With the requirement of high property processor rapidly increasing, ordinary single-core processors can hardly deal with the task it faces due to the limitation of frequency, power consumption, heat dissipation and etc. Under this circumstance multi-core processor technology turns out to be a reasonable solution for this problem.
While multi-core processors will improve the performance like clock frequency, parallel threads and etc, a certain research illustrate that the improvement of the performance is not linear with the number of cores.
This is because the overhead of scheduler, unbalanced load and the architecture of the multi-core processors. When operating system gives good model like SMP, AMP and industry like X86 and PowerPC design kind of architecture for multi-core, author’s direction naturally focus on a light overhead scheduler which is a C language scheduler “Wool” researched in this paper originally designed by Mr. Karl-Filip Faxen in SICS. Wool is a library providing lightweight tasks on top of pthreads.
In order to understand the principal and structure of “Wool”, author does several pre-study about multi-core schedule and decides the platform and operating system to design some tests. The first part of this master thesis report give an overview of modern technology of multi-core architecture, parallel programming, task parallelism strategy and etc.
The second part specified the “Wool” scheduler. PowerPC e500 core and Enea OSE operating system for the test design and use case. The last part conclude the results of the tests and point out the probably direction for future research.
Source: KTH
Author: Wang, Yang