Our joint task force efforts will ultimately provide the industry with a simple, accredited source of information these companies need to make critical decisions regarding supplier selection and project investment. It will be.
San Jose and San Francisco, CA (PRWEB)
May 17, 2023
AVCC®, a global autonomous vehicle (AV) consortium that specifies and benchmarks solutions for AV computing in the automotive industry, and an open, global consortium dedicated to making machine learning (ML) better for everyone. Engineering consortium MLCommons®, the industry’s first Automotive Benchmark, acquires specifications and benchmarks and transitions to open source software and certification. Early participants in the benchmark include Arm (co-chair), Bosch, cTuning Foundation, KPIT, NVIDIA, Red Hat, Qualcomm, Inc. (co-chair), Samsung Electronics, and other industry leaders.
The use of ML, especially in self-driving car perception systems, has increased dramatically over the last few years, enabling new innovations such as auto lane keeping that make roads safer. As vehicles become more intelligent, the industry needs a common set of ML benchmarks that enable fair and accurate comparisons between different technologies.
The goal of this partnership is to use AI/ML deep neural network (DNN) technology to develop an industry-standard automotive benchmark suite for use by OEMs and automotive suppliers. The suite builds on the AVCC AI/ML Benchmark Technical Report and the MLPerf™ Benchmark Suite developed by MLCommons. This common set of benchmarks also guides industry-wide engineering on future platforms and accelerates the development of new features. Development of the automotive benchmark suite is a multi-stage approach, with the goal of delivering an open-source software solution by the end of the year.
“We are excited to work with AVCC to bring our machine learning expertise to the automotive industry,” said David Kanter, Executive Director of MLCommons. “We believe this opportunity will help drive innovation and drive standards for increasingly intelligent, high-performance vehicles.”
“OEMs and automotive suppliers are currently challenged in understanding the computing performance and system resource requirements of their solutions,” said AVCC President Armando Pereira. “Our joint task force efforts will ultimately provide the industry with a simple, accredited source of information these companies need to make critical decisions regarding supplier selection and project investment. will be
Technical work has begun and broad industry participation is encouraged. The Automotive Benchmark initiative is soliciting input from all members of AVCC and MLCommons, as well as other industry stakeholders. If your organization uses (or is considering using) automotive AI technology, we encourage you to join this joint initiative to support the development of the new Standard Automotive Benchmark Suite.
To join the Standard Automotive Benchmark Suite initiative, please visit https://mlcommons.org/en/groups/inference-automotive/.
For more information on AVCC, please visit http://www.avcconsortium.org.
For more information on MLCommons, please visit https://mlcommons.org/en.
About AVCC
AVCC is a global autonomous vehicle (AV) consortium that specifies and benchmarks solutions for autonomous vehicle (AV) computing, cybersecurity, functional safety and building block interconnection. AVCC is a non-profit membership organization that builds an ecosystem of his OEMs, automotive suppliers, semiconductor and software suppliers in the automotive industry. The Consortium addresses the complexities of the AV environment and promotes member-driven dialogue within technical working groups to address common challenges that cannot be differentiated. AVCC is committed to driving the evolution of autonomous and automated solutions up to L5 performance over the next few decades. http://www.avcconsortium.org
About ML Commons
MLCommons is an open engineering consortium with a mission to make machine learning better for everyone through benchmarks and data. The foundation of MLCommons began with the MLPerf benchmark in 2018 and has rapidly expanded into a set of industry metrics to measure machine learning performance and promote transparency in machine learning technology. MLCommons is a collaborative engineering effort with over 50 founding partners, global technology providers, academics, and researchers to build tools for the entire machine learning industry through benchmarks and metrics, public datasets, and best practices. Emphasis on
Share the article on social media or email:
