A distributed thread scheduler for dynamic multithreading on throughput processors

Ta Kan Yen, Hsien Kai Kuo, Bo-Cheng Lai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

GPGPUs have emerged as one of the most widely used throughput processors. Deep multithreading and cache hierarchy are the two effective implementations to achieve high throughput computing in modern GPGPUs. However, these are two conflicting design options. Finding a proper design point between the two has become a significant performance factor to GPGPUs. This paper proposes a distributed thread scheduler for dynamic multithreading on GPGPUs. By demonstrating the trade-off issue between the multithreading and cache contention, the proposed scheduler dynamically adjusts the multithreading degree to achieve superior performance. With the proposed scheduler, the cache misses can be decreased by 20.6% and 37.9% on the L1 and L2 cache respectively. The overall performance can be enhanced by an average of 16.4%.

Original languageEnglish
Title of host publication2013 International Symposium on VLSI Design, Automation, and Test, VLSI-DAT 2013
DOIs
StatePublished - 15 Aug 2013
Event2013 International Symposium on VLSI Design, Automation, and Test, VLSI-DAT 2013 - Hsinchu, Taiwan
Duration: 22 Apr 201324 Apr 2013

Publication series

Name2013 International Symposium on VLSI Design, Automation, and Test, VLSI-DAT 2013

Conference

Conference2013 International Symposium on VLSI Design, Automation, and Test, VLSI-DAT 2013
CountryTaiwan
CityHsinchu
Period22/04/1324/04/13

Fingerprint Dive into the research topics of 'A distributed thread scheduler for dynamic multithreading on throughput processors'. Together they form a unique fingerprint.

Cite this