[The Exiled]

nVidia details Grace Hopper CPU Superchip design: 144 cores on 4N TSMC process

nVidia's Grace CPU is the company's first CPU-only Arm chip designed for the data center and comes as two chips on one motherboard, totaling 144 cores, while the Grace Hopper Superchip combines a Hopper GPU and the Grace CPU on the same board. Among the most important disclosures, nVdiia finally officially confirmed that the Grace CPUs use the TSMC 4N process. TSMC lists the "N4" 4nm process under its 5nm node family, describing it as an enhanced version of the 5nm node. nVidia uses a specialized variant of this node, dubbed '4N,' that is optimized specifically for its GPUs and CPUs. The Grace CPU has 16 dual-channel LPDDR5X memory controllers, working out to 32 channels that support up to 512 GB of memory and up to 546 GB/s of throughput. nVidia says it selected LPDDR5X over HBM2e due to multiple factors, like capacity and cost. Meanwhile, LPDDR5X provides 53% more bandwidth and 1/8th the power-per-GB compared to standard DDR5 memory, making it the better overall choice.

There are really two reasons nVidia is building its own CPU. First, nVidia wants something that is a more efficient co-processor to the company’s GPUs in large systems. nVidia owns the hardware/ software stack much like Apple, so this is an attempt to become a truly full-stack provider. nVidia does not need Intel/ AMD’s new AI accelerators, it has its own. Likewise, it can build a chip with the right performance attributes to augment a GPU, rather than duplicating other parts. The second reason is more obvious now. nVidia needs to de-couple itself from Intel and AMD. Both are competing with nVidia in HPC and AI. At the same time, the Hopper H100 is waiting for Sapphire Rapids to launch before the DGX H100 can launch. As a result, we are expecting a mid-to-late Q1 2023 debut for Hopper. Given that the chips exist, (see below) nVidia needs a CPU solution so it can sell its GPUs.

Izvor: Tom's Hardware i ServeTheHome