Core Overview - 1.3 English

DPUCVDX8G for Versal ACAPs Product Guide (PG389)

Document ID
Release Date
1.3 English

The DPUCVDX8G is a high-performance, general-purpose convolutional neural network (CNN) processing engine optimized for Versal ACAP devices. This IP is user-configurable and exposes several parameters, which can be specified to configure the number of AI Engines used and PL resource utilization. The DPUCVDX8G is composed of both AI Engines and PL.

The AI Engines in the DPUCVDX8G perform convolution. The AI Engine interface tiles transfer data between the AI Engine memory tiles and the PL. For high-performance calculation in some Versal devices, the AI Engine groups are composed of multiple adjacent AI Engines. For a multi-batch DPUCVDX8G architecture, each batch handler has a private AI Engine group and a memory tile group.

The PL component includes a high-level scheduler module, a global memory for shared weights, and batch handlers for Load, Save, Depth-Wise, Pool, and Elt-wise. The scheduler and weights buffer are shared logic among all the  batch handlers. The Load and Save Module, Depth-Wise, Pooling, and Elt-wise Module, and local feature map storage are private for each batch handler.

The top-level block diagram of DPUCVDX8G is shown in the following figure.

Figure 1. DPUCVDX8G Block Diagram