High performance network virtualization with SR-IOV

By Yaozu Dong, Xiaowei Yang, Jianhui Li, Guangdeng Liao, Kun Tian, Haibing Guan. International Symposium on High-Performance Computer Architecture, 2010

331 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture, Information Systems

View Paper: https://www.semanticscholar.org/paper/a9a2089b20cc003d5aca16f2a304998392a276bc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Abhishek Dhanotia
2. Akshitha Sriraman
3. David A. Maltz
4. Deepak Bansal
5. Doug Burger
6. Christopher J. Rossbach
7. J. Padhye
8. Thomas F. Wenisch

In Hardware and Architecture

1. Thomas F. Wenisch
2. Doug Burger
3. Christopher J. Rossbach
4. Amogh Akshintala
5. Andrew Putnam
6. Arthur Michener Peters
7. Akshitha Sriraman
8. David A. Maltz

In Information Systems

1. Abhishek Dhanotia
2. Akshitha Sriraman
3. David A. Maltz
4. Christopher J. Rossbach
5. Amogh Akshintala
6. Thomas F. Wenisch
7. Albert G. Greenberg
8. Andrew Putnam

Citations in the corpus

• Azure Accelerated Networking: SmartNICs in the Public Cloud (2018, methodology): “Offloading only exact match flows with 1Azure D v3 series or AWS EC2 m4 series instances, with price varying slightly by region associated actions allows for a tractable hardware design with the full performance of a native SR-IOV hardware solution on all but the first packet of each flow.”
• SoftSKU: Optimizing Server Architectures for Microservice Diversity @Scale (2019, background): “Software/hardware optimizations [54–62] that reduce context switch latency or counts might considerably improve Cache performance.”
• Accelerometer: Understanding Acceleration Opportunities for Data Center Overheads at Hyperscale (2020, background): “Software/hardware optimizations [28, 29, 32, 41, 44, 60, 73, 75, 116] that reduce scheduler latency (e.”
• AvA: Accelerated Virtualization of Accelerators (2020, background): “The technique can provide strong virtualization guarantees [36, 37], but hardware-level resource management is inflexible and unevolvable: current implementations are trivially vulnerable to fragmentation and unfairness pathologies that cannot be changed.”
• This paper is included in the Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16). (unknown): “Despite improved support for hardware virtualization [21, 1, 60], containers retain a performance advantage over virtual machines (VMs) on hypervisors: not only are their startup times faster but also their I/O throughput and latency are superior [22].”