RC3E: Provision and Management of Reconfigurable Hardware Accelerators in a Cloud Environment
read the original abstract
Heterogeneous systems consisting of general-purpose processors and different types of hardware accelerators are becoming more and more common in HPC systems. Especially FPGAs provide a promising opportunity to improve both performance and energy efficiency of such systems. Adding FPGAs to clouds or data centers allows easy access to such reconfigurable resources. In this paper we present our cloud service models and cloud hypervisor called RC3E, which integrates virtualized FPGA-based hardware accelerators into a cloud environment. With our hardware and software framework, multiple (virtual) user designs can be executed on a single physical FPGA device. We demonstrate the performance of our approach by implementing up to four virtual user cores on a single device and present future perspectives for FPGAs in cloud-based data environments.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
THEMIS: Time, Heterogeneity, and Energy Minded Scheduling for Fair Multi-Tenant Use in FPGAs
THEMIS improves multi-tenant FPGA scheduling fairness by 24.2-98.4% over prior methods via spatiotemporal metrics, energy-aware intervals, and heterogeneous region handling, evaluated on Xilinx Zedboard XC7Z020.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.