Litcius/Paper detail

SECDA-TFLite: A toolkit for efficient development of FPGA-based DNN accelerators for edge inference

Jude Haris, Perry Gibson, José Cano, Nícolas Bohm Agostini, David Kaeli

2022Journal of Parallel and Distributed Computing12 citationsDOIOpen Access PDF

Abstract

In this paper we propose SECDA-TFLite, a new open source toolkit for developing DNN hardware accelerators integrated within the TFLite framework. The toolkit leverages the principles of SECDA , a hardware/software co-design methodology, to reduce the design time of optimized DNN inference accelerators on edge devices with FPGAs . With SECDA-TFLite, we reduce the initial setup costs associated with integrating a new accelerator design within a target DNN framework, allowing developers to focus on the design. SECDA-TFLite also includes modules for cost-effective SystemC simulation, profiling, and AXI-based data communication. As a case study , we use SECDA-TFLite to develop and evaluate three accelerator designs across seven common CNN models and two BERT-based models against an ARM A9 CPU-only baseline, achieving an average performance speedup across models of up to 3.4× for the CNN models and of up to 2.5× for the BERT-based models. Our code is available at https://github.com/gicLAB/SECDA-TFLite .

Topics & Concepts

Computer scienceField-programmable gate arrayInferenceEnhanced Data Rates for GSM EvolutionComputer architectureParallel computingArtificial intelligenceProgramming languageEmbedded systemAdvanced Neural Network ApplicationsAdvanced Memory and Neural ComputingAdversarial Robustness in Machine Learning
SECDA-TFLite: A toolkit for efficient development of FPGA-based DNN accelerators for edge inference | Litcius