AMD has published the firmware required for its upcoming GFX 11.7-based RDNA 4m graphics. AMD's Upcoming RDNA 4m Graphics Take Another Step Toward Launch as Firmware Support Goes Live AMD is making some significant progress in preparing its next-gen RDNA 4m-based products. It has now added the firmware binaries for the RDNA 4m graphics architecture, providing a major clue that its next-generation APUs are getting closer to release. The firmware has been upstreamed to the "linux-firmware" repository, where Linux distributions can package it alongside the required AMDGPU drivers. The RDNA 4m platform has attracted our attention because it doesn't follow […]

Read full article at https://wccftech.com/amd-publishes-rdna-4m-firmware-ahead-of-launch/

AMD has enabled support for GFX1171 in Mesa 26.3, adding another GPU target under the RDNA 4m family. Latest Mesa Graphics Driver Update Lays the Groundwork for Upcoming Medusa Point Integrated Graphics AMD continues preparing its open-source Linux graphics stack for hardware that hasn't been officially announced yet. You might be aware of the recent changes, as AMD is preparing for the upcoming Zen 6-based Medusa Point chips. One of the latest developments comes in the Mesa 26.3 graphics driver, where developers have added support for GFX1171, which is another GPU target under the RDNA 4m family. GFX1171 isn't a […]

Read full article at https://wccftech.com/amd-adds-new-gfx1171-gpu-support-to-mesa-26-3-hinting-at-future-rdna-4m-graphics/

AMD has started adding Ryzen Zen 6 "client" CPU support for its HSMP driver, spanning Olympic Ridge & Medusa Point families. AMD Ryzen "Zen 6" Client CPU Support Enabled on HSMP Driver: Targets Olympic Ridge & Medusa Point With the launch of the first Zen 6 CPUs in the EPYC 9006 family, AMD is now gearing up to bring the same architecture to its client-based lineups. As per the latest Linux Kernel patches, AMD has enabled support for several Zen 6 client families, which will be part of the Ryzen product portfolio. There are three families listed, which include: The […]

Read full article at https://wccftech.com/amd-seeds-zen-6-client-support-in-linux-olympic-ridge-desktops-medusa-mobile-ryzen-chips/

The hardware monitoring tool has added early support for the upcoming AMD and Intel CPU families. AIDA64 v8.35 Rolls Out With Support for AMD Zen 6 Processors, Including Mainstream CPUs/APUs, and Mustang Peak Threadripper Chips This isn't the first time we've seen AMD Zen 6 being mentioned in release notes, but it's surely a big update as it brings support for several upcoming CPU families from both AMD and Intel. AIDA64 remains a popular hardware monitoring utility that usually adds support for next-gen hardware early, similar to other monitoring software. The latest AIDA64 version 8.35 has been released, which adds […]

Read full article at https://wccftech.com/aida64-adds-support-for-amd-zen-6-cpus-apus-and-mustang-peak-chips-alongside-intel-panther-lake-r/

An engineering sample of AMD's upcoming 10-core Medusa Point mobile processor has surfaced on Geekbench, achieving its highest benchmark scores to date. The chip reached 3,329 points in the single-core test and 16,555 points in the multi-core test, marking a notable performance jump over previous-gen chips.

The processor appeared on Geekbench (via Tom's Hardware) on an AMD Plum-MDS1 platform under the engineering sample identifier 100-000001713-33_N. Geekbench logs reveal a configuration with 10 cores and 20 threads, divided into two clusters of 4 and 6 cores. Telemetry data indicate that the chip reached a peak frequency of 5.37GHz during testing. The listing also details 10MB of L2 cache and 32MB of L3 cache.

This latest run outperforms a previous submission by 5% on single-core and 10% on multi-core. When compared with current retail models, this Zen 6 chip delivers a significant performance boost. It scores roughly 28% higher in single-core workloads and 24% higher in multi-core workloads than the 12-core Ryzen AI 9 HX 370, which averages 2,605 and 13,397 points, respectively.

While final clock speeds and power limits remain unconfirmed, the Medusa Point lineup is expected to form the foundation of AMD's upcoming mobile Ryzen 500 series.

KitGuru says: AMD's Zen 6 mobile architecture is shaping up to deliver a substantial performance uplift, if these early engineering-sample benchmarks are anything to go by.

AMD Medusa Point "Zen 6" CPUs are making some decent progress, and if we go by the latest benchmark numbers, these are faster than we expected. 10-Core amd Medusa Point Engineering Sample Delivers 3,329 Points in Single and 16,555 Points At 5.4 GHz in Multi-Core Geekbench Tests Looks like we underestimated the Medusa Point a bit. We continue to see leaked benchmarks for the upcoming Zen 6-based series CPUs, and now, with another set of benchmarks, it's clear that AMD has been aiming for a much higher uplift than we expected. Nearly 10 days ago, we posted the first-ever benchmarks […]

Read full article at https://wccftech.com/amd-medusa-point-10-core-zen-6-5-4-ghz-cpu-beats-strix-point-10-core-zen-5/

AMD's Medusa Point "Zen 6" APUs have leaked out once again at Geekbench, showcasing even higher performance than earlier. AMD Medusa Point "Zen 6" CPU Showcases Strong Single & Multi-Core Performance At 2 GHz A few months ago, we reported the first sighting of AMD's Medusa Point within the Geekbench database. The chip was spotted on the Plum-MDS1 platform, which features the new FP10 BGA socket, and is the Evaluation platform designed for next-gen AMD SoCs in the 28-45W range. The last performance numbers were quite good given that the chip was operating at 2.40 GHz, but now we have […]

Read full article at https://wccftech.com/amd-medusa-point-10-core-cpu-beats-strix-by-29-percent-in-single-core-at-just-2-ghz/

AMD's upcoming product stack is a complete mystery, but here are a few things we can expect at Computex. Zen 5-Based Desktop/Mobile Chips, Zen 6-Based Medusa Point, and More; Here's Everything We Know About AMD's New Product Stack The Computex 2026 event is scheduled for next week in Taipei, Taiwan, and major vendors have already prepared for their presentations. After CES, this event is the most anticipated one throughout the year, as almost every hardware maker presents their new and upcoming product stacks. The three major hardware players are also expected to reveal the latest hardware at the event, including […]

Read full article at https://wccftech.com/amd-computex-2026-what-to-expect/

New LLVM patches confirm additional RDNA 4m variants alongside GFX1170 with similar instruction capabilities. AMD Quietly Expands Next-Gen iGPU Roadmap by Adding New RDNA 4m Graphics Targets, GFX1171 and GFX1172 Earlier compiler patches showed that RDNA 4m incorporates several RDNA 4-style instruction-set upgrades, such as support for FP8 and BF8 data formats, along with WMMA matrix instructions used in AI workloads. Now, AMD is further expanding its next-gen integrated GPU roadmap, as new Linux compiler patches unveil two additional RDNA 4m graphics targets. These are the GFX1171 and GFX1172. These targets are now joining the recently discovered GFX1170, confirming that […]

Read full article at https://wccftech.com/amd-adds-rdna-4m-gpu-targets-gfx1171-and-gfx1172-hinting-at-next-gen-zen-6-apu-graphics/

The first signs of AMD's next-generation “Medusa Point” mobile silicon have surfaced on Geekbench, providing a first look at the architecture expected to arrive in laptops next year. While the benchmark scores are negligible due to the chip running at a low clock speed of roughly 1.39GHz, the technical specifications revealed in the entry confirm major architectural shifts.

The chip is listed on Geekbench (via Wccftech) as a 10-core, 20-thread part, similar to the Ryzen AI 9 365 and Ryzen AI 9 465. Given that all cores appear to have SMT (two threads per core), none of them should be low-power cores dedicated to background tasks.

Perhaps the most significant piece of information taken from the Geekbench entry is the cache upgrade. The sample features 32MB of L3 cache, a 50% increase over current 10-core parts like the Ryzen AI 9 365 (24MB) and double that of the older Hawk Point (16MB). Each core also has 1MB of L2 cache. Medusa Point is rumoured also to feature a new type of integrated graphics, combining RDNA 5 and RDNA 3.5 IP with an updated NPU to meet the increasingly demanding local AI requirements of 2027-era operating systems.

While a launch isn't expected until 2027, the presence of a functional engineering sample in a public database suggests that AMD is well into the validation phase of the 3nm Zen 6 process.

Discuss on our Facebook page, HERE.

KitGuru says: The increased cache is a nice upgrade but shouldn't be the only one on the CPU side of this APU. What other specs do you expect to see improve with the new generation of Ryzen AI mobile APUs?

The technical picture for AMD's next-generation Medusa Point APUs is becoming clearer through recent Linux compiler activity. The emergence of the GFX1170 target, explicitly labelled as “RDNA 4m”, suggests AMD will finally bring FSR4 support to its APUs.

As noted by Phoronix (via TechPowerUp), while technically part of the GFX11 (RDNA 3) family, GFX1170 is receiving specific instruction-set updates that move it closer to GFX12 (RDNA 4) behaviour, effectively creating a “Pro” version of the current RDNA 3.5 architecture. Some of the changes include adding the WMMA (Wave Matrix Multiply-Accumulate) and SWMMAC instructions, along with support for FP8 and BF8 data formats. These matrix-oriented instructions are the cornerstone of modern AI and machine learning workloads.

By implementing WMMA128b variants specifically for GFX1170, AMD is providing the foundation necessary for neural-link upscaling and frame interpolation. This architectural “hybridisation” is precisely what will allow mainstream Zen 6 APUs to support FSR 4, even without a full transition to the GFX12 graphics.

The introduction of the “m” suffix (presumably standing for “Mobile”) suggests that AMD views GFX1170 as a bridge to keep its high-volume APUs from falling behind the competition. By allowing the hardware to handle 8-bit floating-point operations natively, AMD is expanding the “Redstone” ecosystem, ensuring that even a thin-and-light laptop in 2026 can run the latest AI-enhanced titles with acceptable frame rates.

Discuss on our Facebook page, HERE.

KitGuru says: With FSR 4 bringing so many improvements over previous versions, AMD should ensure that it works across as many products as possible.