MSEI/MSCE Research Internships

With the advent of research on the next generation of
mobile communications 6G, we are engaged in exploring
architecture extensions for Smart Network Interface Cards
(SmartNICs). To enable adaptive, energy-efficient and
low-latency network interfaces, we are prototyping a
custom packet processing pipeline on FPGA-based NICs,
partially based on the open-nic project
(https://github.com/Xilinx/open-nic).

To test the performance of a SmartNIC-assisted server
under peak loads and achieve precise measurements of
key performance indicators (KPIs) such as throughput and latency, high performance packet trace replay and measurements are required. As software mechanisms for replay of 100Gbps traffic is difficult, an FPGA-based Network Tester for 100 Gbps links shall be implemented and tested. For this, the Alveo U55C FPGA-based SmartNICs shall be used. A previous implementation for 10Gbps links (FlueNT10G) can be used for reference.

The goal of this work is to implement the required logic modules in HDL (Verilog), integrate these modules into the OpenNIC Shell platform and test the design on the Alveo U55C FPGAs. Additionally, a software-interface to control the network tester and feed the packet traces should be adapted from the FlueNT10G. The design should also be evaluated regarding the performance of the packet replay as well as the precision in throughput and latency measurement.

Prerequisites

With the advent of research on the next generation of
mobile communications 6G, we are engaged in exploring
architecture extensions for Smart Network Interface Cards
(SmartNICs). To enable adaptive, energy-efficient and
low-latency network interfaces, we are prototyping a
custom packet processing pipeline on FPGA-based NICs,
partially based on the open-nic project
(https://github.com/Xilinx/open-nic).

Modern server architectures face constant challenges in
performance and energy efficiency. SmartNICs offer a
promising solution by offloading packet preprocessing and collecting real-time traffic analytics. These capabilities allow servers to dynamically adapt to changing network conditions and processing demands. However, operating at speeds of 100 Gbps generates massive data volumes that require sophisticated monitoring and debugging capabilities.

This thesis focuses on designing and implementing advanced hardware extensions for debugging and tracing SmartNIC packet processing pipelines using Hardware Description Language (HDL). The developed system will provide critical visibility into high-speed packet processing operations and monitoring logic.

• Developing trace collection mechanisms compatible with 100 Gbps line rates
• Engineering efficient solutions for capturing, moving, and storing large volumes of trace data
• Implementing strategies to avoid performance degradation during trace collection
• Applying suitable postprocessing and generating visualizations of key information

Prerequisites

In memory hierarchy, multi-levels caches are used to cache datas in order to avoid the long access latency when accessing to the DRAM. However, when cache misses happen, the long memory access latency will still stall the program execution. To further improve the performance, prefetching techniques are widely used in our modern processors. A prefetcher predict and fetch the data to cache/buffer before it is actually accessed, thereby hiding memory access latency.

Our prefetcher reacts to cache load misses by prefetching large memory regions. While simple, this can severly burden the DRAM bandwidth and flood the buffer, especially when many of those prefetched regions are not actually needed.

Applications exhibit varied memory access patterns. Some memory regions show some characteristics that they are better candidates for prefetching. By profiling an program in advance, it is possible to determine which memory region should be prefetched and which memory region should be evicted earlier. 

In this internship, the student will help to implement the prefetching priority and eviction policy in our existing SystemC model. And by using the profiling result in the policy, we expect to get a performance improvement compared to the original model.

Prerequisites