Back to Results
First PageMeta Content
Computer architecture / Parallel computing / Application checkpointing / Scheduling / Computer cluster / Job scheduler / Computing / Concurrent computing / Fault-tolerant computer systems


Using Checkpointing to Recover from Poor Multi-site Parallel Job Scheduling Decisions William M. Jones Electrical and Computer Engineering Department United States Naval Academy Mail Stop 14B, 105 Maryland Avenue, Annapo
Add to Reading List

Document Date: 2007-11-15 07:44:53

Open Document

File Size: 325,42 KB

Share Result on Facebook

City

Washington / DC / Baltimore / Newport / /

Company

Checkpoint / IBM / Los Alamos National Laboratory / Cluster Computing Systems / Computer Communication Networks / High Performance Computing Systems / IEEE Transactions Parallel Distributed Systems / /

Country

United States / China / /

Currency

USD / /

Facility

After checkpoint / Checkpoint Overhead / Clemson University / /

IndustryTerm

interconnection network / multi-site / co-allocation scheduling algorithms / multi-cluster systems / multicluster systems / distributed computing / on-line algorithm / computing / meaningful tool / parallel systems / large-scale cluster systems / /

NaturalFeature

Newport Beach / /

Organization

United States Naval Academy / Naval Academy Research Council / ORN / Clemson University / IEEE Computer Society / /

Person

C. Ernemann / V / Walt Ligon / William M. Jones / Nathan DeBardeleben / Brad Settlemyer / /

Position

author / backfilling meta-scheduler / parallel job scheduler / Performance Attributes General / scheduler / head / /

Technology

RAM / network interface card / on-line algorithm / SIMULATION / Multisite co-allocation scheduling algorithms / Parallel Processing / /

URL

http /

SocialTag