Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there is still a group of tasks that can easily challenge even high-end devices, namely running artificial intelligence algorithms. In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones. We give an overview of the hardware acceleration resources available on four main mobile chipset platforms: Qualcomm, HiSilicon, MediaTek and Samsung. Additionally, we present the realworld performance results of different mobile SoCs collected with AI Benchmark 1 that are covering all main existing hardware configurations. * We also thank Przemyslaw Szczepaniak (pszczepaniak@google.com), Google Inc., for writing and editing sections 2.7, 3.1 and 3.2. 1

Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and four orders of magnitude in performance; they range from embedded devices to data-center solutions. Fueling the hardware are a dozen or more software frameworks and libraries. The myriad combinations of ML hardware and ML software make assessing ML-system performance in an architecture-neutral, representative, and reproducible manner challenging. There is a clear need for industry-wide standard ML benchmarking and evaluation criteria. MLPerf Inference answers that call. Driven by more than 30 organizations as well as more than 200 ML engineers and practitioners, MLPerf implements a set of rules and practices to ensure comparability across systems with wildly differing architectures. In this paper, we present the method and design principles of the initial MLPerf Inference release. The first call for submissions garnered more than 600 inference-performance measurements from 14 organizations, representing over 30 systems that show a range of capabilities.

No abstract

No abstract

The time and cost associated with the development and certification of flight-critical software bled air vehicles. This upward trend is expected to continue as future vehicles will be increasingly autonomous and intelligent. Affordable, efficient processes and tools are needed to control development costs and schedule, as well as to ensure the safety of these vehicles. This paper presents the results of a U. S. Air Force Research Laboratory (AFRL) sponsored project on the development of validation and verification (V&V) technologies for flightcritical software. The purpose of the project is to improve the affordability and safety for software V&V, specifically, for adaptive and/or mixed-criticality software.