Benchmarking GPU-Accelerated Edge Devices
Jongmin Jo, Sucheol Jeong, Pilsung Kang
Abstract
We evaluate one of the state-of-the-art GPU-accelerated edge devices in this paper. We perform a set of deep learning benchmarks on the device to measure its performance. By comparing its performance with other GPU-accelerated systems in different computing platforms, we assess the computational capability of the modern edge devices equipped with a significant amount of hardware parallelism.
Topics & Concepts
Computer scienceBenchmarkingEnhanced Data Rates for GSM EvolutionParallelism (grammar)Edge computingParallel computingEdge deviceSet (abstract data type)Measure (data warehouse)General-purpose computing on graphics processing unitsState (computer science)Computer architectureComputational scienceArtificial intelligenceComputer graphics (images)Cloud computingGraphicsOperating systemAlgorithmMarketingDatabaseProgramming languageBusinessAdvanced Neural Network ApplicationsAdvanced Memory and Neural ComputingIoT and Edge/Fog Computing