A Comprehensive Methodology to Optimize FPGA Designs via the Roofline Model

Autor: Marco Rabozzi, Samuel Williams, Lorenzo Di Tucci, Donatella Sciuto, Marco Siracusa, Emanuele Delsozzo, Marco D. Santambrogio

Publikováno v: IEEE Transactions on Computers, vol 71, iss 8
IEEE Transactions on Computers, vol PP, iss 99

Author(s): Siracusa, M; Delsozzo, E; Rabozzi, M; Di Tucci, L; Williams, S; Sciuto, D; Santambrogio, MD | Abstract: With reconfigurable fabrics delivering increasing performance over the years, Field-Programmable Gate Arrays (FPGAs) are becoming an ap

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10aeb5cc97804704af39840e7b52bd9c
https://doi.org/10.1109/tc.2021.3111761

The Importance of Being X-Drop: High Performance Genome Alignment on Reconfigurable Hardware

Autor: Marco Rabozzi, Marco D. Santambrogio, Alberto Zeni, Lorenzo Di Tucci, Guido Walter Di Donato

Publikováno v: FCCM

Pairwise sequence alignment accounts for the majority of key genome analysis applications’ runtime. Because of the quadratic time complexity of exact alignment algorithms, the community is moving away from exact algorithms in favor of heuristics th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01c975e86078fb6c3af2bb28f5216d94
https://doi.org/10.1109/fccm51124.2021.00023

Pareto Optimal Design Space Exploration for Accelerated CNN on FPGA

Autor: Marco Rabozzi, Luca Stornaiuolo, Enrico Reggiani, Alberto Scolari, Anna Maria Nestorov, Marco D. Santambrogio

Publikováno v: IPDPS Workshops

Convolutional Neural Networks (CNNs) are at the base of many applications, both in embedded and in server-class contexts. While Graphics Processing Units (GPUs) are predominantly used for training, solutions for inference often rely on Field Programm

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10a38ab54044b96b55686604839caa21
https://doi.org/10.1109/ipdpsw.2019.00028

Automated Acceleration of Dataflow-Oriented C Applications on FPGA-Based Systems

Autor: Alex J. W. Thom, Lorenzo Di Tucci, Marco Rabozzi, Francesco Peverelli, Emanuele Del Sozzo, Salvatore Cardamone, Marco D. Santambrogio

Publikováno v: FCCM

The acceleration of compute-intensive applications on FPGA-based systems has become an increasingly common trend thanks to their availability as cloud commodities. This trend has also been accompanied by wider support of High-Level Synthesis tools. D

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::54c9f87670abc8c7ae41e9cc4a23a2eb
https://doi.org/10.1109/fccm.2019.00054

Building High-Performance, Easy-to-Use Polymorphic Parallel Memories with HLS

Autor: Marco Rabozzi, Marco D. Santambrogio, Luca Stornaiuolo, Giulio Stramondo, Ana Lucia Varbanescu, Donatella Sciuto, Catalin Bogdan Ciobanu

Publikováno v: VLSI-SoC: Design and Engineering of Electronics Systems Based on New Computing Paradigms ISBN: 9783030234249
VLSI-SoC (Selected Papers)

With the increased interest in energy efficiency, a lot of application domains experiment with Field Programmable Gate Arrays (FPGAs), which promise customized hardware accelerators with high-performance and low power consumption. These experiments p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::787e629d912a8639ac21fd37801c4952
https://doi.org/10.1007/978-3-030-23425-6_4