This article was published on February 23rd, 2021.
The low latency performance and massive parallel processing capabilities of Xilinx Alveo accelerator cards make them the perfect foundation on which to build these critical applications, and today Xilinx launched an AI video analytics platform, built on Alveo, with an ecosystem of partner solutions built to accelerate the most complex and latency-sensitive AI video inferencing applications.
The Xilinx platform, powered by the Video Machine-learning Streaming Server (VMSS), delivers whole application acceleration and can support multiple neural networks on a single Alveo accelerator card at deterministic sub-100ms pipeline latency. The result is the industry’s lowest TCO for demanding AI video applications.
Along with the platform itself, solutions in the Xilinx ecosystem available today include:
Aupera, with turnkey smart city and smart retail solutions that combine Aupera’s intelligent video AI processing with Alveo accelerators to deliver best-in-class AI analytics solutions for critical applications.
Mipsology, providing a toolset for easy migration of existing AI applications from GPU-based architectures to the Alveo platform as well as plug-and-play, high-performance AI inference acceleration.
Deep-AI, delivering the industry's first integrated training and inference solution at the Edge on Alveo accelerators. Deep-AI's unique breakthrough INT8 AI training can offer up to a 10x performance per cost advantage compared to GPU-based solutions.
Watch Dr. Seong Kim, Xilinx Senior Director of Datacenter Architecture, as he highlights Aupera deployment options: