On Tuesday, Intel launched Gaudi 3, its cutting-edge artificial intelligence chip, aiming to rival NVIDIA’s dominance in the AI market. Boasting over double the power efficiency and 1.5 times the speed of NVIDIA’s H100 GPU, Gaudi 3 is designed for training and deploying major AI models, including speech recognition and generative AI.
“We do expect it to be highly competitive” with NVIDIA’s latest chips, said Das Kamhout, vice president of Xeon software at Intel, on a call with reporters. “From our competitive pricing, our distinctive open integrated network on chip, we’re using industry-standard Ethernet. We believe it’s a strong offering.”
Available in various configurations for flexible system integration, it’s slated for third-quarter release, with companies like Dell and HPE set to incorporate the chips into their systems. Amid the AI sector’s expansion, Intel’s move, alongside AMD’s efforts and Nvidia’s continuous innovation, signifies a heated race for AI chip market share.
“We are working with the software ecosystem to build open reference software, as well as building blocks that allow you to stitch together a solution that you need, rather than be forced into buying a solution,” Sachin Katti, senior vice president of Intel’s networking group, said on a call with reporters.
