AMD Unveils Ryzen Threadripper PRO 9000 ´Shimada Peak´ for Workstations

AMD debuts its Ryzen Threadripper PRO 9000 series, equipped with the latest ´Zen 5´ architecture and designed to accelerate demanding workloads like Artificial Intelligence and design.

AMD has introduced its latest Ryzen Threadripper PRO 9000 series processors, codenamed ´Shimada Peak´, at Computex 2025. Targeting high-end desktops and workstation environments, these chips are based on the cutting-edge ´Zen 5´ microarchitecture. The new lineup is a modified adaptation of the EPYC ´Turin´ multi-chip module, engineered for Socket TR5 and offering 128 PCIe Gen 5 lanes. However, unlike their server counterparts, these Threadripper variants forego CXL support, and are equipped with 8-channel DDR5 memory (comprised of 16 sub-channels), a step down from Turin’s 12-channel capability.

The flagship CPU in this series, the Ryzen Threadripper PRO 9995WX, features an impressive 96-core and 192-thread design. It supports a maximum boost clock of 5.40 GHz and includes a vast sum of 384 MB L3 cache arranged in a 12x 32 MB configuration. The memory architecture, restricted to 8 channels of DDR5, is specifically tuned for high-performance professional applications. PCIe Gen 5 support extends across 128 lanes, providing ample bandwidth for advanced graphics, NVMe storage, and networking add-ons prevalent in workstation settings.

AMD asserts that the Threadripper PRO 9995WX achieves performance gains of 10-20% in Cinebench 2024 nT compared to the previous-generation 7995WX based on ´Zen 4´. The new chip also claims a dominant lead over Intel’s Xeon W9-3595X, showing up to 220% better performance in certain workloads. In multimedia, design, architectural modeling, scientific computation, and Large Language Model inferencing, the new Threadripper is said to outperform the Xeon W9-3595X by margins ranging from 44% to 145%. The Threadripper PRO 9000 lineup will be launched exclusively through original equipment manufacturers, including Lenovo, marking a focused approach on professional users and enterprise clients.

61

Impact Score

Artificial Intelligence LLM confessions and geothermal hot spots

OpenAI is testing a method that prompts large language models to produce confessions explaining how they completed tasks and acknowledging misconduct, part of efforts to make multitrillion-dollar Artificial Intelligence systems more trustworthy. Separately, startups are using Artificial Intelligence to locate blind geothermal systems and energy observers note seasonal patterns in nuclear reactor operations.

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.

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.