• Description

In this subject inside the Máster of Computational Engineering, will try to deepen in the field of the High Performance Computation (HPC), seeing the different possibilities that offers us this field,  the different levels of paradigms of programming, parallel and distributed applications, and the different hardware/software architectural solutions, that allow us work in this field (supercomputing, distributed systems, or new architectures like the GPUs).

We will examine architectures of high performance, its models by parallel and distributed computation, and some middlewares for the computational Grid and Cloud.  Also we will observe the different concepts around Green Computing, as new paradigm that incorporates the idea of optimisation of consumption, in addition to maximise the system performance.

• Information prior to enrolment

In this course, the main language to used is english, e.g. the reference materials to be used and the activities. Also in different  course subjects we will use some current articles on the field of high performance computing, which are written in English.

For this reason it is recommended to have a sufficient level of understanding of technical English.

• Description: This course allows the student to know the concepts and acquire the necessary competences to design and develop computational solutions based on high performance computing, as an alternative to traditionally sequential systems. It addresses the process and communications design techniques needed to develop applications that take advantage of the computing resources of today's computing architectures. Allowing the migration from classic algorithms to new optimized algorithms aware of the architecture that allow to obtain better computational performance.

• Requirements: Basic programming knowledge (C or Fortran) and GNU / Linux environments at the user level.

• Bibliography: Using the UOC Modules, the reference textbook, and other recomended biblography and research papers.
  

• Software: GNU gcc (C/C ++/Fortran compiler) and GNU/Linux distributions like Ubuntu/CentOS.

• Learning objectives and results

In this couse we plan to obtain the tools you will need to achieve the following objectives:

1. Understand the motivations behind high performance computing and parallelism.

2. Understand the fundamentals of parallelism, parallel architectures, and programming models, including those related to shared-memory systems and distributed-memory systems.

3. Learn about the fundamental concepts for programming GPU devices using graphic computing programming models.

4. Understand the fundamentals related to management systems for high performance systems and their components, planning policies, and performance and analysis for high performance systems.

5. Understand the fundamentals and technologies related to distributed computing as well as the paradigms of grid and cloud computing, including their relationship with high performance computing.

6. Understand the fundamentals, characteristics, and main lines of research related to green computing and energy efficiency, as well as to sustainable computing and sustainability.

7. Understand the current challenges facing high performance computing.

• Content

Module 1 Introduction to high performance computing

1. Motivations behind high performance computing
2. Parallelism and parallel architectures
3. Programming parallel applications
4. Performance for parallel applications
5. Challenges for high performance computing

Module 2 High performance architectures

1. Functional and data decomposition
2. Flynn's taxonomy
3. SIMD processor architectures
4. Multithread or MIMD processor architectures
5. Many-core architectures: the case of the Intel Xeon Phi

Module 3 Parallel programming and computing

1. Shared-memory programming models
2. Graphics programming models
3. Programing models for distributed memory
4. Parallel algorithmic schemes

Module 4 High performance computing system architectures

1. Organization of high performance systems
2. Interconnection networks
3. File systems for high performance systems
4. Job scheduler and resource managers

Module 5 Introduction to high performance distributed computing

1. Fundamentals of distributed computing
2. Grid computing
3. Cloud computing

Module 6 Green computing

1. Fundamentals and basic concepts
2. Energy efficiency
3. Sustainable computing and sustainability
4. List of recommended reading

• View the UOC learning resources used in the subject

• Guidelines on assessment at the UOC

The assessment process is based on the student's personal work and presupposes authenticity of authorship and originality of the exercises completed.

Lack of authenticity of authorship or originality of assessment tests, copying or plagiarism, the fraudulent attempt to obtain a better academic result, collusion to copy or concealing or abetting copying, use of unauthorized material or devices during assessment, inter alia, are offences that may lead to serious academic or other sanctions.

Firstly, you will fail the course (D/0) if you commit any of these offences when completing activities defined as assessable in the course plan, including the final tests. Offences considered to be misconduct include, among others, the use of unauthorized material or devices during the tests, such as social media or internet search engines, or the copying of text from external sources (internet, class notes, books, articles, other students' essays or tests, etc.) without including the corresponding reference.

And secondly, the UOC's academic regulations state that any misconduct during assessment, in addition to leading to the student failing the course, may also lead to disciplinary procedures and sanctions.

The UOC reserves the right to request that students identify themselves and/or provide evidence of the authorship of their work, throughout the assessment process, and by the means the UOC specifies (synchronous or asynchronous). For this purpose, the UOC may require students to use a microphone, webcam or other devices during the assessment process, and to make sure that they are working correctly.

The checking of students' knowledge to verify authorship of their work will under no circumstances constitute a second assessment.

• View the assessment model