TRAP@NCI

Automated instantiantion of heterogenous FastFlow CPU/GPU parallel pattern applications in Clouds

Boob, Suresh (2013) Automated instantiantion of heterogenous FastFlow CPU/GPU parallel pattern applications in Clouds. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview

Abstract

Parallel scientific workloads typically entail highly customised software environments, involving complex data structures, specialised systems software and even distinct hardware, where virtualisation is not necessarily supported by third-party providers. Considering the expansion of cloud computing in different domains and the development of different proprietary and open source cloud platforms, users should arguably be able to automatically and seamlessly migrate their parallel workloads across cloud platforms using standardised virtual machines based on elasticity rules. However, even if migrating the workload between the nodes is easier when the nodes have similar configuration on the same platform, the transition between different platforms raises different issues such as vendor lock-in, portability and interoperability.

Moreover, the static distribution of virtual appliances was not proved straightforward because of the time required for user to do all the migrations steps and because of the vendor lock-in issues.

The aim of this paper is to automate the portability of FastFlow|a C/C++ pattern-based programming framework for multi/many-core and distributed platforms|using virtual machines for both CPU and GPU-based environments between heterogeneous virtualised platforms. Our approach relies on the standard Open Virtualization Format (OVF) in order to achieve a universal description of virtual appliances. Such description is not only useful to migrate but also to determine the hardware/system software configuration needed for switching into any new (cloud) image format. We have successfully evaluated our work using virtual machines based on VirtualBox and AWS on local cluster and public cloud providers.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software

T Technology > T Technology (General) > Information Technology > Cloud computing
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 29 Nov 2013 12:21
Last Modified: 29 Nov 2013 12:21
URI: http://trap.ncirl.ie/id/eprint/896

Actions (login required)

View Item View Item