AMD, which after a strong push into the data center using the ARM architecture a few year ago that eventually withered seemed to have all but conceded the server market to Intel, is back at it. This time, it’s returning to x86 and targeting the high end of the market.
The company on Tuesday previewed its upcoming Naples CPU, designed for cloud and dedicated corporate data centers. Naples is a System on Chip, or SoC, meaning it integrates multiple devices in a single package, including processor cores, memory chips, and connectivity.
In a statement, Forrest Norrod, senior VP and general manager of AMD’s Enterprise, Embedded, and Semi-Custom business unit, said the preview marked “the first major milestone in AMD re-asserting its position as an innovator in the data center and returning choice to customers in high-performance server CPUs.”
The announcement comes on the eve of the Open Compute Summit, which kicks off Wednesday in Santa Clara, California. AMD plans to unveil the details of its new data center strategy at the event, so stay tuned for more coverage by Data Center Knowledge later this week.
For now, here are the core features of AMD Naples:
- A highly scalable, 32-core System on Chip (SoC) design, with support for two high-performance threads per core
- High memory bandwidth, with eight channels of memory per "Naples" device. In a two-socket server, support for up to 32 DIMMS of DDR4 on 16 memory channels, delivering up to 4 terabytes of total memory capacity.
- The processor is a complete SoC with fully integrated, high-speed I/O supporting 128 lanes of PCIe 34, negating the need for a separate chipset.
- A highly-optimized cache structure for high-performance, energy efficient compute
- AMD Infinity Fabric coherent interconnect for two "Naples" CPUs in a 2-socket system
- Dedicated security hardware