Intel expands XeSS 2 support to NVIDIA and AMD GPUs with SDK 2.1.0

Intel opens up its XeSS 2 toolkit to NVIDIA and AMD graphics cards, bringing advanced super resolution and frame generation to a wider gaming audience powered by Artificial Intelligence.

Intel has announced the release of XeSS 2 SDK version 2.1.0, a significant update that brings support to a broad spectrum of graphics cards outside of Intel´s own lineup. With this release, GPUs from both NVIDIA and AMD are now able to tap into Intel´s suite of upscaling and frame generation technologies, provided they support Shader Model 6.4. This expands compatibility to include any GeForce GTX 10-series ´Pascal´ or newer card from NVIDIA and Radeon RX 5000 series or newer from AMD, dramatically increasing the reach of XeSS 2.

The updated SDK enables not just XeSS super resolution (XeSS SR), but also frame generation (XeSS FG) and a low latency feature (XeLL). However, it´s important to note that XeLL cannot be used independently and requires XeSS FG to be active, ensuring that all low latency advantages go hand in hand with frame generation support. This synergy is aimed squarely at enhancing real-time gaming experiences, raising both image quality and playback smoothness by leveraging advanced upscaling and timing reductions.

From a technical standpoint, XeSS 2´s super resolution and frame generation capabilities depend on DP4a compute instructions for processing across general consumer GPUs. Only Intel’s own Arc ´Alchemist´ and upcoming ´Battlemage´ graphics cards get the added benefit of XMX hardware accelerators, which further optimize performance. By releasing SDK 2.1.0 to the public, Intel empowers game developers to integrate this suite of features into their titles, further democratizing access to advanced image upscaling and smooth frame generation across multiple hardware platforms, not just Intel GPUs. This marks a strategic move in the competitive graphics ecosystem, as rival hardware now stands to benefit from Intel´s software innovations.

66

Impact Score

LLMSurgeon targets foundation model data auditing

LLMSurgeon introduces a way to infer the domain mix of large language model pretraining data using only generated text. The framework is designed to improve transparency around foundation models whose training corpora remain largely undisclosed.

Databricks model units target lower inference costs

Databricks is positioning model units as a new way to manage large language model inference, aiming to cut GPU spending while improving reliability under enterprise-scale demand. The approach reflects growing pressure on platforms to balance cost, latency, and resilience as agentic Artificial Intelligence workloads expand.

Texas arrests man over Artificial Intelligence-generated child abuse images

Texas authorities arrested a Carrizo Springs man accused of creating hundreds of pornographic images and videos involving children by using Artificial Intelligence tools to manipulate photos taken from public school-affiliated pages. Investigators said the case also uncovered non-Artificial Intelligence-generated child sexual abuse images and identified approximately 30 victims.

Google launches Gemini Omni for conversational video editing

Google has introduced Gemini Omni, a video model that edits and generates clips through natural conversation using text, images, audio, and existing footage. The first public version, Gemini Omni Flash, is now rolling out across the Gemini app, Google Flow, and YouTube Shorts.

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.