At its Vision 2022 event, Intel Tuesday launched its second generation Habana AI deep learning processors which offer high performance and efficiency.
The new chips include Habana Gaudi2 and Habana Greco and use 7 nanometer technology. Intel acquired Habana Laboratories in 2019 for $2 billion.
“The launch of Habana’s new deep learning processors is a great example of Intel executing its AI strategy to provide customers with a wide range of solution choices, from cloud to edge, addressing the growing number and complex nature of AI workloads,” said Sandra Rivera. , Intel’s executive vice president and general manager of the data center and AI group, in a statement,
For data center professionals, training deep learning models is an expensive and time-consuming endeavor due to complex datasets and AI workloads. Gaudi2, the company said, was designed to improve the performance and efficiency of deep learning in cloud and on-premises systems.
According to research firm IDC, 74% of machine learning practitioners surveyed in 2020 run five to 10 training iterations of their models, more than 50% rebuild models weekly or more often, and 26% rebuild models daily. , or even every hour. These workers cited cost as the biggest barrier to their companies using the improvements that AI can bring to managing these workloads.
“Compared to the A100 GPU, implemented in the same process node and roughly the same chip size, Gaudi2 delivers clear leadership training performance, as evidenced by the apples-to-apples comparison on key workloads,” said Eitan Medina, COO of Habana Labs, in a statement. “This deep learning acceleration architecture is fundamentally more efficient and backed by a solid roadmap.”