By Topic

Java Virtual Machine performance analysis with Java instruction level parallelism and advanced folding scheme

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
A. Kim ; Dept. of Comput. Sci., Illinois Inst. of Technol., Chicago, IL, USA ; M. Chang

This paper attempts to solve the inherently slow performance problem of Java by improving instruction level parallelism merged with a newly developed instruction folding technique. The new ILP scheme with an advanced folding mechanism creates a possibility of further improvement of instruction parallelism. A new architecture is introduced in this project by demonstrating the most recent bytecode folding mechanism followed by folded instruction level parallelism. This paper also presents a comprehensive study of branch prediction logic in the new ILP mechanism. An experiment using SPECJVM98 benchmarks reveals that as many as 7.8 bytecode instructions can be executed concurrently. In our simulation results, the 4-way parallel issue processor has achieved the highest performance, exceeding by 4 times the parallel bytecodes per issue among many other configurations. Moreover, the new ILP system proposed in this paper shows significantly higher parallelism against an existing Java ILP machine

Published in:

Performance, Computing, and Communications Conference, 2002. 21st IEEE International

Date of Conference: