenges
arising in machine learning due to the growing importance of this field, the large scale of systems
tackled in that area, and the increasing interest from more traditional HPC areas.
A goal of HiPar20 is to highlight not just success stories but also discuss drawbacks and challenges.
HiPar20 welcomes HPC practitioners from all areas, ranging from hardware and compiler experts
to algorithms and software developers, to present and discuss the state of the art in emerging
approaches to utilize multi-level parallelism for extreme scale computing.
Submissions are encouraged in, but not limited to the following areas:
* Hierarchical work scheduling and execution;
* Hardware, software, and algorithmic advances for efficient use of memory hierarchies, multi-threading and vectorization;
* Efficient use of nested parallelism, for example CUDA dynamic parallelism, for large scale simulations;
* Programming heterogeneous nodes;
* Leading-edge programming models, for example fully distributed task-based models and hybrid MPI+X,
with X representing shared memory parallelism via threads, vectorization, tasking or parallel loop constructs.
* Implementations of algorithms that are natural fits for nested work (for example approaches that use recursion);
* Challenges and successes in managing computing hierarchies;
* Examples demonstrating effective use of the combination of inter-node and intra-node parallelism;
* Novel approaches leveraging asynchronous execution to maximize efficiency;
* Challenges and successes of porting of existing applications to many-core and heterogeneous platforms;
* Recent developments in compiler optimizations for emerging architectures;
* Applications of hierarchical programming models from emerging AI fields, for example deep learning and extreme-scale data analytics.
We solicit submissions in the following categories:
(a) Regular research papers:
Intended for submissions describing original work and ideas that have not appeared in another conference or journal,
and are not currently under review for any other conference or journal.
Regular papers must be at least (6) and must not exceed (10) letter size pages (U.S. letter – 8.5"x11").
Accepted regular papers will be published in the workshop proceedings in cooperation with IEEE TCHPC.
(b) Short papers:
Intended for material that is not mature enough for a full paper, to present novel, interesting ideas
or preliminary results that will be formally submitted elsewhere.
Short papers must not exceed four (4) pages.
Short papers will NOT be included in the proceedings.
Please note that:
- The page limits above only apply to the core text, content-related appendices, and figures.
References and reproducibility appendix do not count against the page limit.
- When deciding between submissions with comparable evaluations, priority will be given to those
with higher quality of presentation and whose focus relates more directly to the workshop themes.
- Papers must be submitted electronically at https://submissions.supercomputing.org/
and must follow the IEEE format: www.ieee.org/conferences/publishing/templates.html
HiPar20 follows the SC20 reproducibility and transparency initiative.
The SC20 details can be found at: https://sc20.supercomputing.org/submit/transparency-reproducibility-initiative.
HiPar20 requires all submission to include an Artifact Description (AD) Appendix.
Note that the AD will be auto-generated from author responses to a form embedded in the online submission system.
The Artifact Evaluation (AE) remains optional.
We also encourage authors to follow the transparency initiative for two reasons:
(a) it helps the authors themselves with the actual writing and structuring of the paper to express the research process;
(b) it helps readers understand the thinking process used by the authors to plan, obtain and explain their results.
HiPar20 will be virtual
SCC20 will be fully virtual: https://sc20.supercomputing.org/2020/07/27/sc20-virtual-event-announced-by-general-chair-christine-e-cuicchi/
Please refer to our website www.hipar.net for latest updates.
Submission Deadline: August 31, 2020 (AoE)
Author Notification: September 14, 2020
Camera Ready: October 5, 2020
Final Program: October 9, 2020
Workshop Date: November 11-13, 2020 (details TBD)
Chairs and Committees
- Francesco Rizzi NexGen Analytics
- D.S. Hollman Sandia National Labs
- Lee Howes Facebook
- Xiaoye Sherry Li Lawrence Berkeley National Lab
Program Committee Chairs:
- Christian Trott Sandia National Labs
- Filippo Spiga NVIDIA
- Mark Bull EPCC
- Carlo Cavazzoni CINECA
- Benjamin Cumming CSCS
- Chris Forster NVIDIA
- Marta Garcia Gasulla BSC
- Anja Gerbes Goethe Uni.Frankfurt
- Mark Hoemmen Stellar Science
- Toshiyuki Imamura RIKEN
- Guido Juckeland Helmholtz Center
- Hartmut Kaiser LSU
- Vivek Kale Brookhaven Labs
- Jonathan Lifflander Sandia National Labs
- James Lin Shanghai J.Tong Univ.
- Aram Markosyan Xilinx
- Rui Oliveira INESC TEC
- Philippe Pebay NexGen Analytics
- Zhiqi Tao Intel
- Flavio Vella Univ. of Bozen
- Michèle Weiland EPCC
- Jeremiah Wilke Sandia National Labs
For questions, please email us at: [log in to unmask]