Active Standard

IEEE 2937-2022

IEEE Approved Draft Standard for Performance Benchmarking for AI Server Systems

Artificial intelligence (AI) computing differs from generic computing in terms of devices' formation, operators, and usage. AI server systems, including AI server, cluster, and High-Performance Computing (HPC) infrastructures are designed specifically for this purpose. The performance of these infrastructures is important to users not only on generic models but the ones for specific domains. This standard provides formal methods for the performance benchmarking for AI server systems?including approaches for test, metrics and measure. In addition, this specification provides the technical requirements on tools for benchmarking.

Sponsor Committee
C/AISC - Artificial Intelligence Standards Committee
Active Standard
PAR Approval
Board Approval

Working Group Details

IEEE Computer Society
Learn More
Sponsor Committee
C/AISC - Artificial Intelligence Standards Committee
Working Group
ASA WG - AI system and application test
Learn More
IEEE Program Manager
Christy Bahn
Working Group Chair
Wei Bao
No Active Projects
No Active Standards
No Superseded Standards
No Inactive-Withdrawn Standards
No Inactive-Reserved Standards

Stay up to date about new developments, including resources, insights and more.