EEL 6762 (FEEDS): PERFORMANCE ANALYSIS OF COMPUTER
& COMMUNICATION SYSTEMS (Spring 2013)
Syllabus
Instructor:
Dr. Jun Wang, HEC 320, 823-0449(office), jun.wang@ucf.edu.
Web: http://www.eecs.ucf.edu/~jwang/EEL6762-s13
Course
Objective and Description:
This course
aims to introduce how to conduct performance evaluation and analysis of
computer systems. The course starts with some fundamental performance analysis
techniques including methods for performance measurement, performance metrics,
monitoring, experimental design, and system modeling. Then, the course
continues with probability theory and statistics. Other topics include:
comparing two or more systems; system tuning; performance bottleneck
identification; characterizing the load on the system (workload
characterization); determining the number and size of components (capacity
planning); predicting the performance at future loads (forecasting); queuing
theory, mean value analysis, and modeling. The course also includes some
real-life case studies of the learned concepts to measure the performances of
computer systems like I/O systems and data centers.
Course Learning Outcomes:
At the end of the course, student must be able to
.
(1) use
applied probability theory in measuring the performance of a computer system.
.
(2)
Understand statistics and data presentation.
.
(3) Practice
performance evaluation techniques and performance measures or metrics.
.
(4)
Summarize and analyze experiments outcomes.
.
(5) Compare
systems using sample data.
.
(6) Use
Queuing theory to measure performances of systems.
.
(7) Model
communication networks and I/O computer systems
Case studies
1.
Open-source Disksim
simulation framework http://www.pdl.cmu.edu/DiskSim/
2.
Performance, Power and Reliability
(e.g. Recoverability) in Storage Systems
3.
Power and Energy Modeling and
Analysis in Computer Systems and Data Centers
Prerequisite: EEL
4742C and STA 3032, or instructor approval.
Required
textbooks:
1) Computer
Architecture, Fourth or fifth Edition: A Quantitative Approach (The Morgan
Kaufmann Series in Computer Architecture and Design) [Paperback]John
L. Hennessy (Author), David A. Patterson (Author)
2) Art of Computer
Systems Performance Analysis Techniques For Experimental Design
Measurements
Simulation And Modeling, by Raj Jain, Wiley Computer Publishing, John Wiley
& Sons, Inc. ISBN: 0471503363 Pub Date: 05/01/91
Other
References:
Course
Homepage:
http://www.eecs.ucf.edu/~jwang/Teaching/EEL6762-s13
Course
Outline (tentative):
Introduction
to performance analysis and evaluation
Main
performance evaluation techniques and measures
Statistics for
performance analysis
Summarizing
data and its variability
Comparing systems;
Introduction
to Queuing theory;
Little¡¯s Law;
Utilization
Law
Mid-Term
Examination
Stochastic
Processes;
Markov
Processes;
Analysis of a
Single Queue;
M/M/1 queuing
analysis, M/M/c queuing
analysis;
Operational law M/G/1 queue.
Grading
Policies:
Note: Homework and programming assignments are due by 11:59pm of
the due date (unless announced in class otherwise). Late homework
(non-programming) will NOT be accepted. Late program penalty is 10% per day,
according to the timestamp of your online submission. Only when verifiable
extenuating circumstances can be demonstrated will extended assignment due
dates be considered. Verifiable extenuating
circumstances must be reasons beyond control of the students, such as illness
or accidental injury. Poor performance in class is not an extenuating
circumstance. Inform your instructor of the verifiable extenuating
circumstances in advance or as soon as possible. In such situations, the date
and nature of the extended due dates for the assignments will be decided by the
instructor.
Attendance Policy:
Attendance is required. Students are
responsible for any material covered in class. Lots of the materials covered in
class will not be in the textbook. Announcements about homework, projects,
programming assignments, etc. may be made in class or online or by emails.
Students are encouraged to check the online WebCourses
regularly.