Multicore Xinu

Philip M Van Every, Purdue University

Abstract

Multicore architectures employ multiple processing cores that work together for greater processing power. Shared memory, symmetric multiprocessor (SMP) systems are ubiquitous. All software must be explicitly designed to support SMP processing, including operating systems. XINU is a simple, lightweight, elegant operating system that has existed for several decades and has been ported to many platforms. However, XINU has never been extended to support multicore processing. This project incrementally adds SMP support to the XINU operating system. Core kernel modules, including the scheduler and memory manager, have been successfully extended without overhauling or completely redesigning XINU. A multicore methodology is laid out for the remaining kernel modules.

Degree

M.S.

Advisors

Comer, Purdue University.

Subject Area

Computer science

Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server
.

Share

COinS