MLCommoncs: Latest MLPerf AI Benchmark Results Show Machine Learning Inference Advances – High-Performance Computing News Analysis | insideHPC – insideHPC

SAN FRANCISCO – September 8, 2022 – Today, the open engineering consortium MLCommons announced results from MLPerf Inference v2. 1, which analyzes the performance of inference — the application of a trained machine learning model to new data. Inference allows for the particular intelligent enhancement of a vast array associated with applications and systems.

Here are the results   plus additional information about the benchmarks.

MLCommons said this round established new standards with nearly 5, 300 performance results and 2, 400 power measures, 1 . 37X and 1. 09X more than the previous round, respectively, “reflecting the community’s vigor. ”

The MLPerf Inference benchmarks are usually focused on datacenter and edge systems, plus Alibaba, ASUSTeK, Azure, Biren, Dell, Fujitsu, GIGABYTE, H3C, HPE, Inspur, Intel, Krai, Lenovo, Moffett, Nettrix, Neural Magic, NVIDIA, OctoML, Qualcomm Technologies, Inc., SAPEON, and Supermicro are among the contributors to the submission round.

MLPerf benchmarks are usually comprehensive system tests that stress device learning models, software, plus hardware, and optionally monitor energy consumption, according to MLCommons. The open-source and peer-reviewed benchmark suites are designed to level the playing ground for competitiveness, which fosters innovation, performance, plus energy efficiency for the whole sector.

“We are very excited with the growth in the ML community and welcome brand new submitters across the globe such as Biren, Moffett AI, Nerve organs Magic, plus SAPEON, ” said ML Commons Executive Director David Kanter. “The exciting new architectures all demonstrate the particular creativity and innovation in the industry designed to create greater AI functionality that will bring new plus exciting capability to business and consumers alike. ”