[hpc-announce] CALL FOR PARTICIPATION -- IPDRM 2020 at SC20, Nov. 13

Jiajia Li fruitfly1026 at gmail.com
Mon Nov 2 12:23:33 CST 2020

                                           CALL FOR PARTICIPATION
                                                IPDRM 2020
Fourth Annual Workshop on Emerging Parallel and Distributed Runtime
Systems and Middleware
     November 13, 2020
   Atlanta, Georgia, USA.

Held in conjunction with the International Conference for High
Performance Computing, Networking, Storage and Analysis (SC20), Nov
15-20, 2020, Atlanta, Georgia, USA.

In collaboration with IEEE TCHPC and IEEE STC Parallel Model and
System DataFlow and Beyond



Node architectures of extreme-scale systems are rapidly increasing in
complexity. Emerging homogeneous and heterogeneous designs provide
massive multi-level parallelism, but developing efficient runtime
systems and middleware that allow applications to efficiently and
productively exploit these architectures is extremely challenging.
Moreover, current state-of-the-art approaches may become unworkable
once energy consumption, resilience, and data movement constraints are
added. The goal of this workshop is to attract the international
research community to share new and bold ideas that will address the
challenges of design, implementation, deployment, and evaluation of
future runtime systems and middleware.


This workshop will emphasize novel, disruptive research ideas over
incremental advances. We will solicit papers on topics including, but
not limited to, the following areas:

Runtime System/Middleware Design, Evaluation and Usage
* Runtime/Middleware for emerging HPC and cloud computing platforms
* Runtime/Middleware for Big Data Computing and Machine Learning
* Modeling and Performance Analysis of Runtime Systems
* Comparison studies of different runtime systems and middleware
* Tuning and Optimization studies
* Interactions between Runtime Systems and Middleware
* Runtime-architecture co-design
* SystemML, TinyML, and topics related to runtime ML/DL optimizations
and implementations such as efficient training and inference.

Constraints and Issues for Runtime Systems and Middleware
* Energy- and Power-aware schemes
* Fault Tolerance and Reliability
* Scalable high-performance I/O and access to Big Data
* Memory management
* Runtime data analysis (e.g., in-situ analysis)
* Real-time solutions and QOS
* Virtualization, provisioning, and scheduling
* Scalability of novel runtime systems and applications using them

Design Principles and Programming Support
* High-level programming models (e.g., thread and task based models,
data parallel models, and stream programming) and domain-specific
* Programming frameworks, parallel programming, and design methodologies
* Methodologies and tools for runtime and middleware design,
implementation , verification, and evaluation
* Wild and crazy ideas on future Runtime System and Middleware

Submission Guidelines:

Full submission will be 8 pages long using the same format as the SC20
conference (i.e. using the IEEE conference template).  All submitted
papers will undergo a rigorous review process and each will have at
least three reviews by members of the program committee. Papers will
be accepted based on their technical contributions. “Crazy and Wild
ideas” are welcome. Submissions can be made through this link:

* EXTENDED Paper Submission: September 7th, 2020
* Paper Notification: October 1st, 2020
* Final Paper Due: October 7th, 2020

Organizing Committees

General Chairs
* Shuaiwen Leon Song, University of Sydney, Australia
* Guang R Gao, Professor Emeritus, Electrical and Computing
Engineering Department, University of Delaware, USA
* Barbara Chapman, Brookhaven National Lab & Stony Brook University, USA
* Joshua Suetterlein, Pacific Northwest National Laboratory, USA
* EunJung Park, Los Alamos National Laboratory, USA

Program Co-Chairs
* Shirley Moore, OakRidge National Laboratory, USA
* Joseph Manzano, Pacific Northwest National Laboratory, USA

Publicity Chair
* Jiajia Li, Pacific Northwest National Laboratory, USA
European Liaison
* Marc Casas, Barcelona Supercomputing Center, Spain
Publication Chair
* Jose Monsalve Diaz, University of Delaware, Argonne National Laboratory, USA

Keynote: Dr. Xiaoming Li, University of Delaware, USA
Title: Fast Convolutional Neural Network With Fine Grained FFT


Time         Paper / Session Title
10:00-10:05 IPDRM 2019 Intro
10:05-10:45 Keynote: Fast Convolutional Neural Network With Fine
Grained FFT | Author:  Xiaoming Li, University of Delaware
10:45-11:10 Scheduling across Multiple Applications using task based
programming models | Authors: Minh Chung, Josef Weidendorfer, Philipp
Samfass, Karl Fuerlinger, Dieter Kranzlmuller
11:10-11:35 MENPS: A decentralized distributed shared memory
exploiting RDMA | Authors: Wataru Endo, Shigeyuki Sato, Kenjiro Taura
11:35-12:00 RaDD Runtimes: Radical and Different Distributed Runtimes
with SmartNICs | Authors: Ryan Grant, Whit Schonbein, Scott Levy
12:00-12:35 LUNCH
12:35-13:00 DEMAC, A Modular Platform for HW-SW Co-Design | Authors:
Diego Andres Roa Perdomo, Jose Manuel Monsalve Diaz, Ryan Kabrick,
Siddhisanket Raskar, Dawson Fox, Guang R. Gao
13:00-13:25 CODIR: Towards an MLIR Codelet Model Dialect | Authors:
Ryan Kabrick, Diego Roa Perdomo, Siddhisanket Raskar, Jose Monsalve
Diaz, Dawson Fox, Guang R. Gao
13:25-13:50 MPI meets Cloud: Case Study with Amazon EC2 and Microsoft
Azure | Authors: Shulei Xu, Seyedeh Mahdieh Ghazimirsaeed, Jahanzeb
Maqbool Hashmi, Hari Subramoni, Dhabaleswar Kumar Panda
13:50-13:55 Conclusion

More information about the hpc-announce mailing list