Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Parallel Computing

Author(s):

N. Kariotoglou, A. Domahidi, S. M. Huck
Conference/Journal:

IfA Internal Seminar Series, Zurich
Abstract:

The purpose of this talk is twofold: To introduce and motivate parallel computing using GPUs and Multi-CPU systems as well as outline the available resources to IfA members. We discuss the basic architectural properties of parallel systems in order to outline the cases where parallel computation offers a great potential to accelerate algorithms. We show how GPUs can be programmed and discuss high level tools which significantly ease the process both in native C and MATLAB. With the aid of a live demo we illustrate significant computational benefits free of the usual time-consuming code development process for GPUs. The GPU-related part of the talk is based on a workshop offered at the Swiss National Supercomputing Centre in late March of 2011. In the second part, we introduce Brutus, the central high performance computing cluster at ETH, and give you an overview of the potential to shift your computations to the cluster and how to get successfully started.

Year:

2011
Type of Publication:

(06)Talk
Supervisor:



File Download:

Request a copy of this publication.
(Uses JavaScript)
% No recipe for automatically generating a BibTex entry for (06)Talk
Permanent link