Intel Corp.'s AI deep learning processors for data centers developer Habana Labs has launched a new processor that intensifies competition with chip rival Nvidia. According to the announcement, the Gaudi2 processor, which has been unveiled, demonstrates two-times throughput compared with Nvidia’s flagship A100 GPU graphic processor. Israeli company Habana Labs was acquired by Intel in 2019 for $2 billion.
According to the company, the AI deep learning processor market is controlled by Nvidia and the Gaudi2 is Intel's attempt to raise its game and compete as the data centers market grows 36.7% annually. Habana Labs says that the new processor is already available for customers and supply change disruptions have not influenced distribution with Intel able to supply the required chips.
With a leap in process from 16 nm Gaudi to 7 nm, Gaudi2 provides a significant boost to its compute, memory and networking capabilities. Another Israeli-owned Intel company, autonomous vehicle developer Mobileye, has already placed orders for the Gaudi2 processor.
Mobileye EVP R&D Gaby Hayon said, "As a world leader in automotive and driving assistance systems, training cutting-edge deep learning models for tasks such as object detection and segmentation that enable vehicles to sense and understand their surroundings is mission-critical to Mobileye business and vision. As training such models is time-consuming and costly, multiple teams across Mobileye have chosen to use Gaudi-accelerated training machines, either on Amazon EC2 DL1 instances or on-prem. Those teams consistently see significant cost savings relative to existing GPU-based instances across model types, enabling them to achieve much better time-to-market for existing models or training much larger and complex models aimed at exploiting the advantages of the Gaudi architecture."
Habana Labs COO Eitan Medina added, "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. This deep-learning acceleration architecture is fundamentally more efficient and backed with a strong roadmap."
The Gaudi2 is able to process 5,425 images per second compared with the 2,930 that Nvidia's A100 can process.
Intel EVP and general manager of the Datacenter and AI Group Sandra Rivera said, "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. Gaudi2 can help Intel customers train increasingly large and complex deep learning workloads with speed and efficiency, and we’re anticipating the inference efficiencies that Greco will bring."
Published by Globes, Israel business news - en.globes.co.il - on May 11, 2022.
© Copyright of Globes Publisher Itonut (1983) Ltd., 2022.