Intel® Core™ Processor (Series 3)
Formerly known as Wildcat Lake, Datasheet, Volume 1 of 2
| ID | Date | Version | Classification |
|---|---|---|---|
| 913965 | 05/19/2026 | 001 | Public |
Functional Description
The NPU IP comprises several individual components grouped into two major subsystems:
Details of these blocks are provided in the next sections.
Host Control
The functionality of the NPU is exposed to a SoC via a base set of registers (enumerated as a PCIe device or directly memory mapped into the address space of the Host).
These registers provide access to control and data path interfaces and reside in the Host Subsystem. All host communications are consumed by the NPU scheduler, a 64-bit RISC-V micro-controller. As well as responding to control messages it manages all the job submission/completion FIFOs that make up the data path of the NPU.Deep Learning (Neural Compute Engine)
The NPU IP Deep Learning capability is provided by a configurable number of Neural Compute Engine (NCE) Tiles. The NCE Tiles are managed by the NPU Scheduler.
Each Tile includes a configurable amount of near-compute SRAM, one Data Processing Unit (DPU) with a configurable number of multiply-accumulates, and two DSPs (SHAVE-512) for optimal processing of custom deep learning operations. Global barriers and task FIFOs are also available for job synchronization and dispatch.
The Intel® Core™ Processor (Series 3) NPU comprises of 1 NCE Tiles, totaling 4k DPU INT8 MACs, 2 DSPs and 2.0 MB of associated near-compute memory.Below is the block diagram of NPU IP: