skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Codesign for Extreme Heterogeneity: Integrating Custom Hardware With Commodity Computing Technology to Support Next-Generation HPC Converged Workloads

Journal Article · · IEEE Internet Computing
ORCiD logo [1];  [1]; ORCiD logo [1];  [1]
  1. Pacific Northwest National Laboratory, Richland, WA, USA
+ Show Author Affiliations

The future of high-performance technical computing will be driven by the convergence of physical simulation, Artificial Intelligence (AI), Machine Learning (ML), and data science computing capabilities. While computational performance gains afforded by technology scaling, as predicted by Moore’s Law, have enabled large scale HPC system design and deployment using commodity CPU and GPU processing components, emerging technologies will be required to effectively support such converged workloads. These emerging technologies will integrate commodity computing components with custom processing and networking accelerators into ever-more heterogeneous architectures resulting in a diverse ecosystem of industry technology developers, university, and U.S. Government researchers. In this article, we describe efforts at the U.S. DOE Pacific Northwest National Laboratory (PNNL) to construct an end-to-end codesign framework to lay the groundwork for such an ecosystem, including notable outcomes, remaining challenges, and future opportunities.

Research Organization:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program
Grant/Contract Number:
AC05-76RL01830
OSTI ID:
1924572
Alternate ID(s):
OSTI ID: 1924573; OSTI ID: 1962392
Report Number(s):
PNNL-SA-175408; 9936046
Journal Information:
IEEE Internet Computing, Journal Name: IEEE Internet Computing Vol. 27 Journal Issue: 1; ISSN 1089-7801
Publisher:
Institute of Electrical and Electronics EngineersCopyright Statement
Country of Publication:
United States
Language:
English

References (14)

Towards data-driven next-generation transmission electron microscopy journal October 2020
Toward the Balance between the Reductionist and Systems Approaches in Computational Catalysis: Model versus Method Accuracy for the Description of Catalytic Systems journal May 2017
Assessing Advanced Technology in CENATE conference August 2016
OpenCGRA: An Open-Source Unified Framework for Modeling, Testing, and Evaluating CGRAs conference October 2020
A Survey on Network Security-Related Data Collection Technologies journal January 2018
Data-driven Distributed Learning of Multi-agent Systems: A Koopman Operator Approach conference December 2021
MLIR: Scaling Compiler Infrastructure for Domain Specific Computation conference February 2021
GEDet journal July 2021
Koopman-based Differentiable Predictive Control for the Dynamics-Aware Economic Dispatch Problem conference June 2022
LLVM: A compilation framework for lifelong program analysis & transformation conference January 2004
The Minos Computing Library conference February 2020
The long road to calibrated prediction uncertainty in computational chemistry journal March 2022
Single-node partitioned-memory for huge graph analytics
  • Ghosh, Sayan; Tallent, Nathan R.; Minutoli, Marco
  • Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1145/3458817.3476156
conference November 2021
Graph Neural Network and Koopman Models for Learning Networked Dynamics: A Comparative Study on Power Grid Transients Prediction journal January 2022

Similar Records

Related Subjects

97 MATHEMATICS AND COMPUTING
Hardware/Software interfaces
Heterogeneous (hybrid) systems
Environments for multiple-processor systems
Compiler frameworks
Programming models