2020/02/17 by Wanling Gao, Fei Tang, Gao, Wanling +67
Computer Science · Engineering · Materials Science · #Agile software development #Benchmark (surveying) #Benchmarking #Component (thermodynamics) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain (mathematical analysis) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Machine Learning in Materials Science #Operating system #Performance (cs.PF) #Software #Software System Performance and Reliability #Software engineering #Suite #Testbed #The Internet #World Wide Web #cs.CV #cs.PF
paper · pdf · doi:10.48550/arxiv.2002.07162
25 pages, 7 figures. arXiv admin note: substantial text overlap with arXiv:1908.08998
arxiv created 2020/02/17 · openalex publication_date 2020/02/17 · arxiv updated 2020/02/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Domain-specific software and hardware co-design is encouraging as it is much easier to achieve efficiency for fewer tasks. Agile domain-specific benchmarking speeds up the process as it provides not only relevant design inputs but also relevant metrics, and tools. Unfortunately, modern workloads like Big data, AI, and Internet services dwarf the traditional one in terms of code size, deployment scale, and execution path, and hence raise serious benchmarking challenges. This paper proposes an agile domain-specific benchmarking methodology. Together with seventeen industry partners, we identify ten important end-to-end application scenarios, among which sixteen representative AI tasks are distilled as the AI component benchmarks. We propose the permutations of essential AI and non-AI component benchmarks as end-to-end benchmarks. An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application. We design and implement a highly extensible, configurable, and flexible benchmark framework, on the basis of which, we propose the guideline for building end-to-end benchmarks, and present the first end-to-end Internet service AI benchmark. The preliminary evaluation shows the value of our benchmark suite---AIBench against MLPerf and TailBench for hardware and software designers, micro-architectural researchers, and code developers. The specifications, source code, testbed, and results are publicly available from the web site \urlhttp://www.benchcouncil.org/AIBench/index.html.