Oracle
Country
Communities
I am a...
I want to...
Welcome
Account
Sign Out
Sign In/Register for Account
Help
Products
Solutions
Downloads
Store
Support
Training
Partners
About
Oracle
Technology Network
Home
Oracle Labs
People
Publication Details
Oracle Labs
About
Overview
Locations
People
Projects
Awards
External Research Office
Publication
Callisto: Co-Scheduling Parallel Runtime Systems (April 2014)
It is increasingly important for parallel applications to run together on the same machine. However, current performance is often poor: programs do not adapt well to dynamically varying numbers of cores, and the CPU time received by concurrent jobs can differ drastically. This paper introduces Callisto, a resource management layer for parallel runtime systems.We describe Callisto and the implementation of two Callisto-enabled runtime systems—one for OpenMP, and another for a task-parallel programming model. We show how Callisto eliminates almost all of the scheduler-related interference between concurrent jobs, while still allowing jobs to claim otherwise-idle cores. We use examples from two recent graph analytics projects and from SPEC OMP.
Authors:
Tim Harris, Martin Maas, Virendra Marathe,
Oracle Labs on OTN
Want to try out some of the cool technology being built at Oracle Labs?
Visit our
OTN page
.
Close
Stay Connected
Email to a friend
Facebook
Twitter
Close
Integrated Cloud Applications and Platform Services
Subscribe
Careers
Contact Us
Site Maps
Legal Notices
Terms of Use
Privacy
Cookie Preferences
Oracle Mobile
Facebook
LinkedIn
Twitter
Google+
YouTube
Oracle RSS Feed