Intel Launches Deep Learning Processors to Rival Nvidia AI Chips

During its Vision 2022 event, Intel launched its second-generation Habana AI deep learning processors that deliver high performance and high efficiency.

The new chips include the Habana Gaudi2 and the Habana Greco and use 7-nanometer

technology. Intel acquired Habana Labs in 2019 for $ 2 billion.

“Habana’s new deep learning processors are a prime example of Intel executing its AI strategy to give customers a wide array of solution choices — from cloud to edge — addressing the growing number and complex nature of AI workloads,” said Sandra Rivera , A statement from Intel’s executive vice president and general manager of the data center and AI group,

For data center professionals, training deep learning models are a costly and time-consuming endeavor because of complex datasets and AI workloads. Gaudi2, the company said, was designed to bring improved deep learning performance and efficiency to cloud and on-premises systems.

According to research firm IDC, 74 percent of machine learning practitioners surveyed in the 2020 run five to 10 training iterations of their models, more than 50 percent rebuild models weekly or more often, and 26 percent rebuild models daily or even hourly. Those workers are the ones who have the biggest hurdle to do with their businesses in terms of utilizing the improvements that AI can provide in those workloads.

“Compared with the A100 GPU, with the same process node and roughly the same die size, Gaudi2 delivers clear leadership training performance with key workloads on apples-to-apples comparison,” said Eitan Medina, Habana Labs’ COO. a statement. “This deep-learning acceleration architecture is fundamentally more efficient and backed up with a strong road map.”

Intel’s partners applauded the Habana Labs developments.

“We’re excited to bring our next-generation AI deep learning server to market with a high-performance 7 nm Gaudi2 processor that will enable our customers to achieve faster time-to-train advantages while enhancing efficiency and scalability. first-generation Gaudi, ”said Charles Liang, CEO of Supermicro.

Channel partners were also on hand to check out the new processing power. In an interview with Accenture’s Jason Mitchell, managing director and Intel client account lead, CRN said, “Understanding how those technologies are brought to bear is important to our applied intelligence, artificial intelligence and analytics.” That’s a significant area of ​​investment. So what we see is what’s next and how their software platform provides an interface between their silicon and our software. The underlying hardware is always really, really impressive. ”