Artificial intelligence and machine learning are experiencing widespread adoption in the industry, academia, and even public consciousness. This has been driven by the rapid advances in the applications and accuracy of AI through increasingly complex algorithms and models; this, in turn, has spurred research into developing specialized hardware AI accelerators. The rapid pace of the advances makes it easy to miss the forest for the trees: they are often developed and evaluated in a vacuum without considering the full application environment in which they must eventually operate. In this paper, we deploy and characterize Face Recognition, an AI-centric edge video analytics application built using open source and widely adopted infrastructure and ML tools. We evaluate its holistic, end-to-end behavior in a production-size edge data center and reveal the "AI tax" for all the processing that is involved. Even though the application is built around state-of-the-art AI and ML algorithms, it relies heavily on pre-and post-processing code which must be executed on a general-purpose CPU. As AI-centric applications start to reap the acceleration promised by so many accelerators, we find they impose stresses on the underlying software infrastructure and the data center's capabilities: storage and network bandwidth become major bottlenecks with increasing AI acceleration. By not having to serve a wide variety of applications, we show that a purpose-built edge data center can be designed to accommodate the stresses of accelerated AI at 15% lower TCO than one derived from homogeneous servers and infrastructure. We also discuss how our conclusions generalize beyond Face Recognition as many AI-centric applications at the edge rely upon the same underlying software and hardware infrastructure.

Artificial intelligence and machine learning are experiencing widespread adoption in industry and academia. This has been driven by rapid advances in the applications and accuracy of AI through increasingly complex algorithms and models; this, in turn, has spurred research into specialized hardware AI accelerators. Given the rapid pace of advances, it is easy to forget that they are often developed and evaluated in a vacuum without considering the full application environment. This article emphasizes the need for a holistic, end-to-end analysis of artificial intelligence (AI) workloads and reveals the “AI tax.” We deploy and characterize Face Recognition in an edge data center. The application is an AI-centric edge video analytics application built using popular open source infrastructure and machine learning (ML) tools. Despite using state-of-the-art AI and ML algorithms, the application relies heavily on pre- and post-processing code. As AI-centric applications benefit from the acceleration promised by accelerators, we find they impose stresses on the hardware and software infrastructure: storage and network bandwidth become major bottlenecks with increasing AI acceleration. By specializing for AI applications, we show that a purpose-built edge data center can be designed for the stresses of accelerated AI at 15% lower TCO than one derived from homogeneous servers and infrastructure.

For certain structural testing criteria a significant proportion of tests instances are infeasible in the sense the semantics of the program implies that test data cannot be constructed that meet the test requirement. This paper describes the design and prototype implementation of a structural testing system that uses a theorem prover to determine feasibility of testing requirements and to optimize the number of test cases required to achieve test coverage. Using this approach, we were able to accurately and efficiently determine path feasibility for moderately-sized program units of production code written in a subset of Ada. On these problems, the computer solutions were obtained much faster and with greater accuracy than manual analysis. The paper describes how we formalize test criteria as control flow graph path expressions; how the criteria are mapped to logic formulas; and how we control the complexity of the inference task. It describes the limitations of the system and proposals for its improvement as well as other applications of the analysis.

Article Test data generation and feasible path analysis Share on Authors: Robert Jasper The Boeing Co. The Boeing Co.View Profile , Mike Brennan The Boeing Co. The Boeing Co.View Profile , Keith Williamson The Boeing Co. The Boeing Co.View Profile , Bill Currier The Boeing Co. The Boeing Co.View Profile , David Zimmerman Z-Access Consulting Z-Access ConsultingView Profile Authors Info & Claims ISSTA '94: Proceedings of the 1994 ACM SIGSOFT international symposium on Software testing and analysisAugust 1994 Pages 95–107https://doi.org/10.1145/186258.187150Online:01 August 1994Publication History 47citation992DownloadsMetricsTotal Citations47Total Downloads992Last 12 Months4Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access