Intel prepares open-source drivers for next-gen Xe3P graphics

Intel is seeding early open-source support for its upcoming Xe3P graphics architecture in Mesa drivers, aiming to have Linux compatibility ready when new GPUs and Nova Lake processors arrive.

Intel has begun early open-source enablement for its next-generation Xe3P graphics architecture within the Mesa OpenGL ‘Iris’ and Vulkan ‘Anvil’ drivers. The current work is not yet aimed at making the drivers fully functional, but instead focuses on creating code paths that can be extended for this graphics IP over time. As a result, preliminary support is still described as being a few weeks away, with additional development required behind the scenes before users will see tangible benefits.

The first versions of Xe3P GPUs are expected to appear this year, with the IP arriving in several configurations across Intel’s product stack. Some variants are planned for the upcoming ‘Nova Lake’ desktop processors targeting the consumer market, which are anticipated later this year. Early signs from the open-source work indicate that ‘Nova Lake-P’ processors will integrate Xe3P-LPG for on-chip graphics, positioning the new architecture as a core part of Intel’s next mobile and desktop platforms.

Beyond integrated graphics, ‘Nova Lake-P’ processors are also set to incorporate additional Xe3P-based IP blocks tailored for specialized tasks. The Xe3P-LPM block will focus on media processing for decoding and encoding workloads, while Xe3P-LPD will handle display output processing. The Xe3P IP is further slated to feature in Intel’s Artificial Intelligence-focused ‘Crescent Island’ inference GPU, which will feature 160 GB of onboard LPDDR5X. Performance expectations for the Xe3P GPU family have not yet been disclosed, leaving prospective users and developers waiting for more detailed benchmarks and claims.

50

Impact Score

NVIDIA shows RTX Spark platform at Computex 2026

NVIDIA presented RTX Spark in Taipei as a Windows on Arm platform spanning gaming, creator, and Artificial Intelligence workloads. Microsoft also detailed Windows 11 optimizations built specifically for the new NVIDIA silicon.

AWS enterprise processor targets Artificial Intelligence inference

AWS’s Annapurna Labs-designed enterprise server processor uses a chiplet architecture for cloud infrastructure and Artificial Intelligence inferencing. The design combines Arm compute resources, cache coherency, and high-bandwidth interconnects for AWS deployments.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.