The Intel Xeon 6952P is a server/workstation processor with 96 cores, launched in September 2024. It is part of the Xeon 6 lineup, using the Granite Rapids-AP architecture with Socket 7529. Thanks to Intel Hyper-Threading the core-count is effectively doubled, to 192 threads. To further increase overall system performance, up to two Xeon 6952P CPUs can work together in a multi-processor (SMP) configuration. Xeon 6952P has 480 MB of L3 cache and operates at 2.1 GHz by default, but can boost up to 3.9 GHz, depending on the workload. Intel is making the Xeon 6952P on a 5 nm production node, the transistor count is unknown. The multiplier is locked on Xeon 6952P, which limits its overclocking potential.
With a TDP of 400 W, the Xeon 6952P is extremely power hungry, which means you need top-notch cooling. Intel’s processor supports DDR5 memory with a twelve-channel interface. The highest officially supported memory speed is 6400 MT/s, but with overclocking (and the right memory modules) you can go even higher. ECC memory is supported, too, which is an important capability for mission-critical systems, to avoid data corruption. For communication with other components in the machine, Xeon 6952P uses a PCI-Express Gen 5 connection. This processor lacks integrated graphics, you might need a graphics card.
Hardware virtualization is available on the Xeon 6952P, which greatly improves virtual machine performance. Additionally, IOMMU virtualization (PCI passthrough) is supported, so that guest virtual machines may directly use host hardware. Programs using Advanced Vector Extensions (AVX) can run on this processor, boosting performance for calculation-heavy applications. Besides AVX, Intel has added support for the newer AVX2 and AVX-512 instructions, too.