AMD's Stance on FSR 4.1 for RDNA 3.5: Conflicting Statements Spark Confusion

Conflicting Internal Messages

During the recent Computex 2026 event, a lack of clarity emerged regarding AMD's strategy for its FSR 4.1 upscaling technology. Reports surfaced from an interview conducted by HardwareLuxx with David McAfee, AMD’s corporate vice president and general manager of the client division, suggesting that the company currently has no intentions of bringing AI-powered FSR 4.1 to GPUs based on the RDNA 3.5 architecture.

However, this narrative was immediately challenged by Frank Azor, who oversees client and graphics marketing at AMD. Taking to social media, Azor contested the claim, stating:

«I wasn't there to hear the exact words said however I will that no such decision as being reported and implied here has been made. We are not ready to speak to any other potential future product plans at this time. We continue to listen to our customers and we hear you.»

The Technical Hurdle of RDNA 3.5

The RDNA 3.5 architecture is primarily utilized in integrated GPUs found within Ryzen AI 300/400/Max processors and the Ryzen Z2 Extreme APUs, which are popular choices for handheld gaming devices. Currently, these units rely on FSR 3.1, a shader-based solution that lacks the sophisticated AI-driven quality of the upcoming FSR 4 iterations.

Implementing FSR 4.1 on these chips poses a significant challenge. Unlike the upcoming RDNA 4, the RDNA 3.5 architecture lacks the specialized matrix processing capabilities required for high-performance AI upscaling. Experts suggest that forcing the technology onto these smaller chips could result in a performance degradation significant enough to render the feature ineffective.

Looking Ahead

AMD has already committed to rolling out official FSR 4 support for RDNA 3 GPUs later this July, with RDNA 2 support expected in early 2027. Despite the apparent lack of architectural barriers when comparing RDNA 3 to RDNA 3.5, the consensus remains that integrated solutions may simply lack the necessary raw computational horsepower to execute complex AI algorithms at the required speeds.

The ambiguity created by these conflicting statements from top executives leaves both users and analysts uncertain. Whether the limitation is purely technical or a strategic marketing choice, the lack of a unified message from AMD continues to complicate expectations for users of mobile and handheld gaming hardware.