Documentation

Deep learning's demand for computing power is growing at an incredible rate, accelerating recently from doubling every year to doubling every three months. Increasing the capacity of deep neural network (DNN) models has shown improvements across a wide range of areas ranging from natural language processing to image processing. This growth calls for the adoption of customized architectures that squeeze the greatest amount of performance out of each transistor available.

While the performance of an ASIC is typically high enough for broadcast-quality video processing, it supports only the feature set conceived of at design time and is not field upgradable. A CPU is the most flexible and easiest to design; however, clock frequencies have plateaued, and the era of dramatic improvements in performance are over. FPGAs represent a good balance between performance and flexibility for this class of applications.

Communications and networking systems that extend from the edges of the 5G network to the switches inside data centers are placing extreme pressure on the ability of silicon to support the computational and data-transfer rates they require. Traditionally programmable logic provided the best mixture of flexibility and speed for these systems, but has been challenged in recent years by the increase in speed. Through the inclusion of an innovative, multilevel network on chip that allows data to be streamed easily around the device without impacting the FPGA fabric, the Speedster7t architecture ensures all device resources are used to their full potential.

Since the initial introduction of FPGAs decades ago, each new architecture has continued to employ a bit-wise routing structure. While this approach has been successful, the rise of high-speed communication standards has required ever increasing on-chip bus widths to be able to support these new data rates. Achronix's solution was to create a revolutionary 2D high-speed network on chip (NoC) on top of the traditional segmented FPGA routing structure for its new Speedster7t FPGA family.

Intelligent server adapters, or SmartNICs, boost server performance in cloud and private data centers by offloading network processing workloads and tasks from server CPUs. Offloading network processing to a SmartNIC is not a new concept — for example, there are NICs that offload some network-processing functions such as checksum computation and segmentation. However, the rapid explosion in data-center network traffic driven by software-defined networking (SDN), Open vSwitch (OVS), and network functions virtualization (NFV) demands a new class of NIC with even greater offload capabilities: the SmartNIC.