Performance Analysis and Evaluation

6 ECTS credits
165 h study time

Offer 1 with catalog number 4021259FNR for all students in the 2nd semester at a (F) Master - specialised level.

Semester

2nd semester

Enrollment based on exam contract

Impossible

Grading method

Grading (scale from 0 to 20)

Can retake in second session

Yes

Taught in

English

Faculty

Faculty of Sciences and Bioengineering Sciences

Department

Computer Science

Educational team

Antonio Paolillo (course titular)

Activities and contact hours

26 contact hours Lecture
26 contact hours Seminar, Exercises or Practicals
113 contact hours Independent or External Form of Study

Course Content

1. Introduction to Performance Analysis & Evaluation
2. Understanding Performance
3. Challenges of Modern Computing Landscape
4. Approaches to Measure & Improve Performance
5. Simple Examples of Benchmarks
6. Platforms
7. Operating Systems
8. Evaluation Methodology
9. Advanced Tools
10. Gotchas in Benchmarking
11. Plugging-in Metrics
12. Looking Forward: Future Challenges

Additional info

Pre-Requisites:
-   good C programming skills, including pthreads & debugging skills;
-   basic Python programming skills, for results analysis;
-   basic knowledge of operating systems and modern computer organization;
-   mastery of Linux shell command line;
-   basic statistics.

Learning Outcomes

General competences

Knowledge and Understanding: students will gain a comprehensive understanding of computer software & hardware architectures, the non-functional behavior of programs and various performance metrics.
Applying Knowledge and Understanding: students will learn to apply the scientific method for computer system evaluation, i.e. designing & running experiments, capturing outputs, and presenting results.
Making Judgments: students will develop the ability to critically analyze performance issues and apply the right performance analysis techniques to the problem at hand. They will develop an intuition of how to improve the performance of software systems.
Communication: students will learn to effectively present their findings and results, both orally and in writing, with the aid of visual tools like charts, tables, and other performance analysis tools.
Learning Skills: students will acquire the ability to learn and adapt to new tools and technologies to evaluate software, especially in the fast moving landscape of software & hardware. In particular, students will learn to automate their work regarding performance evaluation and analysis. Students will get initiated to evaluation in the context of system research.

Grading

The final grade is composed based on the following categories:
Oral Exam determines 50% of the final mark.
PRAC Practical Assignment determines 50% of the final mark.

Within the Oral Exam category, the following assignments need to be completed:

Oral Exam with a relative weight of 1 which comprises 50% of the final mark.

Within the PRAC Practical Assignment category, the following assignments need to be completed:

Assignments with a relative weight of 4 which comprises 20% of the final mark.
Project with a relative weight of 6 which comprises 30% of the final mark.

Additional info regarding evaluation

20% assignments: small assignments involving performance evaluation;
30% project: a comprehensive project that involves practical application of the concepts learned in the course;
50% final exam: an oral exam covering all the topics discussed in the course and personal research of the student.

Passing the oral exam is mandatory to pass the course.
Participation in class activities & contribution to the open source software framework could lead to a bonus of up to 10% of the maximum grade (i.e. 2 points over 20).

Allowed unsatisfactory mark

The supplementary Teaching and Examination Regulations of your faculty stipulate whether an allowed unsatisfactory mark for this programme unit is permitted.

Academic context