AccaSim: a Customizable Workload Management Simulator for Job\n Dispatching Research in HPC Systems

2018/06/18 by Cristian Galleguillos, Galleguillos, Cristian, Zeynep Kiziltan +5 · 2 citations
Computer Science · #Advanced Data Storage Technologies #Cloud Computing and Resource Management #Distributed #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #Parallel #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.1806.06728

openalex publication_date 2018/06/18 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28

Abstract

We present AccaSim, a simulator for workload management in HPC systems.\nThanks to AccaSim's scalability to large workload datasets, support for easy\ncustomization, and practical automated tools to aid experimentation, users can\neasily represent various real HPC systems, develop novel advanced dispatchers\nand evaluate them in a convenient way across different workload sources.\nAccaSim is thus an attractive tool for conducting job dispatching research in\nHPC systems.\n

Cited by

• A Real-Time Digital Twin for Adaptive Scheduling
• SPARS: A Reinforcement Learning-Enabled Simulator for Power Management in HPC Job Scheduling

Related

• LLload: Simplifying Real-Time Job Monitoring for HPC Users
• Exascale Workflow Applications and Middleware: An ExaWorks Retrospective
• Kub: Enabling Elastic HPC Workloads on Containerized Environments
• ExaWorks Software Development Kit: A Robust and Scalable Collection of Interoperable Workflow Technologies
• A Bespoke Workflow Management System for Data-Driven Urgent HPC