Intel Launches Deep Learning Processors To Address The ‘Complex Nature Of AI Workloads’

Intel uses its inaugural Vision event to showcase its latest developments with a focus on improvements in artificial intelligence.

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

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

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

“The launch of Habana’s new deep learning processors is a prime example of Intel executing on 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, 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 a costly and time-eating 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 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 cited cost as the biggest obstacle to their businesses in utilizing the improvements that AI can provide in handling those workloads.

“Compared with the A100 GPU, implemented in the same process node and roughly the same die size, Gaudi2 delivers clear leadership training performance as demonstrated with apples-to-apples comparison on key workloads,” Eitan Medina, Habana Labs’ COO, said in a statement. “This deep- learning acceleration architecture is fundamentally more efficient and backed 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 featuring the high-performance 7 nm Gaudi2 processor that will enable our customers to achieve faster time-to-train advantages while preserving the efficiency and expanding on the scalability of first-generation Gaudi,” said Charles Liang, CEO of Supermicro.

Channel partners were also on hand to check out the new processing power. Accenture’s Jason Mitchell, managing director and Intel client account lead, in an interview with 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 we like seeing what’s next and how their software platform provides an interface between their silicon and our software. Seeing what’s next in the underlying hardware is always really, really impressive.”