The Intel Xeon W9-3575X carries a Thermal Design Power (TDP) of 340W and a maximum CPU temperature of 100°C, reflecting the thermal demands of a high-core-count enterprise processor. It is built on a 10nm semiconductor process and fully supports 64-bit computing. Connectivity is handled through PCIe 5, the latest generation of the PCI Express standard, while the processor does not include integrated graphics, keeping it focused entirely on compute tasks.
The processor runs 44 cores at a base clock of 2.2 GHz, delivering 88 threads in total, with the ability to boost up to 4.8 GHz through Turbo Boost version 2. It features a clock multiplier of 22 and, notably, an unlocked multiplier, which allows for manual frequency adjustments beyond default settings. The L3 cache totals 97.5 MB, distributed at 2.22 MB per core, providing a substantial pool of fast-access memory to help sustain throughput across all active threads.
The Xeon W9-3575X supports DDR5 memory across eight channels, enabling a maximum bandwidth of 307.2 GB/s at speeds of up to 4800 MHz. It accommodates up to 4000 GB of total memory, making it well-suited for workloads that require large in-memory datasets. ECC memory support is also included, providing hardware-level error detection and correction to help maintain data integrity during extended operation.
The processor supports multithreading, allowing each physical core to handle multiple threads simultaneously for more efficient utilization under parallel workloads. It includes a broad set of instruction sets — MMX, F16C, FMA3, AES, AVX, AVX2, SSE 4.1, and SSE 4.2 — covering vectorized math, hardware-accelerated encryption, and floating-point operations. The NX bit is also present, enabling hardware-enforced memory protection that helps guard against certain classes of malicious code execution.
In PassMark testing, the Xeon W9-3575X achieves an overall score of 82,620, reflecting strong multi-threaded throughput across its 44 cores. Its single-threaded PassMark result stands at 3,787, indicating the per-core performance available for tasks that do not scale across multiple threads.