CS-E4690 - Programming Parallel Supercomputers D, Lecture, 3.9.2024-29.11.2024
Topic outline
-
The topic of this course is high-performance computing (HPC), namely heavy-duty computing on clusters or supercomputers with thousand(s) to million(s) of cores. You will learn about the current supercomputing architectures (NUMA), distributed memory and hybrid (distributed + shared memory) programming models, message-passing interface, threading, and massive parallelism with graphics processing units (GPUs).
Implementation: 10 contact teaching sessions and ~ similar amount of coding exercises.
Materials: Pre-recorded lectures, lecture slides, pre-reading, example codes and scripts.
- Lecture materials and pre-assignments will be posted in MyCourses (Lectures section)
- Example codes, scripts and coding exercises will be available from (TBA).
- Zulip chat (TBA) for discussions and posting questions.
Grading: is based on the returned exercise codes (40%), presence in the contact session teaching sessions (10%), and an exam (50%). Coding exercises are returned in a specified directory in Triton and graded there. Exam takes place in a computer class.