Postgraduate Course: Numerical Algorithms for High Performance Computing (INFR11174)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Available to all students
|Summary||The development of High Performance Computing (HPC) systems has been largely driven by the requirements of Computational Scientists running large-scale numerical simulations such as global weather forecasting or studying new materials at the atomic scale. This course covers some of the basic numerical algorithms and computational patterns used in HPC and how they are implemented and used in practice, including the use of standard packages and libraries. Where appropriate, reference will be made to parallel implementations.
All these algorithms operate on real-valued variables, not integers, so it is important to understand the issues around storing and working with floating-point numbers, including the errors that this can introduce. This is an applied course and running the algorithms in practical situations is a key component.
The course will cover:
- Computational science as the third methodology
- Basic numerics, floating-point representation, errors and exceptions
- Simple ordinary differential equations
- N-body / particle methods
- Dense linear algebra, algorithms and libraries
- Partial differential equations and boundary value problems
- Sparse linear algebra
- Initial value problems and implicit methods
- Spectral methods - Fast Fourier Transforms (FFTs) and applications
- Monte Carlo methods
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| Students are required to be familiar with C, C++ or Fortran for practical exercises. Basic mathematical knowledge is assumed but only at final-year school level.
Information for Visiting Students
|Pre-requisites||Students are required to be familiar with C, C++ or Fortran for practical exercises. Basic mathematical knowledge is assumed but only at final-year school level.
|High Demand Course?
Course Delivery Information
|Academic year 2022/23, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 20,
Supervised Practical/Workshop/Studio Hours 10,
Summative Assessment Hours 2,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
||Written Exam 50%
Coursework 50% (2 assignments)
Written examination comprised of compulsory questions (equally weighted).
Coursework (class test) is an examination question presented to the students mid-Semester
||Provided via practical classes and following examination.
||Hours & Minutes
|Main Exam Diet S1 (December)||Numerical Algorithms for High Performance Computing||2:00|
On completion of this course, the student will be able to:
- Explain why computer simulation is an essential technique in many areas of science, and understand its advantages and limitations.
- Describe how real-valued quantities are represented on a computer and understand the various sources and types of error.
- Understand how physical problems are represented in a discrete form suitable for computer simulation.
- Discuss the appropriate choice of algorithm for different problems.
- Use standard numerical libraries in their own applications.
|Provided via Learn.|
|Graduate Attributes and Skills
||Solution Exploration, Evaluation and Prioritisation.
Computational Science Techniques.
||There are limited spaces on this course. Students not on the MSc in High Performance Computing or MSc High Performance Computing with Data Science should contact the course secretary to confirm availability and confirm that they have the required prerequisites before being enrolled on the course.
The course is available to PhD students for class-only study. PhD students requiring a form of assessment (e.g. SUPA/School of Physics and Astronomy CDT students) must contact the course secretary to confirm method of enrolment.
|Additional Class Delivery Information
||2 lectures per week (weeks 1-10) plus 1 practical per week (weeks 2-11).
|Keywords||NAHPC,Numerical Algorithms,HPC,EPCC,Algebra,Algorithms,Monte Carlo,Computational Science
|Course organiser||Dr William Lucas
Tel: (0131 6)51 3586
|Course secretary||Mr James Richards
Tel: 90131 6)51 3578