MLPerf Inference Benchmark
Autor: | Mark Charlebois, Dave Fick, Sachin Satish Idgunji, Yuchen Zhou, Michael Thomson, Ashish Sirasao, George Yuan, Anton Lokhmotov, Koichi Yamada, Tom St. John, Bing Yu, Jeff Jiao, Arun Tejusve Raghunath Rajan, Paulius Micikevicius, Ephrem C. Wu, Francisco Massa, Carole-Jean Wu, Hanlin Tang, David Lee, William Chou, Frank Wei, Jared Duke, Cody Coleman, Sam Davis, Jeffery Liao, Itay Hubara, Dilip Sequeira, Lingjie Xu, Pan Deng, Vijay Janapa Reddi, Guenther Schmuelling, Gennady Pekhimenko, Maximilien Breughe, Peng Meng, Greg Diamos, David Kanter, Colin Osborne, Thomas B. Jablin, Peizhao Zhang, Fei Sun, Pankaj Kanwar, Ramesh Chukka, J. Scott Gardner, Aaron Zhong, Christine Cheng, Peter Mattson, Brian M. Anderson |
---|---|
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Inference Machine Learning (stat.ML) 02 engineering and technology computer.software_genre 01 natural sciences Machine Learning (cs.LG) Software Statistics - Machine Learning 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Software system computer.programming_language 010302 applied physics Flexibility (engineering) Computer Science - Performance business.industry Standard ML Benchmarking 020202 computer hardware & architecture Software framework Performance (cs.PF) Benchmark (computing) Software engineering business computer |
Zdroj: | ISCA |
DOI: | 10.48550/arxiv.1911.02549 |
Popis: | 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 five 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. In this paper, we present our benchmarking method for evaluating ML inference systems. Driven by more than 30 organizations as well as more than 200 ML engineers and practitioners, MLPerf prescribes a set of rules and best practices to ensure comparability across systems with wildly differing architectures. The first call for submissions garnered more than 600 reproducible inference-performance measurements from 14 organizations, representing over 30 systems that showcase a wide range of capabilities. The submissions attest to the benchmark's flexibility and adaptability. Comment: ISCA 2020 |
Databáze: | OpenAIRE |
Externí odkaz: |