AMD Share Details of Upcoming Zen 2 Chips

Postado Novembro 08, 2018

Today at Next Horizon, AMD (NASDAQ: AMD) and Amazon Web Services, announced the immediate availability of the first AMD EPYC processor-based instances on Amazon Elastic Compute Cloud (EC2).

Performance wise, EPYC Rome will bring 2x the performance per socket and 4x floating point per socket improvements, compared to the previous generation.

"The multi-chip processor uses 7nm process technology for the "Zen 2" CPU cores that benefit from the advanced process technology, while leveraging a mature 14nm process technology for the input/output portion of the chip".

Following up Intel's announcement of new Xeon server processors recently, AMD is firing a return salvo of their own to lay claim to more real estate in the enterprise CPU market. AMD is expecting the per socket performance to double because of the higher core count, and the floating point performance per socket to improve by four times due to the architectural IPC improvements along with the core count increase.

AMD also talked about Zen 2 CPU core and modular design methodology with the so-called chiplet design but we will cover that one in a separate article. According to AMD, the performance uplift is 25% over their current 12nm Zen+ offering. In a floating-point-intensive ray tracing demonstration of a single 64-core Rome CPU prototype running alongside a dual-socket Intel Xeon Platinum 8180M server, the new AMD chip was seen to beat its competitor. This offers not only higher IPCs and a significant increase in overall performance, but also improved security features in the recently announced EPYC CPU "Rome".

Zen 2 will be the building block of its Ryzen and Ryzen Threadripper desktop CPUs as well as its EPYC server CPUs and is the most significant step in Zen's timeline for a number of reasons.

AMD HAS TAKEN the covers off is Zen 2 processor architecture, showcasing its 7-nanometre design and effectively paving the way for next-generation Ryzen CPUs. But because of continued delays in Intel's 10nm effort, AMD lucked out; it will be shipping some of the fastest and most power-efficient silicon in the datacenter next year. It's next-generation Epyc chips combine up to eight 7nm CPU "chiplets" with a central 14nm I/O die supporting 8-channel DDR4 memory and PCIe 4.0.

Yet they do pave the way for the next wave of Ryzen processors.

AMD is now sampling EPYC "Rome" chips with customers, with the chips expected to launch sometime in 2019. The chips will be manufactured by TSMC on its leading 7nm node, which the company says will give it a significant advantage over Intel, which is now struggling with its own 10nm process. Nearly certainly, the Ryzen 3 family will make use of the 7nm Zen 2 architecture, which could see AMD push ahead of Intel in the raw performance and clock speed stakes, as Intel is still on the 14nm process node given it has kept pushing back the debut of 10nm-based CPUs due to problems with manufacturing them at scale.