28104

Task parallelism-based architectures on FPGA to optimize the energy efficiency of AI at the edge

Rafael Gadea-Gironés, Jorge Fe, Jose M. Monzo
Institute for Molecular Imaging Technologies (I3M), Universitat Politècnica de València, Valencia, 46022, Spain
Microprocessors and Microsystems, Volume 98, 104824, 2023

@article{gadea2023task,

   title={Task parallelism-based architectures on FPGA to optimize the energy efficiency of AI at the edge},

   author={Gadea-Giron{‘e}s, Rafael and Fe, Jorge and Monzo, Jose M},

   journal={Microprocessors and Microsystems},

   pages={104824},

   year={2023},

   publisher={Elsevier}

}

Download Download (PDF)   View View   Source Source   

547

views

In the world of artificial intelligence (AI) at the edge, we need to focus primarily on the energy efficiency with which we approach deep neural network (DNN) applications. In many applications, the speed of obtaining an inference can be critical; but many applications easily meet their time requirements, and the energy needed to calculate the huge numbers of multiplication and addition operations of DNNs becomes the essential element. We have provided systolic architectural solutions written in C++ and OpenCL that are highly flexible and easily tunable to take full advantage of the resources of programmable devices and achieve superior energy efficiencies. We focused on low-cost solutions with soft macro microprocessors (Nios2) and hard macro microprocessors (ARM cortex A9).
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: