Abstract

Chip multiprocessor (CMP) is replacing the superscalar processor due to its huge performance gains in terms of processor speed, scalability, power consumption and economical design. Since the CMP consists of multiple processor cores on a single chip usually with share cache resources, process synchronization is an important issue that needs to be dealt with. Synchronization is usually done by the operating system in case of shared memory multiprocessors (SMP). This work studies the effect of performing synchronization by the hardware through its integration with the cache coherence protocol. A novel cache coherence protocol, called Lock-based Cache Coherence Protocol (LCCP) was designed and its performance was compared with MESI cache coherence protocol. Experiments were performed by a functional multiprocessor simulator, MP_Simplesim, that was modified to do this work. A novel interconnection network was also designed and tested in terms of performance against the traditional bus approach by means of simulation.

School

School of Sciences and Engineering

Department

Computer Science & Engineering Department

Degree Name

MS in Computer Science

Date of Award

6-1-2006

Online Submission Date

2-3-2013

First Advisor

El-Ayat, Khaled

Committee Member 1

El-Ayat, Khaled

Committee Member 2

Sameh, Ahmed

Document Type

Thesis

Extent

188 p.

Rights

The American University in Cairo grants authors of theses and dissertations a maximum embargo period of two years from the date of submission, upon request. After the embargo elapses, these documents are made available publicly. If you are the author of this thesis or dissertation, and would like to request an exceptional extension of the embargo period, please write to thesisadmin@aucegypt.edu

IRB

Not necessary for this item

Share

COinS