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

Samsung shows 96% power reduction in NAND flash

Samsung researchers report a design that combines ferroelectric materials with oxide semiconductors to cut NAND flash string-level power by up to 96%. The team says the approach supports high density, including up to 5 bits per cell, and could lower power for data centers and mobile and edge-Artificial Intelligence devices.

the download: fossil fuels and new endometriosis tests

This edition of The Download highlights how this year’s UN climate talks again omitted the phrase “fossil fuels” and why new noninvasive tests could shorten the nearly 10 years it now takes to diagnose endometriosis.

SAP unveils EU Artificial Intelligence Cloud: a unified vision for Europe’s sovereign Artificial Intelligence and cloud future

SAP launched EU Artificial Intelligence Cloud as a sovereign offering that brings together its milestones into a full-stack cloud and Artificial Intelligence framework. The offering supports EU data residency and gives customers flexible sovereignty and deployment choices across SAP data centers, trusted European infrastructure or fully managed on-site solutions.

HPC won’t be an x86 monoculture forever

x86 dominance in high-performance computing is receding – its share of the TOP500 has fallen from almost nine in ten machines a decade ago to 57 percent today. The rise of GPUs, Arm and RISC-V and the demands of Artificial Intelligence and hyperscale workloads are reshaping processor choices.

A trillion dollars is a terrible thing to waste

Gary Marcus argues that the machine learning mainstream’s prolonged focus on scaling large language models may have cost roughly a trillion dollars and produced diminishing returns. He urges a pivot toward new ideas such as neurosymbolic techniques and built-in inductive constraints to address persistent problems.

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.