Alveo U25N
(2x 10G/25G)
Cost-effective, turnkey network acceleration for Open vSwitch (OVS), IPsec, firewall, QoS, and more.
Offloading work from the CPU to drive greater performance and efficiency
AMD solutions help accelerate infrastructure tasks in modern data centers, freeing up CPU cycles to perform high-value, business-critical functions.
With familiar FPGA development flows and comprehensive IP and reference designs, Alveo™ SmartNICs and network accelerators enable customizable datapaths to meet the diverse needs of hyperscalers, cloud service providers, telco operators, and enterprise data centers.
The Vivado™ Design Suite offers hardware developers a design environment and methodology for Alveo SmartNICs and network accelerators, including RTL programming, GUI-based IP integration, and a cohesive verification and implementation environment. A complete open-source NIC design (OpenNIC) is also available to simplify FPGA development of inline networking applications—featuring pre-built ethernet or QDMA subsystems, DPDK Linux® drivers, and AXI-based connectivity for ease of integration into custom IP.
Built on the same technology that many hyperscalers use, the heart of the AMD Pensando™ platform is the fully-programmable P4 data processing unit (DPU). It is optimized to execute a software stack delivering cloud, compute, network, storage, and security services at cloud scale—with minimal latency, jitter, and power requirements.
Where other vendors have roadmaps, AMD Pensando has an established solution in production today, with customers including Goldman Sachs, Microsoft Azure, NetApp, and Oracle Cloud Infrastructure.
AMD Solarflare™ Ethernet adapters are designed for high-performance electronic trading environments and enterprise data centers—including artificial intelligence, big data, analytics, hyperscale, machine learning, storage, and telco applications.
With low latency and high throughput, these Ethernet adapters provide real-time packet and flow information to thousands of virtual NICs. This combination of ultra-high bandwidth, ultra-low latency, ultra-scale connectivity, and packet telemetry allows for simplified scaling with each server, virtual machine, or container.
For cloud data centers, Onload™ application acceleration software dramatically accelerates and scales network-intensive workloads such as in-memory databases, software load balancers, and web servers.
In electronic trading environments, Onload kernel bypass application acceleration and DPDK services deliver superior small packet performance with sub-microsecond hardware latency.
With the widespread adoption of high-speed storage and the increased performance requirements of data-intensive applications, traditional architectures have created CPU, memory, and storage bottlenecks.
AMD FPGAs power computational storage devices that help move information processing closer to where the data resides. This helps reduce system-level bottlenecks, increase parallelism, and reduce overall power requirements.
Learn how Versal Premium Series Gen 2 devices are ideal for a wide range of storage applications in the data center including custom enterprise SSD’s, encryption/compression accelerators, memory pooling, and live migration.
The Vivado Design Suite offers hardware developers a design environment and methodology for customizing AMD FPGAs, including RTL programming, GUI-based IP integration, and a cohesive verification and implementation environment.
Contact an AMD Sales representative.