[DigitalToday reporter Jae-won Choi] AMD has launched the 6th-generation EPYC 9006 server processor with up to 256 cores, stepping up its push into the AI data center market. It is seeking to strengthen its competitiveness in the AI infrastructure market by highlighting server computing performance that surpasses Nvidia and Intel.

On Nov. 11 (local time), Taiwan outlet IT Home reported that AMD officially launched the SP7 platform, the first product family of its 6th-generation EPYC processor previously known by the codename Venice, a day earlier on Nov. 10.

The new product is based on the Zen 6 architecture and supports up to 256 cores and 512 threads. It applies next-generation connectivity technologies including DDR5 and high-bandwidth MRDIMM memory, as well as PCIe 6.0 and CXL 3.1.

AMD stressed that the role of server CPUs is expanding as AI spreads. It said high core density and memory bandwidth are needed to carry out multiple tasks at the same time, including running AI agents, data retrieval, program processing and database integration.

It also claimed performance that outpaces competing products. According to AMD, a dual-CPU server equipped with the EPYC 9996 recorded up to 3.7 times higher integer computing performance than a system based on Nvidia Vera CPUs and 2.2 times higher performance than an Intel Xeon 6980P system.

It also said the processors are optimized for AI-specific tasks. The high-clock products operate at up to 5.3 GHz and can increase large language model (LLM) output throughput by up to 1.8 times from the previous generation, AMD said.

Those figures, however, are based on AMD's internal measurements or estimates. Actual performance can vary depending on server configuration and the type of workload.

Along with the new processors, AMD also highlighted Helion, a rack-scale AI infrastructure design. It supports companies in building large-scale AI agent execution environments by choosing CPU and GPU configurations, cooling methods and connection structures.

Servers based on the 6th-generation EPYC have begun shipping through major manufacturers. Microsoft (MS) Azure is providing a preview of related cloud services, and Oracle Cloud Infrastructure (OCI) is set to roll out services applying the new products.

AMD plans to continue expanding product lines tailored to uses such as AI host nodes, enterprise servers and high-performance computing.