High Performance Computing I
This lecture provides an introduction to parallel computer architectures and standard programming interfaces for parallel numerical algorithms. We focus on few numerical algorithms like dense matrix multiplications and LU decompositions which allow us to approach step by step the theoretical peak performance.
- Introduction to the programming language C++ with a special focus on numerical linear algebra
- Memory hierarchies
- Parallel computer architectures
- shared memory with POSIX threads and OpenMP
- distributed systems with MPI
Due to the ongoing Corona crisis this lecture will be held online. But we will continue to have a weekly schedule with two sessions per week. Each session comes with two parts, a lecture and a practice session. One will be on Monday afternoon, the other on Friday afternoon.
Linear algebra, calculus, numerical linear algebra, and programming are required. We expect some basic knowledge of C. Knowledge of C++ is not required as we provide an introduction to C++. Introduction to High Performance Computing is recommended but not strictly required. Consider, however, that probably considerable more time will be required for the assignments of the lab sessions without the associated introductory lecture of the bachelor program.
The exams will be held orally in March and April 2021. An oral exam takes about 45 minutes. You are free to chose English or German as exam language. An active and successful participation in the labs (at least half of the quizzes are passed) and an registration for the exam at HIS is required.
Resources and examples of the lectures will be posted at the Moodle course page.
Lab sessions will be held on two times per week. The materials are at the Moodle course page.
- ISO/IEC 9899 (final draft of C18 standard of 2017)
- ISO/IEC 14882 (final draft of C++17 standard of 21 March 2017)
- Wiki with C++ reference
- In German language: Zur Einführung in die Programmiersprache C empfiehlt sich der Vorlesungsbegleiter der Vorlesung Systemnahe Software I
- Manual of gnuplot 5.0 (PDF)
- Utilities to measure read access times of caches, memory, and hardware prefetches for simple and fused operations
- fmt::printf (type-safe alternative to std::printf)