Computer architecture traditionally focuses on general-purpose processors (CPUs) designed to handle a wide range of tasks. However, the increasing demands of specific applications, like machine learning or network processing, have led to the development of so-called domain-specific architectures (DSAs). DSAs are tailored to excel in a particular domain, often achieving significant performance and energy efficiency gains compared to general-purpose CPUs.

One technique to improve performance or energy efficiency (or both!) is offloading computationally intensive tasks from the CPU to specialized hardware accelerators. Field-Programmable Gate Arrays (FPGAs) offer a flexible platform for implementing these accelerators, allowing for customization and optimization of the hardware to match the specific algorithms and data structures of the target application. This combination of CPUs and FPGA-based acceleration enables systems to tackle complex workloads more efficiently.

Open source has revolutionized software development, enabling free use and modification. To minimize costs, risks and ensure compliance in modern automotive, industrial, medical, or telecommunications systems, software reuse is essential. Leveraging existing code, whether open source or internal, reduces development time, bugs, and simplifies meeting legal and security standards.

Endric has been working on the intersection of those three topics: Domain-Specific Architectures where - mostly open source - software shall be accelerated via the use of FPGAs. Hence, computations move from Software to Silicon!

Research projects focus on data highways for banks, factories and vehicles which can transport massive amounts of data reliably, safely, securely, and in a timely fashion:

• Reliability means to protect against data loss to guarantee proper delivery of data, for example by enhancing existing transport protocols such as TCP/IP, or by researching alternatives.
• Safety means Functional Safety as in ISO 61508 to protect humans from technical malfunctions, for example by redundancies and watchdogs.
• Security means all data, in motion or at rest, shall be kept private and protected against leakage and tampering, for example, via on-the-fly encryption using post quantum cryptography.
• Timely means guaranteed worst-case delivery times which are crucial to implement distributed, real-time systems, for example by advancing work on Deterministic Networking, Time-Sensitive Networking and High-Precision, High-Accuracy Time Synchronization. Timely also means improving the Bandwidth-Delay Product and reducing tail-end latencies during transport.

Optimizing High-Speed Transport Protocols - using DSAs to reduce transport latency, from milli-seconds down to 100s of nanoseconds. For better applicability, we investigate hybrid solutions where the Linux NAPI collaborates with FPGA NICs (for in-network processing) and modern concepts of FPGA full acceleration.

Connectivity for high data rate camera, Lidar, Radar systems to implement massive MIMO sensor systems using de-facto standards like PCIe, MIPI CSI-2, Multi-Gigabit Ethernet.

Hardware-accelerated network virtualization by tunneling one packet-based protocol over another packet-based protocol. This facilitates the convergence of IT and OT networks.