Projects per year
Abstract
How can GPU acceleration be obtained as a service in a cluster? This question has become increasingly significant due to the inefficiency of installing GPUs on all nodes of a cluster. The research reported in this paper is motivated to address the above question by employing rCUDA (remote CUDA), a framework that facilitates Acceleration-as-a-Service (AaaS), such that the nodes of a cluster can request the acceleration of a set of remote GPUs on demand. The rCUDA
framework exploits virtualisation and ensures that multiple nodes can share the same GPU. In this paper we test the feasibility of the rCUDA framework on a real-world application employed in the financial risk industry that can benefit from AaaS in the production setting. The results confirm the feasibility of rCUDA and highlight that rCUDA achieves similar performance compared to CUDA, provides consistent results, and more importantly, allows for a single application to benefit from all the GPUs available in the cluster without loosing efficiency.
framework exploits virtualisation and ensures that multiple nodes can share the same GPU. In this paper we test the feasibility of the rCUDA framework on a real-world application employed in the financial risk industry that can benefit from AaaS in the production setting. The results confirm the feasibility of rCUDA and highlight that rCUDA achieves similar performance compared to CUDA, provides consistent results, and more importantly, allows for a single application to benefit from all the GPUs available in the cluster without loosing efficiency.
Original language | English |
---|---|
Title of host publication | 2015 IEEE 11th International Conference on e-Science (e-Science) (2015) |
Publisher | IEEE Computer Society |
Number of pages | 10 |
Publication status | Published - 1 Sept 2015 |
Event | 11th IEEE International Conference on eScience - Ludwig-Maximilians-Universität , Munich, Germany Duration: 31 Aug 2015 → 4 Sept 2015 http://escience2015.mnm-team.org/ |
Conference
Conference | 11th IEEE International Conference on eScience |
---|---|
Country/Territory | Germany |
City | Munich |
Period | 31/08/15 → 4/09/15 |
Internet address |
Keywords
- rCUDA
- GPU computing
- Virtualisation
- Acceleration-as-a-service
- CUDA
Fingerprint
Dive into the research topics of 'Acceleration-as-a-Service: exploiting virtualised GPUs for a financial application'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Working Together in ICT: Working Together: Constraint Programming and Cloud Computing
Miguel, I. J. (PI) & Barker, A. D. (CoI)
1/01/13 → 30/09/16
Project: Standard