Below is a summary of the blog contributed by AMD
AMD introduced the Pollara 400, a specialized network accelerator card, as a building block for creating a robust AI infrastructure. It is designed to address the limitations of traditional RoCEv2 Ethernet networks by integrating features such as real-time telemetry, adaptive packet spray with intelligent path aware congestion control to alleviate incast scenarios, selective acknowledgement, and robust error detection.
“With its ability to deliver high throughput, low latency, and exceptional scalability, combined with the flexibility of P4 programmability, AMD Pensando™ Pollara 400 is an essential tool in the arsenal of any AI cloud infrastructure. This programmable approach not only enhances the NIC’s versatility but also allows for rapid deployment of new networking features, ensuring that AI infrastructures can evolve as quickly as the AI technologies they support.”