Hands-on with AMD Ryzen AI Max, Ryzen AI Pro, and EPYC 9006 Processors

AMD showcases its cutting-edge Artificial Intelligence processors, including Ryzen AI Max, Ryzen AI Pro, and EPYC 9006, targeting both client and enterprise markets.

AMD has unveiled its latest lineup of client and enterprise processors, providing a detailed look at new technologies and design advancements. Leading the showcase is the Ryzen AI Max ´Strix Halo,´ a notably large processor that stands out with a chiplet design featuring a prominent SoC and integrated graphics tile. Built on the TSMC N4P process, the Strix Halo integrates two ´Zen 5´ Core Complex Dies (CCDs), each drawn from the family shared by ´Granite Ridge,´ ´Fire Range,´ and ´Turin.´ These CCDs offer full 512-bit data paths for the floating-point unit and substantial 32 MB L3 caches per CCD, aimed at delivering top-end computational performance.

The SoC and graphics tile of Ryzen AI Max features an integrated GPU with 40 compute units, further enhanced by a 256-bit wide LPDDR5X memory interface. This combination results in a package size approaching that of high-end GPUs, reflecting both the complexity of the architecture and the high memory bandwidth requirements. The processor is designed with Artificial Intelligence workloads in mind, balancing compute and graphics power for advanced client applications.

Continuing its focus on Artificial Intelligence, AMD presents the Ryzen AI 9 HX Pro mobile processor. Utilizing the familiar mobile processor package, it is built on the ´Strix Point´ monolithic silicon platform—also leveraging the TSMC N4P process. The Pro series includes business-oriented features as part of the AMD Pro suite and is tailored for commercial notebooks, underscoring security and manageability for enterprise clients. AMD also reveals the Ryzen Z2 Extreme, which uses an optimized ´Strix Point´ design with some CPU cores disabled but a fully enabled 16-CU iGPU. This processor is aimed at gaming handhelds, providing a powerhouse solution for portable gaming.

At the enterprise level, AMD showcases the EPYC 9006 ´Turin´ processor. This server-class chip boasts 12 ´Zen 5´ CCDs, exemplifying AMD´s commitment to scaling up its high-performance processor technology for data center and enterprise deployments. All these processors illustrate AMD´s wide-reaching approach, from handheld gaming systems to commercial notebooks and massive server environments, marking significant steps forward in both Artificial Intelligence and general compute performance.

71

Impact Score

Saudi Artificial Intelligence startup launches Arabic LLM

Misraj Artificial Intelligence unveiled Kawn, an Arabic large language model, at AWS re:Invent and launched Workforces, a platform for creating and managing Artificial Intelligence agents for enterprises and public institutions.

Introducing Mistral 3: open artificial intelligence models

Mistral 3 is a family of open, multimodal and multilingual Artificial Intelligence models that includes three Ministral edge models and a sparse Mistral Large 3 trained with 41B active and 675B total parameters, released under the Apache 2.0 license.

NVIDIA and Mistral Artificial Intelligence partner to accelerate new family of open models

NVIDIA and Mistral Artificial Intelligence announced a partnership to optimize the Mistral 3 family of open-source multilingual, multimodal models across NVIDIA supercomputing and edge platforms. The collaboration highlights Mistral Large 3, a mixture-of-experts model designed to improve efficiency and accuracy for enterprise artificial intelligence deployments starting Tuesday, Dec. 2.

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.