A study of reconfigurable accelerators for cloud computing

Mohammedali, N. and Opoku Agyeman, M. (2018) A study of reconfigurable accelerators for cloud computing. In: International Symposium on Computer Science and Intelligent Control. Sweden: ISCSIC. (Accepted)

The files below are currently restricted to repository staff only.

They may be awaiting processing or under a publisher's embargo.

Items under embargo will be available for download from the date noted.

Untitled (200kB)

Item Type:	Book Section
Abstract:	Due to the exponential increase in network traffic in the data centers, thousands of servers interconnected with high bandwidth switches are required. Field Programmable Gate Arrays (FPGAs) with Cloud ecosystem offer high performance in efficiency and energy, making them active resources, easy to program and reconfigure. This paper looks at FPGAs as reconfigurable accelerators for the cloud computing presents the main hardware accelerators that have been presented in various widely used cloud computing applications such as: MapReduce, Spark, Memcached, Databases.
Additional Information:	Paper presented at the 2nd International Symposium on Computer Science and Intelligent Control (ISCSIC 2018) held in Stockholm, Sweden, 21-23 September 2018.
Uncontrolled Keywords:	Reconfigurable computing, hardware accelerator, SPARK, reconfigurable architectures, cloud computing, FPGAs, data centers
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science > QA76.585 Cloud computing
Creators:	Mohammedali, Noor and Opoku Agyeman, Michael ORCID: 0000-0002-3734-4451
Publisher:	ISCSIC
Faculties, Divisions and Institutes:	Faculties > Faculty of Arts, Science & Technology > Computing
Date:	20 April 2018
Date Type:	Acceptance
Title of Book:	International Symposium on Computer Science and Intelligent Control
Place of Publication:	Sweden
Event Type:	Conference
Language:	English
Status:	Accepted
Refereed:	Yes
URI:	http://nectar.northampton.ac.uk/id/eprint/10311

Actions (login required)

Edit Item

Altmetric