AMD ´GFX13+´ Target Surfaces in Code, Hints at UDNA/RDNA 5 Architecture

A new kernel code discovery links AMD´s upcoming ´GFX13+´ GPU target to the unified UDNA and advanced RDNA 5 architectures, signaling big shifts in future gaming and enterprise graphics hardware.

Recent kernel-level software updates have revealed the presence of an AMD ´GFX13+´ target, fueling speculation about its connection to the company´s next-generation graphics architecture roadmap. Notably, renowned leaker Kepler L2 identified this new GPU reference within open-source code, reminiscent of previous findings that connected ´GFX12´ to AMD´s RDNA 4-based Radeon RX 9000 family. These discoveries typically emerge from vigilant data miners monitoring AMD´s transparent open-source development efforts, which often provide early hints about upcoming hardware generations. While official statements emphasized RDNA 4 as a desktop priority, leaks regarding discrete mobile variants have also surfaced, and RDNA 3.5 continues as a staple for integrated graphics solutions.

As AMD looks beyond this current slate of architectures, the company has announced plans for a unified GPU strategy. Last year, AMD leadership unveiled the ´UDNA´ initiative, aimed at blending the technologies found in RDNA (consumer and gaming) and CDNA (enterprise, data center) lines. This convergence would deliver a GPU platform capable of addressing both markets and competing more directly with rivals like Nvidia’s CUDA platform. Recent patent leaks and code properties labeled ´ENABLE_WAVEFRONT´ and ´ENABLE_WAVEGROUP´ suggest that future hardware, likely RDNA 5 or early UDNA iterations, could feature advanced streaming and workload coalescing capabilities to reduce execution divergence and improve overall efficiency.

These code indicators, believed to relate to a Streaming Wave Coalescer mechanism managing wavefront execution and order, align with persistent rumors that RDNA 5 and UDNA could achieve the scalability needed for higher-end gaming segments and deliver Blackwell-style ray tracing performance. For now, RDNA 4 powers up to the Navi 48-based Radeon 9070 XT, but mounting leaks and industry commentary hint that UDNA-enabled hardware may soon transform AMD’s portfolio across consumer and enterprise GPU markets, aligning its roadmaps for both game consoles like a prospective PlayStation 6 and advanced desktop offerings.

77

Impact Score

vLLM server brings OpenAI compatible APIs to local and cloud models

vLLM exposes an OpenAI compatible HTTP server for text, chat, embeddings, audio, and multimodal workloads, while adding its own extensions for pooling, scoring, and re-ranking. It is designed to let existing OpenAI clients talk to local or self-hosted models with minimal code changes.

SK hynix debuts 1c LPDDR6 memory with 16 Gb capacity and higher speeds

SK hynix has developed 1c-node LPDDR6 memory with 16 Gb capacity, targeting speeds beyond 10.7 Gbps and improved power efficiency for next-generation devices. The company plans to start mass production in the first half of the year and ship to customers in the second half.

Nvidia debuts rtx mega geometry with next gen ray tracing demos

Nvidia introduced rtx mega geometry at gdc 2026 alongside its geforce rtx 50 series, showcasing new techniques for handling extreme geometric detail in ray traced scenes. Early demos in alan wake 2 and the witcher 4 highlight performance gains and memory savings from nested triangle clusters.

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.