… After performing an exhaustive survey on Internet service AI domains, we identify and
implement nineteen … We contribute by far the most comprehensive AI training benchmark suite. …

… characterizing the AI and Internet services application domains. First, in cooperation with
seventeen industry partners, we investigate their domain-specific benchmarking requirements, …

… We implement two Internet service AI scenario benchmarks based on the framework as …
Several AI benchmark suites only provide component benchmarks, which may lead to error-…

… We discuss and present our plans to extend the benchmark suite tasks over time in … Ai
benchmark: All about deep learning on smartphones in 2019. In 2019 International Conference on …

… Considering the model diversity and framework diversity, we propose a benchmark suite, …
used in other AI benchmarks, and becomes a de facto standard to evaluate AI system. MLPerf …

… In summary, our Edge AIBench differs from the other four benchmark suites. The AIPerf is
mainly designed for HPC platforms. MLMark appeals more to measure embedded …

… and AI benchmarks and point out their downsides for AI-HPC … Therefore, we choose to build
our own benchmark suite on … , AIBench: An industry standard internet service AI benchmark …

… These benchmarks have provided various metrics and results for machine learning … ,
AIBench is a comprehensive AI benchmark suite, distilling real-world application scenarios into AI …

… benchmark suite for evaluating ML datasets and data-centric algorithms. We aim to foster
innovation in data-centric AI … , and we provide an open, online platform with multiple rounds of …

… KITTI [12] is a vision benchmark suite for autonomous driving. It proposes stereo and …
benchmark suite for edge computing systems. It summarizes four scenarios and implements six AI …