Update: Registration starts on Monday August 15 at 08.15 in front of lecture room E3

Registration starts on Monday August 15 at 08.15 in front of lecture room E3

In this presentation, an overview of the computing landscape in Sweden and internationally will be given. Also, two concrete examples of scientific computing problems in different disciplines will be described and the impact of models, numerical methods, implementation and computer architecture will be discussed.

Two common ways of speeding up programs are to use processes or threads executing in parallel. The second week of the Summer School presents process-based parallel computing using MPI. In this lecture parallelization using threads will be discussed. Threads can be managed in different ways, e.g. using a low level library, like the POSIX threads library. The lecture deals with OpenMP, which is a more convenient way to use threads. OpenMP is a specification for a set of compiler directives, library routines, and environment variables that can be used to specify shared memory parallelism in Fortran and C/C++ programs. The threaded program can be executed on a shared memory computer (e.g. a multi- core processor). Typically, the iterations of a time consuming loop are shared among a team of threads, each thread working on part of the iterations. The loop is parallelized by writing a directive in the code and a compiler or a pre- processor will generate parallel code. Using short code examples, the lecture covers the most important OpenMP-constructs, how to use them and how not to use them. A few more realistic examples are presented as well.

See preceding description.

See preceding description.

Today everyone is positioning GPUs for general purpose computing. They claim that you can get 10-100x speedups over conventional CPUs, and sometimes they're even right. However, to get the most out of current- (and next-) generation GPUs, one needs to understand the architectural differences and how they effect your choice of algorithm. In this talk I will cover GPU architecture in comparison to current CPUs, discuss the implications for getting good performance, and introduce OpenCL as a general-purpose programming language for accessing GPUs and CPUs today.

Brain science is a rapidly growing application area for supercomputers with a main focus on data analysis of large volumes of data generated from measurements on the brain and on simulations of brain dynamics. The talk will mostly dwell on the latter aspect, first describing briefly some structural and functional aspects of the brain and standard methodology used in computational neuroscience to simulate activity of neurons and networks. Then follows some examples from our own investigations of perceptual and memory functions of the brain using simulation models with varying degrees of biophysical detail. Finally, our experience from performing very large-scale simulations and scaling of models to actual brain size on the Blue Gene architecture will be described.

A programming language that is able to abstract the peculiarities of parallel programming on a higher level and deliver good performance and scalability will be a key to harness the vast amount of parallelism available in current and future high-end systems. This lecture gives an overview of the different ways parallelism is expressed in languages designed for -or used in- High Performance Computing. The aim of the lecture is to give students an understanding of the technical possibilities and limitations of those languages. We will have a look at the way parallelism is abstracted and briefly discuss how difficult it is to produce efficient code by the compiler.

Cloud computing is one of the key business and technology trends impacting every aspect of the ICT industry. While the IT industry was succesful in pushing down the cost of computation and storage, signifcant challenges remain in the areas of networking, SLA enforcement and security, traditionally areas of strength for telecom companies. In this talk we analyze the impact and opportunities of the cloud computing paradigm for the telecommunication companies, both as users as well as provider of cloud-based solutions. Based on the identified opportunities, we describe the key technological and operational innovations that can help streamline operations of telecommunication companies and, at the same time, generate new revenue streams through differentiating solutions.