DeepAI AI Chat
Log In Sign Up

METRO: A Software-Hardware Co-Design of Interconnections for Spatial DNN Accelerators

by   Zhao Wang, et al.

Tiled spatial architectures have proved to be an effective solution to build large-scale DNN accelerators. In particular, interconnections between tiles are critical for high performance in these tile-based architectures. In this work, we identify the inefficiency of the widely used traditional on-chip networks and the opportunity of software-hardware co-design. We propose METRO with the basic idea of decoupling the traffic scheduling policies from hardware fabrics and moving them to the software level. METRO contains two modules working in synergy: METRO software scheduling framework to coordinate the traffics and METRO hardware facilities to deliver the data based on software configurations. We evaluate the co-design using different flit sizes for synthetic study, illustrating its effectiveness under various hardware resource constraints, in addition to a wide range of DNN models selected from real-world workloads. The results show that METRO achieves 56.3 to 73.6 network designs.


Resistive Neural Hardware Accelerators

Deep Neural Networks (DNNs), as a subset of Machine Learning (ML) techni...

Enumerating Hardware-Software Splits with Program Rewriting

A core problem in hardware-software codesign is in the sheer size of the...

Dijkstra-Through-Time: Ahead of time hardware scheduling method for deterministic workloads

Most of the previous works on data flow optimizations for Machine Learni...

CoSA: Scheduling by Constrained Optimization for Spatial Accelerators

Recent advances in Deep Neural Networks (DNNs) have led to active develo...

TensorLib: A Spatial Accelerator Generation Framework for Tensor Algebra

Tensor algebra finds applications in various domains, and these applicat...

Towards hardware acceleration for parton densities estimation

In this proceedings we describe the computational challenges associated ...