AMD Ryzen 500 series Medusa APUs to debut RDNA 4m graphics and Zen 6 cores

AMD's upcoming Ryzen 500 series Medusa APUs pair Zen 6 CPU cores with new RDNA 4m graphics and LPDDR6 memory, targeting higher performance and bandwidth in laptops, mini PCs, and desktops.

AMD is preparing its next-generation Ryzen 500 series APUs under the Medusa codename, with two main variants called Medusa Point and Medusa Halo. Compiler patches indicate that Medusa Point will use a new RDNA 4m graphics architecture, which is described as a variant of RDNA 4 likely optimized for mobile devices such as laptops and mini PCs. Medusa Point is also expected to introduce a desktop exclusive implementation of RDNA 4 with this RDNA 4m variant, while Medusa Halo is slated to move to AMD’s next-generation RDNA 5 / UDNA GPU microarchitecture for higher end configurations.

The graphics subsystem of Medusa Point is linked to a GPU identified as GFX1170, which is associated with the GFX11 generation, also known as RDNA 3. Instruction set extensions such as WMMA and SWMMAC instructions indicate support in the new GFX1170 GPU and suggest a design that builds on an upgraded RDNA 3 base with many RDNA 4 modules. In this configuration, the upgraded RDNA 3 with many RDNA 4 modules is believed to enable FSR 4 support even on the less powerful Medusa Point APU, potentially extending advanced upscaling capabilities to more mainstream systems.

On the CPU side, AMD is targeting Zen 6 cores across both Medusa variants. Medusa Point is expected to use a mix of Zen 6 and Zen 6c CPU cores, following a similar differentiation strategy seen in current generation APUs, while Medusa Halo is planned to feature a uniform Zen 6 core cluster aimed at maximum CPU performance. The platform is also set to adopt LPDDR6 memory, and the platform will adopt LPDDR6 memory, which will increase the memory bandwidth by 50% over the standard LPDDR5X memory we see implemented today, signaling a substantial boost in bandwidth for integrated graphics and overall system responsiveness.

55

Impact Score

Global Artificial Intelligence governance pulls back

A broad pullback in Artificial Intelligence regulation is taking shape across Colorado, the European Union, Canada, the United Kingdom, and the United States. The shift reflects implementation gaps, competitive pressure, and resistance to heavy compliance burdens rather than the end of governance efforts.

Anthropic launches Claude Mythos for Project Glasswing

Anthropic has introduced Claude Mythos Preview, a new frontier Artificial Intelligence model positioned as a major advance in cybersecurity capability. The model is being used to power Project Glasswing, a coalition effort to secure critical software before similar capabilities spread more widely.

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.