2021 High Performance Computing Lecture 9 Accelerators and Graphical Processing Units Part2 💻

Lecture 9 - Accelerators and Graphical Processing Units 🖥️ - Part Two

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: General Purpose Graphical Processing Units (GPGPUs)
Multi-core CPUs vs. Many-core GPUs Revisited & TOP500 Impact
Terminology & NVIDIA Architectures (Kepler, Pascal, Volta, Ampere)
Understanding Node Architectures with GPUs & Summit HPC System
Interconnecting GPUs with NVLink/NVSwitch in ‘islands‘ per Nodes
GPUDirect in Modular Supercomputing & Garpur Iceland HPC System

Part Two: GPU Libraries & Programming Models
Data Science with Deep Learning & Multi GPU Horovod Interconnect
Simulation Sciences via Libraries (e.g., cuBLAS & basic linear algebra)
NVIDIA GPUs & Compute Unified Device Architecture (CUDA)
New Vendors & AMD Instinct in Frontier & LUMI Supercomputers
OpenACC & HIP Standard Programming Models

[neerajkumar-wycp]

Awesome work for HPC students....thanks