Advanced search
Start date
Betweenand

Exploration of an FPGA-orientated hardware infrastructure for ultra-low latency DNN deployment.

Grant number: 19/05286-6
Support type:Scholarships abroad - Research
Effective date (Start): October 01, 2019
Effective date (End): September 30, 2020
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computer Systems
Principal researcher:Vanderlei Bonato
Grantee:Vanderlei Bonato
Host: Christos-Savvas Bouganis
Home Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
Research place: Imperial College London, England  

Abstract

The adoption of Deep Neural Networks on real time systems requires a special attention to thelatency of the network inference stage. The signal propagation delay through layers stronglydepends on memory organisation, network connectivity balance, and on the level of computing parallelisation along with the operations complexity. Recent works demonstrated promising results from design space exploration techniques for multi-objective metrics, considering latency, accuracy, and computational resources. However, when ultra low latency is desired the challenge remains since it does a strong pressure on computational resources requiring not only architectural improvements, but also further problem-orientated optimisations provided by highly customised hardware components. This research project aims to explore the conditions to enable ultra low latency deployments of CNN and LSTM-based models on FPGAs, having as case study the High Frequency Trading problem.

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
BONATO, VANDERLEI; BOUGANIS, CHRISTOS-SAVVAS. Class-specific early exit design methodology for convolutional neural networks. APPLIED SOFT COMPUTING, v. 107, AUG 2021. Web of Science Citations: 0.

Please report errors in scientific publications list by writing to: cdi@fapesp.br.