Intel’s leadership has revealed that the company intends to begin manufacturing its own graphics processing units (GPUs), a type of chip that has become highly prominent thanks to rival Nvidia’s success, according to a report from Reuters.
At the Cisco AI Summit on Tuesday, Intel Chief Executive Officer Lip-Bu Tan announced that the company will develop GPUs, marking a noteworthy expansion beyond the central processing units (CPUs) the firm has traditionally focused on. GPUs are specialized processors widely used in areas like gaming and training artificial intelligence models.
Tan said Intel has already brought in an executive to lead the GPU initiative. “I just hired the chief GPU architect, and he’s very good. I’m very delighted he joined me, and it takes some persuasion,” he said, highlighting the importance Intel is placing on attracting top talent for this effort.
The new GPU division will be overseen by Kevork Kechichian, executive vice president and general manager of Intel’s data center group, according to reporting that cites Reuters. Kechichian joined Intel last September as part of a broader effort to bring in engineering leaders. Another key hire for the project in January was Eric Demers, who previously spent more than 13 years at Qualcomm and most recently served as a senior vice president of engineering.
Tan acknowledged that this GPU initiative is still in its early stages, and that Intel intends to shape its plans based on direct customer feedback and needs. He said that the company will work collaboratively with customers to define the specifications and direction of the GPUs as the project progresses.
Although Nvidia did not invent the GPU, the company’s work in this area has played a significant role in its rise, and its GPUs for AI workloads have become highly advanced and widely adopted, helping it secure a dominant position in the market.
, a type of chip...){kind=link}