AMD unveils Ryzen Threadripper PRO 9000 and Radeon AI PRO 9000 series for workstations

AMD launches the Ryzen Threadripper PRO 9000 and Radeon AI PRO 9000 series, pushing workstation performance for artificial intelligence and visualization workloads.

AMD has officially launched two major hardware announcements tailored for the professional workstation market: the Ryzen Threadripper PRO 9000 ´Shimada Peak´ CPUs and the Radeon AI PRO 9000 graphics cards. The new Threadripper series leverages the latest ´Zen 5´ microarchitecture, introducing workstation-centric capabilities through the ´Shimada Peak´ variant, which is derived from the ´Turin´ multi-chip module also powering AMD´s 5th generation EPYC server processors. On the graphics side, the Radeon AI PRO 9000 series brings the RDNA 4 architecture to professional use-cases, mirroring the core technology found in the Radeon RX 9000 consumer gaming GPUs.

The Ryzen Threadripper PRO 9000 CPUs offer configurations scaling up to 96 cores and 192 threads, a significant leap in compute density suitable for demanding workloads like rendering, simulation, and intensive artificial intelligence tasks. An upgraded instruction per cycle (IPC) count is one highlight of the shift from the previous ´Zen 4´-based Threadripper 7000 series, but equally important is the jump to a full 512-bit floating-point unit. This enables a marked performance boost for applications that depend on the AVX-512 instruction set, making these chips especially appealing to scientific and data analytics domains.

AMD has not only improved compute performance but also refined input/output functionality to meet workstation standards. The I/O die now allows for higher native memory speeds, specifically DDR5-6400, supports AMD EXPO memory profiles, and incorporates CKD, enhancing flexibility and throughput. With modest frequency increases on select models, AMD claims the new platform delivers a 16% overall uplift in workstation benchmarks compared to the prior generation, alongside a striking 25% improvement in SPEC Workstation artificial intelligence and machine learning tests when comparing like-for-like configurations. The newly introduced Radeon AI PRO 9000 series aims to address a continuum of professional GPU workloads, from edge artificial intelligence deployment to advanced visualization, positioning AMD as a comprehensive solutions provider for modern workstations.

64

Impact Score

LLM-PIEval: a benchmark for indirect prompt injection attacks in large language models

Large language models have increased interest in Artificial Intelligence and their integration with external tools introduces risks such as direct and indirect prompt injection. LLM-PIEval provides a framework and test set to measure indirect prompt injection risk and the authors release API specifications and prompts to support wider assessment.

NVIDIA may stop bundling memory with gpu kits amid gddr shortage

NVIDIA is reportedly considering supplying only bare silicon to its aic partners rather than the usual gpu and memory kit as gddr shortages constrain fulfillment. The move follows wider industry pressure from soaring dram prices and an impending price increase from AMD of about 10% across its gpu lineup.

SK Hynix to showcase 48 Gb/s 24 Gb GDDR7 for Artificial Intelligence inference

SK Hynix will present a 24 Gb GDDR7 chip rated for 48 Gb/s at ISSCC 2026, claiming a symmetric dual-channel design and updated internal interfaces that push past the expected 32 to 37 Gb/s. The paper positions the device for mid-range Artificial Intelligence inference and SK Hynix will also show LPDDR6 running at 14.4 Gb/s.

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.