FPGA Acceleration by Dynamically-Loaded Hardware Libraries

Andrea Lomuscio, Alberto Nannarelli, Marco Re

Research output: Book/ReportReportResearch

15724 Downloads (Pure)

Abstract

Hardware acceleration is a viable solution to obtain energy efficiency in data intensive computation.

In this work, we present a hardware framework to dynamically load hardware libraries, HLL, on reconfigurable platforms (FPGAs). Provided a library of application-specific processors, we load on-the-y the speciffic processor in the FPGA, and we transfer the execution from the CPU to the FPGA-based accelerator.

Results show that significant speed-up and energy efficiency can be obtained by HLL acceleration on system-on-chips where reconfigurable fabric is placed next to the CPUs.
Original languageEnglish
Place of PublicationKgs. Lyngby
PublisherTechnical University of Denmark
Number of pages19
Publication statusPublished - 2016
SeriesDTU Compute-Technical Report-2016
Number3
ISSN1601-2321

Fingerprint Dive into the research topics of 'FPGA Acceleration by Dynamically-Loaded Hardware Libraries'. Together they form a unique fingerprint.

Cite this