BEARdocs

Clustering in high dimension and choosing cluster representatives for SimPoint.

DSpace/Manakin Repository

Show simple item record

dc.contributor.advisor Hamerly, Gregory James, 1977-
dc.contributor.author Johnston, Joshua Benjamin.
dc.contributor.other Baylor University. Dept. of Computer Science. en
dc.date.copyright 2007
dc.identifier.uri http://hdl.handle.net/2104/5067
dc.description.abstract In computer architecture, researchers compare new processor designs by simulating them in software. Because simulation is slow, researchers simulate small parts of a workload to save time. The widely successful SimPoint approach identifies these key parts with k-means clustering. The extremely high-dimensional nature of these workloads causes difficulties for k-means, so SimPoint must reduce the dimension before clustering. We propose clustering workload data with the exponential Dirichlet compound multinomial (EDCM), a new relative of the multinomial probability distribution and the first model that has been used to cluster workload data without the need for dimension reduction. The EDCM mixture produces good models which have far fewer clusters than models generated by k-means, significantly reducing the amount of time spent in simulation. The EDCM mixture converges quickly and is a good model for "bursty" traits which appear in workloads. We discuss model selection and choosing cluster representatives for the EDCM mixture. en
dc.rights Baylor University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact librarywebmaster@baylor.edu for inquiries about permission. en
dc.subject Computer simulation. en
dc.subject Computer architecture. en
dc.subject System design. en
dc.title Clustering in high dimension and choosing cluster representatives for SimPoint. en
dc.type Thesis en
dc.description.degree M.S. en
dc.rights.accessrights Worldwide access en
dc.contributor.department Computer Science. en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search BEARdocs


Advanced Search

Browse

My Account

Statistics