New benchmarks to measure end-to-end system performance of ML training and inference tasks
The Standard Performance Evaluation Corp. (SPEC) today announced the formation of the SPEC Machine Learning Committee. The SPEC ML Committee will develop practical methodologies for benchmarking artificial intelligence (AI) and machine learning (ML) performance in the context of real-world platforms and environments. The Committee will also work with other SPEC committees to update their benchmarks for ML environments. Current members include AMD, Dell, Inspur, Intel, NetApp, NVIDIA and Red Hat.
Top iTechnology 5G Technology News: O2 Telefónica and Mavenir Demonstrate Zero Touch CI/CD Based Operations of IMS Core on Cloud Infrastructure
“IDC expects enterprises to spend nearly $342 billion on AI in 2021, and it’s essential that these companies understand what that money will buy,” said Arthur Kang, Chair of the SPEC ML Committee. “This new committee will design and develop the vendor agnostic benchmarks that vendors need to prove their solutions in a competitive market and enterprises need to make an informed buying decision. I encourage anyone interested in the future of ML processing to join the SPEC ML Committee and help shape these invaluable benchmarks.”
Top iTechnology Data Centre News: Scala Data Centers Celebrates Entry of Dell Technologies in its digital ecosystem
The SPEC ML Committee is initially developing benchmarks to measure end-to-end performance of a system under test (SUT) handling ML training and inference tasks. The goal of these benchmarks is to better represent industry practices compared to other existing benchmarks by including major parts of the end-to-end ML/DL pipeline, including data prep and training/inference. This vendor-neutral third-party benchmark will enable ML system designers to benchmark their offerings against those of their competitors and allow ML users, such as enterprises and scientific research institutions, to better understand how solutions will perform in real-world environments, enabling them to make better purchasing decisions.
The SPEC ML Committee welcomes any current SPEC members willing to join the development and management of the SPEC ML benchmark, as well as new SPEC members, especially ML/DL end users and manufacturers.
Top iTechnology Cloud News: nClouds Achieves AWS Solution Provider Partner Status
[To share your insights with us, please write to sghosh@martechseries.com]
