2021 High Performance Computing Lecture 8 Debugging and Profiling and Performance Analysis Part1 💻

Lecture 8 - Debugging and Profiling and Performance Analysis 🖥️ - Part One

Advanced Scientific Computing
16 university lectures with additional practical lectures for hands-on exercises in context
University of Iceland, School of Engineering and Natural Sciences
Faculty of Industrial Engineering, Mechanical Engineering and Computer Science

Spring 2021

Course Outline
1. High Performance Computing
2. Parallel Programming with MPI
3. Parallelization Fundamentals
4. Advanced MPI Techniques
5. Parallel Algorithms & Data Structures
6. Parallel Programming with OpenMP
7. Hybrid Programming & Patterns
8. Debugging & Profiling & Performance Analysis
9. Accelerators & Graphical Processing Units
10. Parallel & Scalable Machine & Deep Learning
11. HPC in Health & Neurosciences
12. Computational Fluid Dynamics & Finite Elements
13. Systems Biology & Bioinformatics
14. Molecular Systems & Material Sciences
15. Terrestrial Systems & Climate
16. Epilogue

Lecture Outline

Part One: Debugging & Profiling Techniques
Origin, Terminologies & Bug Prevention Approaches
Review Printf Debugging & Advanced Debugging Techniques & Tools
Terminologies, Performance Terms & Understanding Wall-clock time
Simple MPI Timing Approaches & MPI Profiling Interface
Selected Profiling Techniques & Tools using Profiling

Part Two: Performance Optimization Methods & Toolsets
Performance Measurements Metrics for MPI & OpenMP
Tracing Technique & Open Tracing Format
Simple Loops Constructs & Improving MPI Function Calls
Using the right MPI Collectives for better Performance
MPI & OpenMP Problem Patterns & I/O Hardware Dependencies