Module Catalogues, Xi'an Jiaotong-Liverpool University   
 
Module Code: DTS205TC
Module Title: High performance computing
Module Level: Level 2
Module Credits: 2.50
Academic Year: 2021/22
Semester: SEM2
Originating Department: Shool of AI and Advanced Computing
Pre-requisites: N/A
   
Aims
The module provides an introduction to High Performance Computing (HPC) and its role in data sciences. In this course you will learn how to write faster code that is optimized for modern multi-core processors and clusters, using modern software development tools, parallelization strategies, and advanced parallel programming constructs in OpenMP and MPI.
Learning outcomes 
A. Appreciate the concepts used in modern processors for increasing the performance.

B. Appreciate optimization techniques for serial code

C. Appreciate parallel computing paradigms

D. Write optimized programs designed for high-performance computing systems.
Method of teaching and learning 
Students will be expected to attend 1 hour of a formal lecture and 1 hours for either a tutorial or a lab section in a typical week. Lectures will introduce students to the academic content. Tutorials will be used to expand the students understanding of lecture materials. In addition, students are expected to devote unsupervised time to private study. Private study will provide time for reflection and consideration of lecture material and background reading.
Syllabus 
1. Fundamental concepts in High Performance Computing – Architecture of microprocessor, optimization techniques for serial code, Data access optimization, Parallel computers

2. Shared memory programming (OpenMP) - Concept of OpenMP, OpenMP-parallel Jacobi algorithm, Wavefront parallelization, Efficient OpenMP programming

3. Message passing programming (MPI) – Concept of MPI, MPI parallelization of a Jacobi solver, Efficient MPI programming

4. Hardware, compilers and performance programming – optimization techniques

5. Performance measurement and estimation - performance evaluation methods

6. Introduction to HPC numerical libraries and auto-tuning libraries

7. Application case study
Delivery Hours  
Lectures Seminars Tutorials Lab/Prcaticals Fieldwork / Placement Other(Private study) Total
Hours/Semester 14    6  6    49  75 

Assessment

Sequence Method % of Final Mark
1 Assignment(Groupwork) 20.00
2 Lab Report 20.00
3 Formal Exam 60.00

Module Catalogue generated from SITS CUT-OFF: 6/5/2020 5:41:24 PM