Special guest David Kanter of ML Commons joins Shahin Khan and Doug Black to discuss the critical importance AI performance metrics. AI is everywhere and destined to run on everything, from devices to big systems. So in addition to the well-known MLPerf benchmark for AI training, ML Commons provides a growing suite of benchmarks and data sets for other aspects of AI, such as inference, storage and safety.
In this episode sponsored by Lenovo, David talks about how MLCommons manages the expansion of its benchmark portfolio, the growth of its membership community, how to interpret its benchmarks, and he shares insights on what the benchmarks results, in their totality, are telling us.
David is a founder, board member, and the head of MLPerf for MLCommons, where he helps lead the MLPerf benchmarks. He has more than 16 years of experience in semiconductors, computing and machine learning. David founded a microprocessor and compiler startup, he was an early employee at Aster Data Systems, and has consulted for Intel, Nvidia, KLA, Applied Materials, Qualcomm, Microsoft among others.
You can find our podcasts at insideHPC’s @HPCpodcast page, on Twitter, on the OrionX.net blog page, on iTunes and Google. Here’s the OrionX.net podcast page, and the RSS feed. We’re also available on Spotify and iTunes.
