Intel unveils Gaudi 3 AI processor, an alternative to Nvidia H100
Date: 12/04/2024
At the Intel Vision 2024 conference, Intel showcased its commitment to open and secure enterprise AI solutions. Intel introduced its news Gaudi 3 AI accelerator. Intel Gaudi 3 AI Accelerator to deliver significant improvements in performance and power efficiency compared to Nvidia H100.
It is made available to OEMs like Dell Technologies, Hewlett Packard Enterprise, Lenovo, and Supermicro, expanding AI data center market offerings. Welcomed new customers and partners, including Bharti Airtel, Bosch, IBM, NAVER, Ola, and others.
Collaboration with industry leaders like SAP, Red Hat, and Vmware to accelerate the deployment of secure generative AI systems. Leading the Ultra Ethernet Consortium (UEC) to develop open Ethernet networking for AI fabric.
Partnerships with companies like NAVER, Bosch, IBM, Ola, and NielsenIQ for innovative AI applications across various industries.
Collaborations with Google Cloud, Thales, and Cohesity to leverage Intel's confidential computing capabilities in the cloud.
Introduction of the Intel Xeon 6 processors for data centers, cloud, and edge computing.Updates on client, edge, and connectivity solutions, including the Intel Core Ultra processors and new edge silicon.
Intel claimed its Gaudi 3 AI accelerator, delivering 50% on average better inference1 and 40% on average better power efficiency than Nvidia H100 – at a fraction of the cost.
“Innovation is advancing at an unprecedented pace, all enabled by silicon – and every company is quickly becoming an AI company,” said Intel CEO Pat Gelsinger. “Intel is bringing AI everywhere across the enterprise, from the PC to the data center to the edge. Our latest Gaudi, Xeon and Core Ultra platforms are delivering a cohesive set of flexible solutions tailored to meet the changing needs of our customers and partners and capitalize on the immense opportunities ahead.”
Intel said its Gaudi 3 AI accelerator will power AI systems with up to tens of thousands of accelerators connected through the common standard of Ethernet. Intel Gaudi 3 promises 4x more AI compute for BF16 and a 1.5x increase in memory bandwidth over its predecessor. The accelerator will deliver a significant leap in AI training and inference for global enterprises looking to deploy GenAI at scale.
Intel also shared in its relase that In comparison to Nvidia H100, Intel Gaudi 3 is projected to deliver 50% faster time-to-train on average3 across Llama2 models with 7B and 13B parameters, and GPT-3 175B parameter model. Additionally, Intel Gaudi 3 accelerator inference throughput is projected to outperform the H100 by 50% on average1 and 40% for inference power-efficiency averaged2 across Llama 7B and 70B parameters, and Falcon 180B parameter models.
Source: Intel
