Parallel Numerics - Winter 10: Difference between revisions
No edit summary |
No edit summary |
||
Line 47: | Line 47: | ||
* [[http://www5.in.tum.de/lehre/vorlesungen/parnum/WS10/PARNUM_6.pdf Lecture 6, Sparse storage formats, Schur complement]] | * [[http://www5.in.tum.de/lehre/vorlesungen/parnum/WS10/PARNUM_6.pdf Lecture 6, Sparse storage formats, Schur complement]] | ||
* [[http://www5.in.tum.de/lehre/vorlesungen/parnum/WS10/PARNUM_7.pdf Lecture 7, Reordering, Perfect Matching, Iterative methods]] | * [[http://www5.in.tum.de/lehre/vorlesungen/parnum/WS10/PARNUM_7.pdf Lecture 7, Reordering, Perfect Matching, Iterative methods]] | ||
* [[http://www5.in.tum.de/lehre/vorlesungen/parnum/WS10/PARNUM_8.pdf Lecture 8, Stationary Methods, CG]] | |||
Revision as of 11:21, 20 December 2010
- Term
- Winter 10
- Lecturer
- Univ.-Prof. Dr. Thomas Huckle
- Time and Place
- Lecture: Monday 10:15 - 11:45 Uhr (MI 02.07.023), Tutorial Friday 10:15 - 11:45 Uhr (MI 02.07.023)
- Audience
- CSE (compulsory course, 3rd semester), Mathematics (Master), Informatics (Master) (Modul IN2012)
- Tutorials
- Matous Sedlacek
- Exam
- To be announced
- Semesterwochenstunden / ECTS Credits
- SWS (2V + 2Ü) / 5 Credits
- TUMonline
- {{{tumonline}}}
This course will be given in every winter term. The lectures and tutorials are conducted in English, and the course substitutes the German lecture "Numerik auf Parallelrechnern".
News
- First lecture: Monday, October 25: 10:15-11:45 am
- First tutorial: Friday, November 5: 10:15-11:45 am
- No lecture on Monday, November 1 because of holiday. Second lecture: Monday, November 8.
- Date and place of Exam are updated! Takes place February 4th, 2011. Please register till January 15th, 2011 via TumOnline.
- Last Lecture this year: Monday, December 20
Last Tutorial (Tutorial 7) this year: Friday, December 17
First Lecture in year 2011: Monday, January 10
First Tutorial (Tutorial 8) in year 2011: Friday, January 14 - Post-exam review in MI 02.07.023: Friday, February 11: 10:15-11:45 am
Contents
- High-Performance Computing
- Performance: Analysis, Modeling, and Measurements
- Basic Linear Algebra Subprograms
- Direct Solution of Sparse Linear Systems
- Iterative Methods for Linear Systems
- Linear Eigenvalue Problems
- Programming in MPI
Course Material
Lecture Notes
Slides
- [Lecture 1, Introduction]
- [Lecture 2, MPI, OpenMP, Graphs]
- [Lecture 3, Graphs, Colouring, BLAS]
- [Lecture 4, BLAS, Linear equations with dense matrices]
- [Lecture 5, Linear equations with dense matrices, sparse storage formats]
- [Lecture 6, Sparse storage formats, Schur complement]
- [Lecture 7, Reordering, Perfect Matching, Iterative methods]
- [Lecture 8, Stationary Methods, CG]
Tutorials
Corrections with new version are marked in red.
Tutorial | Topics | Worksheet | Proposal for solution / code | Slides |
1 | Flynn's Taxonomy & MPI Basics | worksheet1.pdf | worksheet1_solution.pdf ws1_task6.cpp |
|
2 | Numerical Integration & P2P Communication I | worksheet2.pdf | worksheet2_solution.pdf ws2_task1.cpp |
Flynn_SPMD.pdf |
3 | Vector-Vector Operations & P2P Communication II | worksheet3.pdf | worksheet3_solution.pdf ws3_task5.cpp |
|
4 | Matrix-Matrix-Operations & P2P Communication III | worksheet4.pdf | worksheet4_solution.pdf ws4_task5.cpp |
|
5 | Parallel Gaussian elimination & Collective Operations | worksheet5.pdf | worksheet5_solution.pdf (v1.1) ws5_task3.cpp |
Comm_Modes.pdf |
6 | Tridiagonal Matrices, Hockney/Golub method & Message Tags | worksheet6.pdf | worksheet6_solution.pdf ws6_task1_serial.cpp ws6_task1_parallel.cpp ws6_task3.cpp |
|
7 | Sparse Matrix-Vector Multiplication & MPI Communicators | worksheet7.pdf | worksheet7_solution.pdf ws7_task3.cpp |
|
8 | Stationary Methods | worksheet8.pdf | coming soon... | |
9 | Domain Decomposition | worksheet9.pdf | coming soon... |
Literature & External Links
- Numerical Linear Algebra for High-Performance Computers (Dongarra, Duff, Sorensen, van der Vorst)
- Parallel Algorithms for Matrix Computations (Gallivan, Heath, Ng, Ortega,...)
- A User's Guide to MPI (Pacheco)
- Iterative Methods for Sparse Linear Systems (Saad)
- Loesung linearer Gleichungssysteme auf Parallelrechnern (Frommer)
Exam
- Date: 2011 February 4th, 11:30-13:30
- Room: MW 1050 (Johann-Bauschinger-Zeichensaal, Departement of mechanical engineering)
- Registration: Via TumOnline till 2011, January 15th.
You can sign off till 2011, January 28th.
Allowed Material for the exam
- 1 two-sided hand-written sheet of paper
- "Message Passing Interface Quick Reference in C" [MPI Quick Reference]
Regulations
The exam takes place on February 4th, 2011 at 11:30 in room MW 1050 (Departement of mechanical engineering). Make sure you are in place on time. As the lecture hall is reserved from 11:30, and as we have to leave at 13:30, there's no chance to wait for late arrivals. A handwritten sheet of paper (size A4, front and back page) may be used during the exam as mnemonic as well as the MPI operation reference distributed during the tutorials. No other material besides dictionaries is allowed.
Please study your examination regulations. Students in most disciplines have to register for the exams throughout the semester via TumOnline.
Students that did not pass the exam or did not participate and still need the credits should contact Prof. Thomas Huckle for an appointment as soon as possible. In this case, the appointment always is the second try, i.e. if you do not take part in the exam, it is a failed try.