ADVANCED SCIENTIFIC COMPUTING
Dr. – Ing. Morris RiedelAdjunct Associated ProfessorSchool of Engineering and Natural Sciences, University of IcelandResearch Group Leader, Juelich Supercomputing Centre, Germany
EpilogueNovember 28th, 2017Room TG-227
High Performance Computing
FINAL LECTURE 18
Review of Lecture 17 – Machine Learning & Data Mining
Final Lecture 18 – Epilogue
1. Some pattern exists2. No exact mathematical
formula3. Data exists
Algorithms using HPC methods
Deep Learning [1] Lee et al.
2 / 16
Outline of the Course
1. High Performance Computing
2. Parallelization Fundamentals
3. Parallel Programming with MPI
4. Advanced MPI Techniques
5. Parallel Algorithms & Data Structures
6. Parallel Programming with OpenMP
7. Hybrid Programming & Patterns
8. Debugging & Profiling Techniques
9. Performance Optimization & Tools
10. Scalable HPC Infrastructures & GPUs
Final Lecture 18 – Epilogue
11. Scientific Visualization & Steering
12. Terrestrial Systems & Climate
13. Systems Biology & Bioinformatics
14. Molecular Systems & Libraries
15. Computational Fluid Dynamics
16. Finite Elements Method
17. Machine Learning & Data Mining
18. Epilogue
+ additional practical lectures for our
hands-on exercises in context
3 / 16
Outline
HPC – Big Data from another Perspective
Further Readings
Thesis for Data Scientists Available
High Performance Computing Course Fall 2017
Acknowledgements
Final Lecture 18 – Epilogue 4 / 16
HPC – From Another Perspective
Final Lecture 18 – Epilogue 5 / 16
The Map of HPC – Advanced Scientific Computing
Final Lecture 18 – Epilogue
THEORY TECHNIQUES PARADIGMS
Parallel Algorithms
Speed-Up
Weak/Strong Scaling
High Performance Computing
High Throughput Computing
Message Passing Interface
OpenMP & Hybrid
Network & Communication
Discretizations & Meshes
Clouds & Grid Infrastructures
Computational Modeling
Amdahls Law Numerical Simulations
Monte Carlo MethodsGustafsons Law
6 / 16
Further Readings
Final Lecture 18 – Epilogue 7 / 16
Further Readings
Final Lecture 18 – Epilogue
Introduction to High Performance Computingfor Scientists and Engineers,Georg Hager & Gerhard Wellein,Chapman & Hall/CRC Computational Science,ISBN 143981192X, English, ~330 pages, 2010
www.morrisriedel.de/talks
8 / 16
Thesis for Data Scientists Available
Final Lecture 18 – Epilogue 9 / 16
Training Data Scientists
Methods & Tools
Applied Statistics
MachineLearning
Algorithms
Samplingvs. Big Data
Scientific Computing
Parallelization!
Data Scientist
Statistician
ComputationalScientist Data
Miner
Statistical Data Mining CourseHPC – A(dvanced Scientific Computing) CourseHPC – B(ig Data) Course
Data Mining
Data Scientists with skills of various fields
SoftwareEngineer
Engineer
Insights
new DBs
WE WANT YOU!Many Thesis Topics
Available!
Acknowledgements
Final Lecture 18 – Epilogue 11 / 16
Acknowledgements
Work around JOTUNN Hjörleifur Sveinbjörnsson Máni Maríus Viðarsson
Organization / Management with HI Kristjan Jonasson Helmut Neukirchen Matthias Book
Discussions around Statistical Data Mining & Parallelization Tomas Philipp Runnarson
Finally – Thanks to all of you!
Final Lecture 18 – Epilogue 12 / 16
[Video] 25 Years of HPC
Final Lecture 18 – Epilogue
[2] SC2013, 25 years of HPC
13 / 16
Lecture Bibliography
Final Lecture 18 – Epilogue 14 / 16
Lecture Bibliography
[1] H. Lee et al., ‘Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations’, Proceedings of the 26th annual International Conference on Machine Learning (ICML), ACM, 2009
[2] YouTube Video, 25 Years of HPC, Online: http://www.youtube.com/watch?v=Q5VAMJn7tHA
Final Lecture 18 – Epilogue 15 / 16
Final Lecture 18 – Epilogue 16 / 16
Top Related