Topics in Performance Evaluation

Course number 67587 – Spring 2014

Topics in Performance Evaluation

This course is designed to be complementary to the course on Experimental Approaches in Computer Science (67650); they have perhaps 15% overlap. This course places more emphasis on the methodologies of simulation and analysis, and presents several case studies of performance evaluation. The other course is more about measurements, including examples of discovering unknown facts about workloads or the Internet, and generally the use of experimental procedures.

Course Details:

Class location: Sundays 10-12 Shprintzak 213
Tuesdays 2-4 Shprintzak 26
(Sunday sessions only on alternate weeks)
Teacher: Prof. Dror Feitelson
Questions: send email to feit@cs
Exercises: submit exercises using the Moodle system

View the week-by-week plan of the course, including exercise definitions.

Go to the course forum (use this to ask technical questions about exercises, so everyone can benefit from the questions and answers).

Textbooks:

The course does not follow any specific textbook, but here are a few recommended ones I use:

Grading:

The grade in the course will be determined by your work. There will be 11 weekly exercises, worth 8 points each, and a quiz worth 12 points. There will be no final exam. Exercises must be submitted on time, as they will be discussed in class the week after they are given. If you have a good reason for not doing one or more of the exercises (e.g. you have milu'im for 5 days or more in that week) you will be excused, and the grade will be calculated based on the others.

The default grade for a “very good” exercise is 95. A grade of 100 is reserved for whoever does something special extra, or shows some special insights. Note that "extra" does not just mean "more" — rather, it has to be MEANINGFUL AND INTERESTING.

Links:

For more information on various topics, see the collection of performance evaluation links.


To HUJI CS home page