The AMD DPUCAHX8H is a programmable DPU core optimized for convolutional neural networks, mainly for high throughput applications on AMD 16 nm AMD Alveo™ HBM cards. The core includes a high-performance scheduler module, a hybrid computing array module, an instruction fetch module, and a tensor buffer module. It uses a specialized instruction set that enables efficient inference of many convolutional neural networks. Some examples of convolutional neural networks that are deployed include VGG, ResNet, GoogLeNet, YOLO, SSD, FPN, and many others.
The DPUCAHX8H is implemented in the programmable logic (PL) of the Alveo U280/U55C and U50/U50LV Data Center accelerator cards.