Advertisement
Published in:
2019 | OriginalPaper | Chapter
10. Class A Results and Analysis
Authors : Art Sedighi, Milton Smith
Published in: Fair Scheduling in High Performance Computing Environments
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Class A simulations describe situations featuring intermittent workloads. In Simulation2, two users submit equal but complementary workloads. As the number of users increases—to 6 in Simulation6, 11 in Simulation10, and 21 in Simulation14—one user’s submission rate stays constant while the workload from the second user (5000 tasks) is distributed among the rest of the users in the system. In Simulation6, users 1–5 submit 1000 tasks each and 5000 total, while user 6 submits 5000 tasks on their own. In Simulation10, users 1–10 submit 500 tasks each, while user 11 submits 5000 tasks on their own. In Simulation14, users 1–20 submit 250 tasks each, while user 21 submits 5000 tasks on their own.