MLPerf Mobile Inference Benchmark
Abstract
This paper presents the first industry-standard open-source machine learning (ML) benchmark to allow perfor mance and accuracy evaluation of mobile devices with different AI chips and software stacks. The benchmark draws from the expertise of leading mobile-SoC vendors, ML-framework providers, and model producers. It comprises a suite of models that operate with standard data sets, quality metrics and run rules. We describe the design and implementation of this domain-specific ML benchmark. The current benchmark version comes as a mobile app for different computer vision and natural language processing tasks. The benchmark also supports non-smartphone devices, such as laptops and mobile PCs. Benchmark results from the first two rounds reveal the overwhelming complexity of the underlying mobile ML system stack, emphasizing the need for transparency in mobile ML performance analysis. The results also show that the strides being made all through the ML stack improve performance. Within six months, offline throughput improved by 3x, while latency reduced by as much as 12x. ML is an evolving field with changing use cases, models, data sets and quality targets. MLPerf Mobile will evolve and serve as an open-source community framework to guide research and innovation for mobile AI.
Cite
@article{arxiv.2012.02328,
title = {MLPerf Mobile Inference Benchmark},
author = {Vijay Janapa Reddi and David Kanter and Peter Mattson and Jared Duke and Thai Nguyen and Ramesh Chukka and Ken Shiring and Koan-Sin Tan and Mark Charlebois and William Chou and Mostafa El-Khamy and Jungwook Hong and Tom St. John and Cindy Trinh and Michael Buch and Mark Mazumder and Relia Markovic and Thomas Atta and Fatih Cakir and Masoud Charkhabi and Xiaodong Chen and Cheng-Ming Chiang and Dave Dexter and Terry Heo and Gunther Schmuelling and Maryam Shabani and Dylan Zika},
journal= {arXiv preprint arXiv:2012.02328},
year = {2022}
}