MLPerf's New Report Shows Gains in Industry
November 10, 2022
SAN FRANCISCO. MLCommons released its findings from the industry-standard MLPerf Training, HPC, and Tiny benchmark suites. The full open-source professionally reviewed benchmark suites scale ULP components from a few microwatts for disruptions up to robust multi-megawatt data center platforms and supercomputers. The recent MLPerf solution has a 5X increase in power capable of expanding speed and intelligence at all scales.
The suites assess the stress machine learning models (underlying software and hardware, and optional measuring energy usage), as well as commercial training machine learning models for solutions comprising of speech-to-text, autonomous vehicles, and medical imaging. V2.1 comprises of 200 outcomes from 18 differing users from miniscule workstations to stout data centers.
“We are pleased to see the growth in the machine learning community and especially excited to see the first submissions from Dell in MLPerf HPC and GreenWaves Technologies, OctoML, and Qualcomm in MLPerf Tiny,” said MLCommons Executive Director David Kanter. “The increasing adoption of energy measurement is particularly exciting, as a demonstration of the industry’s outstanding commitment to efficiency.”
To view the results and additional information about the benchmarks please visit:
For more information, visit mlcommons.org.