Exploring a Layer-based Pre-implemented Flow for Mapping CNN on FPGA

Kwadjo, Danielle Tchuinkou; Mbongue, Joel Mandebi; Bobda, Christophe

doi:10.1109/ipdpsw52791.2021.00025

Cited by 4 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will investigate architectural and dataflow strategies to reduce inference time, which at present is not the metric that our toolflow prioritizes. To provide an exhaustive overview, it should be specified that the selected works for MobileNet-V1 [75], [76] are handtuned accelerators. In terms of FXP accuracy, FPG-AI outperforms the other reported works for the LeNet and NiN models.…”

Section: Comparison With Related Workmentioning

confidence: 99%

FPG-AI: A Technology-Independent Framework for the Automation of CNN Deployment on FPGAs

2023

View full text Add to dashboard Cite

In recent years, Convolutional Neural Networks (CNNs) have demonstrated outstanding results in several emerging classification tasks. The high-quality predictions are often achieved with computationally intensive workloads that hinder the hardware acceleration of these models at the edge. Field Programmable Gate Arrays (FPGAs) have proven to be energy efficient platforms for the execution of these algorithms and works proposing methods for automating the design on these devices have acquired relevance. The common purpose is to enable a wide range of users without specific skills to accelerate CNNs on FPGAs with reduced development times. In this paper, we present FPG-AI, a technology-independent toolflow for automating the deployment of CNNs on FPGA. The framework combines the use of model compression strategies with a fully handcrafted Hardware Description Languages (HDL)-based accelerator that poses no limit on device portability. On top of that, an automation process merges the two design spaces to define an end-to-end and ready-to-use tool. Experimental results are reported for reference models extracted from the literature (LeNet, NiN, VGG16, MobileNet-V1) on multiple classification datasets (MNIST, CIFAR10, ImageNet). To prove the technology independence of FPG-AI, we characterize the toolflow on devices with heterogeneous resource budgets belonging to different vendors (Xilinx, Intel, and Microsemi). Comparison with state-of-the-art work confirms the unmatched device portability of FPG-AI and shows performance metrics in line with the literature.

show abstract

Section: Comparison With Related Workmentioning

confidence: 99%

FPG-AI: A Technology-Independent Framework for the Automation of CNN Deployment on FPGAs

2023

View full text Add to dashboard Cite

show abstract

Towards a component-based acceleration of convolutional neural networks on FPGAs

Kwadjo

Tchinda

Mbongue

et al. 2022

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Deploying Multi-tenant FPGAs within Linux-based Cloud Infrastructure

Mandebi

Tchuinkou

ShupingAlex

et al. 2021

ACM Trans. Reconfigurable Technol. Syst.

View full text Add to dashboard Cite

Cloud deployments now increasingly exploit Field-Programmable Gate Array (FPGA) accelerators as part of virtual instances. While cloud FPGAs are still essentially single-tenant, the growing demand for efficient hardware acceleration paves the way to FPGA multi-tenancy. It then becomes necessary to explore architectures, design flows, and resource management features that aim at exposing multi-tenant FPGAs to the cloud users. In this article, we discuss a hardware/software architecture that supports provisioning space-shared FPGAs in Kernel-based Virtual Machine (KVM) clouds. The proposed hardware/software architecture introduces an FPGA organization that improves hardware consolidation and support hardware elasticity with minimal data movement overhead. It also relies on VirtIO to decrease communication latency between hardware and software domains. Prototyping the proposed architecture with a Virtex UltraScale+ FPGA demonstrated near specification maximum frequency for on-chip data movement and high throughput in virtual instance access to hardware accelerators. We demonstrate similar performance compared to single-tenant deployment while increasing FPGA utilization, which is one of the goals of virtualization. Overall, our FPGA design achieved about 2× higher maximum frequency than the state of the art and a bandwidth reaching up to 28 Gbps on 32-bit data width.

show abstract

Exploring a Layer-based Pre-implemented Flow for Mapping CNN on FPGA

Cited by 4 publications

References 14 publications

FPG-AI: A Technology-Independent Framework for the Automation of CNN Deployment on FPGAs

FPG-AI: A Technology-Independent Framework for the Automation of CNN Deployment on FPGAs

Towards a component-based acceleration of convolutional neural networks on FPGAs

Deploying Multi-tenant FPGAs within Linux-based Cloud Infrastructure

Contact Info

Product

Resources

About