NEWROMAP

IEEE/ACM International Symposium on Networks-on-Chip (NOCS), pp. 15–20

Abstract

Conventional AI accelerators are limited by von-Neumann bottlenecks for edge workloads. Domain-specific accelerators (often neuromorphic) solve this by applying near/in-memory computing, NoC-interconnected massive-multicore setups, and data-flow computation. This requires an effective mapping of neural networks (i.e, an assignment of network layers to cores) to balance resources/memory, computation, and NoC traffic. Here, we introduce a mapping called Snake for the predominant convolutional neural networks (CNNs). It utilizes the feed-forward nature of CNNs by folding layers to spatially adjacent cores. We achieve a total NoC bandwidth improvement of up to 3.8X for MobileNet and ResNet vs. random mappings. Furthermore, NEWROMAP is proposed that continues to optimize Snake mapping through a meta-heuristic; it also simulates the NoC traffic and can work with TensorFlow models. The communication is further optimized with up to 22.52% latency improvement vs. pure snake mapping shown in simulations.

Authors 5

1. Jan Moritz Joseph Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Germany

2. Murat Sezgin Baloglu Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Germany

3. Yue Pan

   Georgia Institute of Technology

   Affiliation as printed

   Georgia Institute of Technology

4. Rainer Leupers Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Germany

5. Lennart Bamberg
   Affiliation as printed

   GrAI Matter Labs, The Netherlands