Efficient Cache-Coherent Migration for Heterogeneous Coprocessors in Dark Silicon Limited Technology
by Ricketts, Scott, M.S., UNIVERSITY OF CALIFORNIA, SAN DIEGO, 2011, 91 pages; 1497133

Abstract:

Current trends in processor manufacturing indicate that in order to meet power budgets, chips will have to power-gate an increasing fraction of transistors. This so called dark silicon will play an important role in motivating future architectures. Recent research proposes to allocate these large dark regions to power-efficient specialized coprocessors. GreenDroid is a tiled architecture where each tile includes a set of coprocessors, generated at design time, that target the anticipated workload. A central challenge to retaining the efficiency of this system is providing low overhead migration mechanisms so that tasks can move around the chip to exploit different coprocessors. This thesis presents a prototype migration system for GreenDroid and other tiled coprocessor-based architectures. The results show that for single-threaded irregular workloads, migration between c-cores spread across a four-tile configuration can provide power savings from 4.8x to 6.2x compared to an all software approach on a single tile. When compared against an ideal case where all c-cores fit on a single tile, the energy overhead of migrating amongst tiles ranges from 2.6% to 24.1%.

 
AdvisersMichael B. Taylor; Steven Swanson
SchoolUNIVERSITY OF CALIFORNIA, SAN DIEGO
SourceMAI/ 50-01, p. , Sep 2011
Source TypeThesis
SubjectsComputer engineering; Computer science
Publication Number1497133
Adobe PDF Access the complete dissertation:
 

» Find an electronic copy at your library.
  Use the link below to access a full citation record of this graduate work:
  http://gateway.proquest.com/openurl%3furl_ver=Z39.88-2004%26res_dat=xri:pqdiss%26rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation%26rft_dat=xri:pqdiss:1497133
  If your library subscribes to the ProQuest Dissertations & Theses (PQDT) database, you may be entitled to a free electronic version of this graduate work. If not, you will have the option to purchase one, and access a 24 page preview for free (if available).

About ProQuest Dissertations & Theses
With over 2.3 million records, the ProQuest Dissertations & Theses (PQDT) database is the most comprehensive collection of dissertations and theses in the world. It is the database of record for graduate research.

The database includes citations of graduate works ranging from the first U.S. dissertation, accepted in 1861, to those accepted as recently as last semester. Of the 2.3 million graduate works included in the database, ProQuest offers more than 1.9 million in full text formats. Of those, over 860,000 are available in PDF format. More than 60,000 dissertations and theses are added to the database each year.

If you have questions, please feel free to visit the ProQuest Web site - http://www.proquest.com - or call ProQuest Hotline Customer Support at 1-800-521-3042.