Predicting Heterogeneity and Serverless Principles of Converged High-Performance Computing, Artificial Intelligence, and Workflows
Authors:
- Pedro BruelPBPedro Bruel
- Sai Rahul ChalamalasettiSCSai Rahul Chalamalasetti
- Aditya DhakalADAditya Dhakal
- Eitan FrachtenbergEFEitan Frachtenberg
- Ninad HogadeNHNinad Hogade
- Rolando Pablo Hong EnriquezRERolando Pablo Hong Enriquez
- Alok MishraAMAlok Mishra
- Dejan MilojicicDMDejan Milojicic
- Pavana PrakashPPPavana Prakash
- Gourav RattihalliGRGourav Rattihalli
- 3 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 57 (1) , 136-144
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.Keywords
This publication has 14 references indexed in Scilit:
- Kernel-as-a-Service2023
- Fine-Grained Heterogeneous Execution Framework with Energy Aware Scheduling2023
- Predicting the Performance-Cost Trade-off of Applications Across Multiple Systems2023
- Sustainability: Fundamentals-Based Approach to Paying It ForwardComputer, 2023
- More Real Than Real: The Race to Simulate EverythingComputer, 2022
- Future of HPC: The Internet of WorkflowsIEEE Internet Computing, 2021
- Enabling Compute-Communication Overlap in Distributed Deep Learning Training Platforms2021
- MLIR: Scaling Compiler Infrastructure for Domain Specific Computation2021
- A Survey of DevOps Concepts and ChallengesACM Computing Surveys, 2019
- Characterization of MPI Usage on a Production Supercomputer2018