NeuroCGRA: A CGRA with support for neural networks

: Syed M. A. H. Jafri, Tuan Nguyen, Sergei Dytckov, Masoud Daneshtalab, Ahmed Hemani, Juha Plosila, Hannu Tenhunen

: International conference on high performance computing and simulation

: 2014

: High Performance Computing & Simulation (HPCS), 2014 International Conference on

: 506

: 511

: 6

: 978-1-4799-5312-7

: 978-1-4799-5313-4

DOI: https://doi.org/10.1109/HPCSim.2014.6903727

: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6903727

Coarse Grained Reconfigurable Architectures

(CGRAs) are emerging as enabling platforms to meet the high

performance demanded by modern embedded applications. In

many application domains (e.g. robotics and cognitive embedded

systems), the CGRAs are required to simultaneously host

processing (e.g. Audio/video acquisition) and estimation (e.g.

audio/video/image recognition) tasks. Recent works have revealed

that the efficiency and scalability of the estimation algorithms

can be significantly improved by using neural networks.

However, existing CGRAs commonly employ homogeneous

processing resources for both the tasks. To realize the best of

both the worlds (conventional processing and neural networks),

we present NeuroCGRA. NeuroCGRA allows the processing

elements and the network to dynamically morph into either

conventional CGRA or a neural network, depending on the

hosted application. We have chosen the DRRA as a vehicle to

study the feasibility and overheads of our approach. Simulation

using edge detection reveal that the neural networks can

successfully process real-time video for up to 1M pixels.

Synthesis results reveal that the proposed enhancements incur

negligible overheads (4.4% area and 9.1% power) compared to

the original DRRA cell.

NeuroCGRA.pdf