The accelerator is comprised of 4 heterogeneous engines - input engine, filter engine, post processing engine, and output engine. The specialized engines ...

Abstract—We describe a programmable and scalable Convolu tional Neural Network (CNN) hardware accelerator optimized for mobile and edge inference computing.

This work describes a programmable and scalable Convolutional Neural Network (CNN) hardware accelerator optimized for mobile and edge inference computing ...

We tackle these issues by proposing a template of heterogeneous shared memory cluster which scales to a large number of accelerators, achieving up to 40% better ...

Apr 9, 2021 · In this paper, we describe the architecture of a heterogeneous hardware accelerator for CNN inference using the MobileNet V2 network. The ...

In this paper, we first analyze ConvNet models to find one that is most suitable for a low-cost FPGA implementation.

Apr 9, 2021 · In this paper, we present a scalable, low power, low resource-utilization accelerator architecture for inference on the MobileNet V2 CNN.

This paper proposes a novel end-to-end heterogeneous acceleration framework for CNN inference on FPGAs, named Pflow.

A scalable, low power, low resource-utilization accelerator architecture for inference on the MobileNet V2 CNN that consumes 7.35 W of power and uses less ...

Oct 11, 2024 · We benchmark MATCH on two different heterogeneous MCUs: GAP9 [2] , featuring an 8 RISC-V cores cluster and a flexible DNN HW accelerator, and ...