AMD Versal™ AI Core Series

Programmable Logic

Programmable logic enables the development of custom computational blocks for ever-changing algorithms. The rearchitected logic in Versal adaptive SoCs provides 4X density per CLB, reducing the need for costly global routing. Loaded with a wide variety of memory elements and tightly coupled with programmable I/O, the programmable logic allows users to create powerful accelerators for any application.

AI Engines and DSP Engines

AI Engines provide up to 5X higher compute density for vector-based algorithms. Optimized for real-time DSP and AI/ML computation, AI Engines provide deterministic performance.

Enhanced DSP Engines provide support for new operations and data types, including single and half-precision floating point and complex 18x18 operations.

Next-Generation I/O

The Versal Prime series combines PCIe® Gen5/Gen4 compliance, high-performance GPIO, 400G High-Speed Crypto (HSC) Engines*, and multirate Ethernet MACs supporting various Ethernet configurations to maximize connectivity and flexibility. Additionally, Versal Prime series devices feature rearchitected low-latency 32.75 Gb/s transceivers, and certain devices support 58 Gb/s and 112 Gb/s* PAM4 transceivers.

^{* Only the VM2152 device supports 400G HSC Engines and 112 Gb/s PAM4 transceivers}

Programmable Network on Chip

The programmable network on chip (NoC) provides an optimized multi-terabit interconnect between the different compute engines and integrated IP blocks present in the Versal adaptive SoC architecture, simplifying timing closure and saving logic resources. The NoC compiler provides a streamlined programming experience while allowing users to manage latency and QoS, ensuring that critical data paths are prioritized.