opinion

Predicting Heterogeneity and Serverless Principles of Converged High-Performance Computing, Artificial Intelligence, and Workflows

Authors:

Sai Rahul Chalamalasetti,

Eitan Frachtenberg,

Rolando Pablo Hong Enriquez,

Dejan Milojicic,

Pavana Prakash,

Gourav RattihalliAuthors Info & Claims

Computer, Volume 57, Issue 1

Pages 136 - 144

https://doi.org/10.1109/MC.2023.3332973

Published: 03 January 2024 Publication History

Abstract

Traditional high-performance computing and modern artificial intelligence computing are converging with workflows as a common paradigm. We predict nine principles of heterogeneity and serverless computing for this convergence, from high-level programming to low-level hardware.

References

[1]

L. Leite, C. Rocha, F. Kon, D. Milojicic, and P. Meirelles, “A survey of DevOps concepts and challenges,” ACM Comput. Surv. (CSUR), vol. 52, no. 6, pp. 1–35, Nov 2019.

Digital Library

[2]

C. Lattner et al., “MLIR: Scaling compiler infrastructure for domain specific computation,” IEEE/ACM Int. Symp. Code Gener. Optim. (CGO), 2021, pp. 2–14.

Digital Library

[3]

S. Qi, D. Milojicic, C. Bash, and S. Pasricha, “SHIELD: Sustainable hybrid evolutionary learning framework for carbon, wastewater, and energy-aware data center management,” in Proc. IEEE Int. Green Sustain. Comput. Conf., 2023.

[4]

C. Bash, N. Hogade, D. Milojicic, G. Rattihalli, and C. D. Patel, “Sustainability: Fundamentals-based approach to paying it forward,” Computer, vol. 56, no. 1, pp. 125–132, Jan. 2023.

[5]

“Computing with Globus.” Globus. Accessed: Jul. 11, 2023. [Online]. Available: https://www.globus.org/compute

[6]

G. Rattihalli et al., “Fine-grained heterogeneous execution framework with energy aware scheduling,” in Proc. IEEE 16th Int. Conf. Cloud Comput. (CLOUD), 2023, pp. 35–44.

[7]

“Lysozyme in water.” MD Tutorials. Accessed: Jul. 11, 2023. [Online]. Available: http://www.mdtutorials.com/gmx/lysozyme/

[8]

T. Pfandzelter et al., “Kernel-as-a-Service: A serverless programming model for heterogeneous hardware accelerators,” in Proc. ACM Middleware, 2023, pp. 1–15.

[9]

A. Dhakal et al., “Fine-grained accelerator partitioning for Machine Learning and Scientific Computing in Function as a Service Platform,” in Proc. Int. Conf. High Perform. Comput., Netw., Storage, Anal., New York, NY, USA, Denver, CO, USA: ACM, Nov. 12–17, 2023, pp. 1606–1613.

Digital Library

[10]

“Enhancing data movement and access for GPUs.” Nvidia Developer. Accessed: Oct. 11, 2023. [Online]. Available: https://developer.nvidia.com/gpudirect

[11]

“MVAPICH: MPI over InfiniBand, Omni-Path, Ethernet/iWARP, RoCE, and Slingshot.” MVAPICH. Accessed: Oct. 11, 2023. [Online]. Available: https://mvapich.cse.ohio-state.edu/benchmarks/

[12]

S. Chunduri et al., “Characterization of MPI usage on a production supercomputer,” in Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal., 2018, pp. 386–400.

Digital Library

[13]

S. Rashidi et al., “Enabling compute-communication overlap in distributed deep learning training platforms,” in Proc. ACM/IEEE 48th Annu. Int. Symp. Comput. Archit. (ISCA), 2021, pp. 540–553.

Digital Library

[14]

D. Korolija et al., “Farview: Disaggregated memory with operator off-loading for database engines,” in Proc. 12th Annu. Conf. Innov. Data Syst. Res., 2022, pp. 1–14.

[15]

T. Hoefler. General in-Network Processing - Time is Ripe! (Oct. 1, 2020). Accessed: Jul. 11, 2023. [Online Video]. Available: https://www.youtube.com/watch?v=t6jdjnnIRZs

[16]

D. J. Kerbyson, H. J. Alme, A. Hoisie, F. Petrini, H. J. Wasserman, and M. Gittings, “Predictive performance and scalability modeling of a large-scale application,” in Proc. ACM/IEEE Conf. Supercomput., 2001, pp. 1–37.

Digital Library

[17]

A. Nassereldine et al., “Predicting the performance-cost trade-off of applications across multiple systems,” in Proc. IEEE/ACM 23rd Int. Symp. Cluster, Cloud Internet Comput. (CCGrid), 2023, pp. 216–228.

[18]

R. M. Badia, I. Foster, and D. Milojicic, “More real than real: The race to simulate everything,” Computer, vol. 55, no. 7, pp. 67–72, Jul. 2022.

Digital Library

[19]

N. Dube, P. Faraboschi, D. Milojicic, and D. Roweth, “Future of HPC: Internet of workflows,” IEEE Internet Comput., vol. 25, no. 5, pp. 26–34, Sep./Oct 2021.

[20]

D. Milojicic, P. Faraboschi, N. Dube, and D. Roweth, “Future of HPC: Diversifying heterogeneity,” in Proc. Des., Autom. Exhib. (DATE), 2021, pp. 276–281.

Cited By

Huang POu X(2024)Application of Artificial Intelligence Technology in Risk Assessment and Management of Pile Foundation Engineering of Offshore Wind Power ProjectsProceedings of the 2024 International Conference on Computer and Multimedia Technology10.1145/3675249.3675286(200-205)Online publication date: 24-May-2024
https://dl.acm.org/doi/10.1145/3675249.3675286
Frachtenberg EMittal VBruel PFaloutsos MMilojicic D(2024)The Distribution Is the PerformanceComputer10.1109/MC.2024.336244857:4(143-149)Online publication date: 3-Apr-2024
https://dl.acm.org/doi/10.1109/MC.2024.3362448

Index Terms

Predicting Heterogeneity and Serverless Principles of Converged High-Performance Computing, Artificial Intelligence, and Workflows

Index terms have been assigned to the content through auto-classification.

Recommendations

Scientific computing using virtual high-performance computing: a case study using the Amazon elastic computing cloud
SAICSIT '08: Proceedings of the 2008 annual research conference of the South African Institute of Computer Scientists and Information Technologists on IT research in developing countries: riding the wave of technology

High-performance computing systems are important in scientific computing. Clusters of computer systems --- which range greatly in size --- are a common architecture for high-performance computing. Small, dedicated clusters are affordable and cost-...
Supporting Multi-Provider Serverless Computing on the Edge
ICPP Workshops '18: Workshop Proceedings of the 47th International Conference on Parallel Processing

Serverless computing has recently emerged as a new execution model for cloud computing, in which service providers offer compute runtimes, also known as Function-as-a-Service (FaaS) platforms, allowing users to develop, execute and manage application ...
Serverless Execution of Scientific Workflows
Service-Oriented Computing
Abstract
In this paper, we present a serverless workflow execution system (DEWE v3) with Function-as-a-Service (FaaS aka serverless computing) as the target execution environment. DEWE v3 is designed to address problems of (1) execution of large-scale ...

Comments

Information & Contributors

Information

Published In

0018-9162 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Publisher

IEEE Computer Society Press

Washington, DC, United States

Publication History

Published: 03 January 2024

Qualifiers

Opinion

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 21 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Huang POu X(2024)Application of Artificial Intelligence Technology in Risk Assessment and Management of Pile Foundation Engineering of Offshore Wind Power ProjectsProceedings of the 2024 International Conference on Computer and Multimedia Technology10.1145/3675249.3675286(200-205)Online publication date: 24-May-2024
https://dl.acm.org/doi/10.1145/3675249.3675286
Frachtenberg EMittal VBruel PFaloutsos MMilojicic D(2024)The Distribution Is the PerformanceComputer10.1109/MC.2024.336244857:4(143-149)Online publication date: 3-Apr-2024
https://dl.acm.org/doi/10.1109/MC.2024.3362448

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents