arXiv Open Access 2023

Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCs

Halima Bouzidi Mohanad Odema Hamza Ouarnoughi Smail Niar Mohammad Abdullah Al Faruque
Lihat Sumber

Abstrak

Heterogeneous MPSoCs comprise diverse processing units of varying compute capabilities. To date, the mapping strategies of neural networks (NNs) onto such systems are yet to exploit the full potential of processing parallelism, made possible through both the intrinsic NNs' structure and underlying hardware composition. In this paper, we propose a novel framework to effectively map NNs onto heterogeneous MPSoCs in a manner that enables them to leverage the underlying processing concurrency. Specifically, our approach identifies an optimal partitioning scheme of the NN along its `width' dimension, which facilitates deployment of concurrent NN blocks onto different hardware computing units. Additionally, our approach contributes a novel scheme to deploy partitioned NNs onto the MPSoC as dynamic multi-exit networks for additional performance gains. Our experiments on a standard MPSoC platform have yielded dynamic mapping configurations that are 2.1x more energy-efficient than the GPU-only mapping while incurring 1.7x less latency than DLA-only mapping.

Topik & Kata Kunci

Penulis (5)

H

Halima Bouzidi

M

Mohanad Odema

H

Hamza Ouarnoughi

S

Smail Niar

M

Mohammad Abdullah Al Faruque

Format Sitasi

Bouzidi, H., Odema, M., Ouarnoughi, H., Niar, S., Faruque, M.A.A. (2023). Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCs. https://arxiv.org/abs/2302.12926

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓