LaKe: The Power of In-Network Computing
View / Open Files
Authors
Tokusashi, Yuta
Matsutani, Hiroki
Zilberman, N
Publication Date
2018Journal Title
2018 International Conference on Reconfigurable Computing and FPGAs, ReConFig 2018
Conference Name
RecCnfig 2018: International Conference on Reconfigurable Computing and FPGAs
ISSN
2325-6532
ISBN
9781728119687
Publisher
IEEE
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Tokusashi, Y., Matsutani, H., & Zilberman, N. (2018). LaKe: The Power of In-Network Computing. 2018 International Conference on Reconfigurable Computing and FPGAs, ReConFig 2018 https://doi.org/10.1109/RECONFIG.2018.8641696
Abstract
In-network computing accelerates applications natively running on the host by executing them within network devices. While in-network computing offers significant performance improvements, its limitations and design trade-offs have not been explored. To usefully and efficiently run applications within the network, we first need to understand the implications of their design. In this work we introduce LaKe, a Layered Key-Value Store design, running as an in-network application. LaKe is a scalable design, enabling the exploration of design decisions and their effect on throughput, latency and power efficiency. LaKe achieves full line rate throughput, while maintaining a latency of 1.1μs and better power efficiency than existing hardware based memcached designs.
Sponsorship
This work was supported by JSPS Research Fellowship and Keio University Research Grant for Young Researcher’s Program. This work was supported by JST CREST Grant Number JPMJCR1785, Japan. We acknowledge the support of the Leverhulme Trust (ECF-2016-289) and the Isaac Newton Trust.
Funder references
Leverhulme Trust (ECF-2016-289)
Isaac Newton Trust (1608(as))
Identifiers
External DOI: https://doi.org/10.1109/RECONFIG.2018.8641696
This record's URL: https://www.repository.cam.ac.uk/handle/1810/288017
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.