Login to Continue Learning
Today, NVIDIA and Intel announced a collaboration to develop next-gen x86 chips that combine Intel’s CPU prowess with NVIDIA’s strong GPUs. However, during the conference, Intel did not reveal whether its own GPU family would be affected by this deal. Currently, Intel has two major GPU lineups: Gaudi and “Shores” for enterprise AI, and Arc for client/business. Despite these products facing challenges in the market, they have become value kings in their segments.
Intel reassured that it will continue to offer its own GPU product offerings despite the new collaboration with NVIDIA. An Intel spokesperson stated, “We’re not discussing specific roadmaps at this time, but the collaboration is complementary to Intel’s roadmap and we will continue to have GPU product offerings.”
The company plans to launch its 3rd Gen Xe architecture, codenamed Celestial, with upcoming Panther Lake CPUs. It seems unlikely that these chips will incorporate NVIDIA GPUs. However, next year’s Nova Lake CPUs might be the first to leverage NVIDIA’s GPUs.
Intel’s previous attempt at an SoC was Kaby Lake-G, which featured three chiplets: a Compute chiplet, an IO chiplet, and an AMD Radeon GPU based on the RX Vega architecture. While Kaby Lake-G did not succeed commercially, it paved the way for future designs like Intel’s AX lineup.
Intel’s plans include using its own Xe architectures, such as Xe3 and Xe4, in its standard product lineup. As for Arc discrete GPUs, Intel will continue to develop them independently. Using NVIDIA’s GPUs for Arc would not make sense since they are direct competitors. This decision prevents NVIDIA from dominating the discrete GPU market.
Jensen Huang mentioned that NVLink and other technologies will be used on the AI side but did not provide details about how this would affect the Jaguar Shores AI accelerator family.
While the collaboration is beneficial for Intel, it remains to be seen when actual products will be announced. CES or the next major 2026 event might see these new developments.