MLPerf Inference Benchmark

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 magnit...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA) S. 446 - 459
Hauptverfasser: Reddi, Vijay Janapa, Cheng, Christine, Kanter, David, Mattson, Peter, Schmuelling, Guenther, Wu, Carole-Jean, Anderson, Brian, Breughe, Maximilien, Charlebois, Mark, Chou, William, Chukka, Ramesh, Coleman, Cody, Davis, Sam, Deng, Pan, Diamos, Greg, Duke, Jared, Fick, Dave, Gardner, J. Scott, Hubara, Itay, Idgunji, Sachin, Jablin, Thomas B., Jiao, Jeff, John, Tom St, Kanwar, Pankaj, Lee, David, Liao, Jeffery, Lokhmotov, Anton, Massa, Francisco, Meng, Peng, Micikevicius, Paulius, Osborne, Colin, Pekhimenko, Gennady, Rajan, Arun Tejusve Raghunath, Sequeira, Dilip, Sirasao, Ashish, Sun, Fei, Tang, Hanlin, Thomson, Michael, Wei, Frank, Wu, Ephrem, Xu, Lingjie, Yamada, Koichi, Yu, Bing, Yuan, George, Zhong, Aaron, Zhang, Peizhao, Zhou, Yuchen
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.05.2020
Schlagworte:
Accuracy
Benchmark testing
Benchmarking
Computer architecture
Degradation
Hardware
Inference
Machine Learning
Optimization
Organizations
Servers
Standards organizations
Throughput
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
DOI:10.1109/ISCA45697.2020.00045