MLPerf: An Industry Standard Performance Benchmark Suite for Machine Learning


Date:  Tuesday, September 22, 2020

Start Time: 1:00 pm

End Time: 1:30 pm

The rapid growth in the use of DNNs has spurred the development of numerous specialized processor architectures and software frameworks. System and application developers need reliable performance metrics to help them select processors and frameworks. Processor and framework developers need reliable performance metrics so that they can improve their products. This talk presents MLPerf, an industry-standard performance benchmark suite, and the design philosophies behind the benchmark suite and associated benchmarking methodologies.

Track

Session Speakers

  • Carole-Jean Wu is a Research Scientist at Facebook AI Research. Her expertise domain is in computer architecture with a particular focus on energy- and memory-efficient systems. Her recent work has pivoted into designing systems for machine learning execution at-scale, such as for personalized recommender systems and mobile deployment. Carole-Jean chairs MLPerf Recommendation Benchmark Advisory Board and co-chairs MLPerf Inference. Carole-Jean holds tenure from ASU and received her M.A. and Ph.D. from Princeton and B.Sc. from Cornell. She is the recipient of the NSF CAREER Award, Facebook AI Infrastructure Mentorship Award, the IEEE Young Engineer of the Year Award, the Science Foundation Arizona Bisgrove Early Career Scholarship, and the Intel PhD Fellowship, among a number of Best Paper awards.


Share

MLPerf: An Industry Standard Performance Benchmark Suite for Machine Learning