Special Issue on:
New Trends in High Performance Computing: Software Systems and Applications
Software: Practice and Experience (Wiley Press)

https://onlinelibrary.wiley.com/pb-assets/assets/page/journal/1097024x/SPE-SI-HPC-1607014410373.pdf

Submission due: May 31, 2021

High performance computing (HPC) offers the computing power to continuously support
the world’s most important discoveries in various scientific and business domains such
as chemistry, physics, biology, material science, drug discovery and financial
investment risk analysis. The exascale computing era is soon coming. A number of
exaflops-capable supercomputers are scheduled to be fully operational in the time
frame of 2021 and 2022. Researchers from across the HPC community are developing
software systems, tools, libraries, frameworks, application packages, and methods that
can fully exploit these extremely powerful computing resources.

Extreme-scale computing will enable the solution of vastly more accurate predictive
models and the analysis of massive quantities of data, producing quantum advances in
areas of science and technology that are essential to the scientific community. New
computational approaches such as machine learning/deep learning have also been
heavily explored in recent years and shown promising evidence for many problems that
cannot be resolved by traditional computational simulation and engineering. Training
deep neural networks with massive data is an extremely computing intensive task that
heavily relies on the HPC power. The upcoming exascale computing era will be the
essential basis for supporting new innovations in machine learning/deep learning based
exploration and lead to new sciences in directions such as smart manufacturing,
laboratory-automation, and automatic programming.

While the hardware architecture can generate extreme computing power, renovation in
software stack plays the essential role for effective performance delivery. The exascale
and pre-exascale systems such as Aurora, Frontier, El Capitan and LUMI continue to
move into the heterogeneous space, while the current fastest ARM-based system,
Fugaku and the many core Sunway Taihulight type of systems are marching towards
the heterogeneous space. With systems equipped with GPUs, ARM SVEs and many
cores, there is a dire need for innovative software frameworks that can seamlessly
migrate scientific code to these systems equipped with rich compute resources. We
need innovation at different levels including compiler tools and techniques, performance
analysis tools, novel abstractions at the programming model, redesign of application-level
algorithms and so on. Furthermore, co-design of applications and low-level software
frameworks can lead to more efficient use of the opportunities of
exascale in many contexts.

Topics of interests include but are not limited to:

+ HPC for AI and AI for HPC
- AI/ML/DL performance optimizations at applications or system frameworks
levels on HPC systems
- Innovations of system, compiler, language, debugging and profiling tools
for parallel AI/ML/DL
- Performance modeling for AI/ML/DL applications
- Visualization for parallel AI/ML/DL
- AI/ML/DL driven approaches for scientific computing and performance
optimization at scale

+ Programming Challenges in HPC
- Exposing parallelism at different levels including application, architecture,
system and algorithmic level
- Enabling combinations of multi physics models and capabilities
- Adopting novel algorithmic/mathematical approaches
- Developing portable applications yet preserving performance
- Exploring programming extensions and auto-vectorization capabilities
- Exploration of application and system software co-design for addressing
performance challenges
- Programming language and compilation techniques for reducing energy
and data movement

+ HPC Systems Software and Middleware
- System software support for data management
- Scalable data analytics
- System software for resource management
- Fault tolerance techniques and implementations
- Synchronization and concurrency control

+ HPC Performance Measurement and Modeling
- Scalable tools and instrumentation infrastructure for measurement,
monitoring, and/or visualization of performance
- Workload characterization and benchmarking techniques
- Novel and broadly applicable performance optimization techniques

+ HPC Applications
- Computational science and scalable methods
- Using HPC for scalable multi-scale, multi-physics, and high-fidelity
computational science
- Structured and unstructured meshes using extreme scale computing
- Computational biology, earth sciences, cosmology, fluid dynamics, plasma
modeling among others

Important Dates
- Submission: May 31, 2021
- Notification: July 31, 2021
- Revision due: Aug 20, 2021
- Notification of final acceptance: Sept 20, 2021
- Final revised paper due: October 15, 2021

Special Issue Paper Submission
Submission site: https://mc.manuscriptcentral.com/spe
Please see detailed guidance at the online Call For Paper:
https://onlinelibrary.wiley.com/pb-assets/assets/page/journal/1097024x/SPE-SI-HPC-1607014410373.pdf


Guest Editors
Sunita Chandrasekaran
University of Delaware, USA
Email: schandra@udel.edu

Min Si
Argonne National Laboratory, USA
Email: msi@anl.gov

Jidong Zhai
Tsinghua University, China
Email: zhaijidong@tsinghua.edu.cn

Lena Oden
University of Hagen, Germany
Email: lena.oden@fernuni-hagen.de