An Open-source Framework for Integrating Heterogeneous Resources in Private Clouds

摘要

Heterogeneous hardware acceleration architectures are becoming an important tool for achieving high performance in cloud computing environments. Both FPGAs and GPUs provide huge computing capabilities over large amounts of data. At the same time, energy efficiency is a big concern in nowadays computing systems. In this paper we propose a novel architecture aimed at integrating hardware accelerators into a Cloud Computing infrastructure, and making them available as a service. The proposal harnesses advances in FPGA dynamic reconfiguration and efficient virtualization technology to accelerate the execution of certain types of tasks. In particular, applications that can be described as Big Data would greatly benefit from the proposed architecture.