Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/61BA7D37-60AC-4117-9EF1-47C5F73A44B1 | ||
| Year | 2021 | ||
| Type of Item | Conference Full Paper | ||
| License |
|
||
| Bibliographic Citation | D. Theodoropoulos, A. Brokalakis, N. Alachiotis and D. Pnevmatikatos, "EDRA: a hardware-assisted decoupled access/execute framework on the digital market," in Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021, vol. 13227, Lecture Notes in Computer Science, A. Orailoglu, M. Jung, M. Reichenbach, Eds., Cham, Switzerland: Springer, 2022, pp. 319–330, doi: 10.1007/978-3-031-04580-6_21. https://doi.org/10.1007/978-3-031-04580-6_21 | ||
| Appears in Collections |
EDRA was an Horizon 2020 FET Launchpad project that focused on the commercialization of the Decoupled Access Execution Reconfigurable (DAER) framework - developed within the FET-HPC EXTRA project - on Amazon’s Elastic Cloud (EC2) Compute FPGA-based infrastructure. The delivered framework encapsulates DAER into a EC2 virtual machine (VM), and uses a simple, directive-based, high-level application programming interface (API) to facilitate application mapping to the underlying hardware architecture. EDRA’s Minimum Viable Product (MVP) is an accelerator for the Phylogenetic Likelihood Function (PLF), one of the cornerstone functions in most phylogenetic inference tools, achieving up to 8x performance improvement compared to optimized software implementations. Towards entering the market, research revealed that Europe is an extremely promising geographic region for focusing the project efforts on dissemination, MVP promotion and advertisement.
Copyright © DIAS 2013
