Design of a Dynamic Parallel Execution Architecture for Multi-core Systems

Shiang Huang, Jer Min Jou, Cheng Hung Hsieh, Ding Yuan Lin

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

In this paper, a new dynamic Parallel Execution Architecture, DEAL, which can execute the dynamic parallel threads and handle the dynamically incorrect data access caused by parallel execution threads efficiently, is proposed. DEAL combines the concept of multi-thread speculation with the transactional memory into a new model and then threads can be efficiently executed in parallel in it. DEAL can detect incorrect parallel data access immediately and resolve them to keep data consistent among threads and ensure the threads do not violate the data dependences during parallel execution dynamically. Based on experimental results, we find that the performance of parallel applications running in DEAL can be significantly faster, 1.4 speed-ups at least, than those running in sequential, which demonstrated that the DEAL can execute parallel threads and manage data and resolve incorrect data access among them efficiently.

Original languageEnglish
Title of host publicationAdvances in Intelligent Systems and Applications - Volume 2
Subtitle of host publicationProceedings of the International Computer
EditorsChang Ruay-Shiung, Peng Sheng-Lung, Lin Chia-Chen
Pages731-740
Number of pages10
DOIs
Publication statusPublished - 2013 Jun 28

Publication series

NameSmart Innovation, Systems and Technologies
Volume21
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Design of a Dynamic Parallel Execution Architecture for Multi-core Systems'. Together they form a unique fingerprint.

Cite this