Navigation

19D111MMR - Modeling and Measuring Computer Performance

Course specification
Course title Modeling and Measuring Computer Performance
Acronym 19D111MMR
Study programme Electrical Engineering and Computing
Module Computer Engineering and Informatics
Type of study doctoral studies
Lecturer (for classes)
Lecturer/Associate (for practice)
    Lecturer/Associate (for OTC)
      ESPB 9.0 Status elective
      Condition None
      The goal Introduction to the modeling, simulation and measurement of computer systems, as well as the choice of workloads. Working with real workloads and typical applications (benchmarks) such as SPEC, Splash, TPC-App. Performance analysis of transaction processing. Comparison of simulation, measurement and analytical techniques in the evaluation process and the impact on research process.
      The outcome Students should become capable of modeling the computer systems, with the goal to improving price/performance ratio. They should develop the skills of making complex simulation models, writing and testing custom simulators for research purposes. They should gain the ability to analyze problems and make an appropriate choice of measurement (benchmark) programs, or generating artificial load.
      Contents
      Contents of lectures Statistical theory, mean values, ranking theory. Planning the analysis and conducting of the experiment. The correct interpretation of the results. Tools for monitoring and measurement of computer systems. Characterization of workload. The methodology to generate artificial address traces. Use of available address traces. Application to multiprocessor systems with shared memory.
      Contents of exercises none
      Literature
      1. Raj Jain, The Art of Computer Systems Performance Evaluation, 1991, John Wiley & Sons.
      2. Brendan Gregg, Systems Performance: Enterprise and the Cloud, 2nd Edition, Addison-Wesley, 2020.
      3. John Eeckhout, Performance Evaluation and Benchmarking, 2006, CRC Press.
      4. Pekka Enberg, Latency: Reduce delay in software systems, Manning Publications, 2025.
      5. Protić, J., Tomašević, M., Milutinović V., Distributed Shared Memory: Concepts and Systems, IEEE Computer Society Press, Los Alamitos, California, USA, 1998.
      Number of hours per week during the semester/trimester/year
      Lectures Exercises OTC Study and Research Other classes
      8
      Methods of teaching lectures and individual project
      Knowledge score (maximum points 100)
      Pre obligations Points Final exam Points
      Activites during lectures 0 Test paper 0
      Practical lessons 0 Oral examination 30
      Projects 70
      Colloquia 0
      Seminars 0