The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.
|Author:||Ralf Kundel, Tim Burkert, Carsten Griwodz, Boris Koldehofe|
|Kind:||In proceedings - use for conference & workshop papers|
|Publisher:||Association for Computing Machinery|
|Book title:||Proceedings of the 20th International Middleware Conference Demos and Posters|
|Keywords:||VNF, PCIe, FPGA, GPU, hardware acceleration, offloading, network function chaining|
|Abstract:||The growth of compute-intensive applications causes an increasing demand for computing resources in both data centers and underlying networks. To satisfy these computing and networking demands, hardware-accelerated computing with GPUs and FPGAs becomes more and more prevalent. However, current approaches of accelerated Virtual Network Functions (VNF), typically based on PCIe accelerator cards, suffer from many superfluous data transfers between the memory of hosts and accelerator devices. In this work we propose “host bypassing” for chained hardware-accelerated network functions, which reduces memory copying to a minimum, which increases throughput and reduces latency.|
|Full paper (pdf)|