FPGAs for Network Function Virtualization: Challenges in Placement and Partitioning

In the Network Function Virtualization paradigm, Field Programmable Gate Arrays (FPGAs) can be used to reduce bottlenecks introduced by the substitution of dedicated hardware middleboxes by virtualized implementations. Employing virtual function implementations leads to easier maintenance and deployment, allowing a more flexible infrastructure. However, where to place and how to efficiently share these computational resources are crucial tasks as we seek to achieve the best possible use of the infrastructure. In this work, we will demonstrate the importance of adequate FPGA placement and partitioning in a network to make effective use of the reconfigurable resources.