For those not in the know, Grace CPU Superchip is a 144-core server processor built to accelerate AI and HPC workloads, but not a lot else is known about it.
Ahead of its presentation at Hot Chips 34, Nvidia said that the processor will use a specialised version of TSMC’s 4nm process node, It also released the power efficiency figures for its NVLink-C2C interconnect which will consume 5x less power than the PCIe 5.0 interface while delivering up to 900 GB/s of throughput, among other benchmark data.
It will have 1TB/s of memory bandwidth and 396MB on-chip cache that Nvidia claims will be the fastest processor on the market for workloads ranging from AI to HPC and more.
Nvidia CEO Jensen Huang said that the Grace CPU Superchip offers the highest performance, memory bandwidth and Nvidia software platforms in one chip and will shine as the CPU of the world’s AI infrastructure.
Although it remains unclear when the new superchip will be widely available, Nvidia recently revealed it will feature in a range of new pre-built servers launching in the first half of 2023.