By Topic

Multithreaded architectural support for speculative trace scheduling in VLIW processors

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
$31 $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

4 Author(s)
Agarwal, M. ; CADL, Indian Inst. of Sci., Bangalore, India ; Nandy, S.K. ; v Eijndhoven, J. ; Balakrishanan, S.

VLIW processors are statically scheduled processors and their performance depends on the quality of schedules generated by the compiler's scheduler. We propose a multi-threaded architectural support for speculative trace scheduling in VLIW processors. In this multithreaded architecture the next most probable trace is speculatively executed, overlapping the stall cycles of the processor during cache misses and page faults. Switching between traces is achieved with the help of special hardware units viz. operation state buffers and trace buffers. We observe an 8.39% reduction in the overall misprediction penalty as compared to that incurred when the stall cycles due to cache misses alone are not overlapped.

Published in:

Integrated Circuits and Systems Design, 2002. Proceedings. 15th Symposium on

Date of Conference:

2002