Postgraduate Course: Practical Introduction to High Performance Computing (PGPH11093)
Course Outline
| School | School of Physics and Astronomy |
College | College of Science and Engineering |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
| Course type | Online Distance Learning |
Availability | Not available to visiting students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | High Performance Computing (HPC) is a fundamental technology used in solving scientific and commercial problems. Many of the grand challenges of science depend on simulations and models run on HPC facilities to make progress, for example: protein folding, the search for the Higgs boson and developing nuclear fusion. In industry, sophisticated computer models are integral to the development of products such as jet engines, wind turbines and new drugs.
Modern supercomputers are parallel computers, gaining their power from many thousands of individual processors. Developing software to run on these systems requires using new parallel programming techniques.
The course will cover all the fundamental concepts that underpin modern HPC. The course is practical in the sense that you will explore these topics by running parallel programs on real HPC systems such as the UK national supercomputer ARCHER.
The course will be delivered entirely online, and videos, notes and exercises will be released as the course progresses.
|
| Course description |
As HPC and parallel programming become more widespread they are being used by an ever increasing number of academic and industrial disciplines. Previously, use of HPC was dominated by people with high levels of technical programming experience and backgrounds in physics, engineering, mathematics or computer science. As a result, HPC training tended to be quite technical in nature and assumed that all users would be competent programmers developing their own software. For example, these are the communities served by EPCC's traditional MSc in HPC programmes.
With the widening base of users, there are now two major HPC communities (from both academia and industry) who are not served by this type of training:
1. users of the increasing number of centrally supported parallel packages, e.g. for computational chemistry or engineering simulations;
2. users from new applications areas who want to learn about the fundamental concepts of HPC to decide if or how it might be applicable to their own subject area before investing further effort in, for example, improving their software development skills.
It is important to understand that, even with the advent of high-quality parallel packages, using HPC resources efficiently is still not completely straightforward so users of these packages still require a `substantial amount of HPC knowledge. Examples include:
1. software may need to be downloaded from a central repository and compiled from source;
2. changing the functionality of the package may require small sections of source code to be modified;
3. selecting the best package to use may require knowledge of how each package's parallelisation strategy interacts with the target HPC architecture;
4. checking that the package is performing acceptably requires a basic knowledge of HPC architectures and parallelisation techniques;
5. interacting with HPC systems is more complicated than with a desktop system, e.g. users log in to shared login nodes and have to submit parallel jobs to a batch queuing system.
This course will not require any substantial experience in programming; all parallel software will be provided to the students so only basic IT literacy is assumed. However, those who can program will be able to further develop their skills by examining the source code although this not a requirement of the course. Those who cannot program will be encouraged to learn the basic concepts by writing simple examples in Python.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
Course Delivery Information
|
| Academic year 2015/16, Not available to visiting students (SS1)
|
Quota: None |
| Course Start |
Flexible |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Lecture Hours 25,
Seminar/Tutorial Hours 15,
Online Activities 28,
Summative Assessment Hours 60,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
68 )
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
Formative
- peer assessment of answers to set exercises;
- self-assessment via online multiple-choice questions to reinforce key topics.
Summative
1. Group report on aspects of HPC architectures (25%);
2. Individual report on performance analysis of HPC programs on a variety of architectures (50%);
3. Individual essay: case-study on application of HPC to a particular subject area (25%). |
| Feedback |
Not entered |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Understand the key components of HPC architectures and how they are put together to form complete systems
- Be able to build and test code in a Linux/Unix environment, execute in parallel and understand the stages involved.
- Compare and contrast the message-passing and multithreaded parallel programming models, and describe four key parallelisation strategies used in modern HPC codes.
- Understand the importance of performance and Amdahl's law, and measure and comment on the performance of parallel codes.
- Explain the current uses of HPC and the key issues for HPC in the future.
|
Learning Resources
| There is no single compulsory course text. Pointers to appropriate material will be made available online. |
Additional Information
| Course URL |
www.epcc.ed.ac.uk/online-courses |
| Graduate Attributes and Skills |
- Critical thinking
- Communication of complex ideas in accessible language
- Working in an interdisciplinary field
- Programming and Scripting
|
| Keywords | Not entered |
Contacts
| Course organiser | Dr Andrew Turner
Tel: (0131 6)51 3578
Email: andrew.turner@ed.ac.uk |
Course secretary | Yuhua Lei
Tel: (0131 6) 517067
Email: yuhua.lei@ed.ac.uk |
|
© Copyright 2015 The University of Edinburgh - 2 September 2015 4:38 am
|
University Homepage