Talks and Presentations

Starware Design regularly shares insights on embedded systems, FPGA, edge AI, and electronics at leading industry conferences.

This page collects recordings, slides and summaries of the most recent talks.

 

July 2026 - FPGA conference Europe

PCIe in Embedded FPGA Companion Chips: Implementation, Performance, and Verification

PCIe has become the de facto high-speed interface for server-grade FPGA accelerator boards, such as
Xilinx Alveo cards, enabling seamless integration with host systems for demanding computational
tasks. However, its versatility, high bandwidth, and relatively straightforward FPGA implementation
make it equally compelling for embedded applications, where FPGAs serve as companion chips to
SoCs.
This talk explores the untapped potential of PCIe in embedded FPGA designs, bridging the gap
between server accelerators and compact companion chips. In the first half, we will delve into key
Intellectual Property (IP) cores for PCIe integration, including their interfaces and configuration
options. We will compare performance metrics such as bandwidth and latency against integrated SoC
FPGAs. Additionally, we will examine the implications for device drivers.
The second half shifts focus to advanced verification strategies tailored for PCIe-connected FPGA
companion chips. We will cover practical techniques using open-source tools like Cocotb for
hardware verification in Python, alongside co-simulation with QEMU to model full-system behaviour.

https://www.fpga-conference.eu/

May 2026 - Embedded Online Conference

Bluetooth Low Energy Audio Deep Dive: Architecture, Protocols, Codecs, and Live Demo

Bluetooth LE Audio brings powerful new capabilities to wireless audio, with new protocols, modern codecs, and entirely new use cases that go far beyond classic Bluetooth audio.

Here are just a few real-world examples:

Multi-stream audio
Picture yourself at the airport, listening to a podcast through your earbuds. At the same time, you’ve subscribed to your gate’s public announcement stream. When boarding announcements begin, your podcast automatically ducks or pauses—just enough for you to hear the gate agent clearly, then seamlessly resumes.

Public audio broadcasts
In a museum, simply open your phone, choose your language, and connect to the exhibit’s audio guide—using your own headphones, no rental device needed.
At the gym, tap to receive audio from any TV screen, even if you’re on the other side of the room.
In train stations, airports, theaters anyone can join location-based audio streams.
This talk provides an introduction to BLE LE audio: from the new features and protocols to the challenges in integrating it in a real scenario with a demo between a devkit and an headset.

https://embeddedonlineconference.com/session/bluetooth-low-energy-audio-deep-dive-architecture-protocols-codecs-and-live-demo

March 2026 – Embedded World (Germany)

Lessons Learned Designing an Edge AI ASIC for Audio Applications

Designing an edge AI ASIC for applications like keyword spotting presents unique challenges, with lessons applicable to processing audio, video, or sensor data. This presentation shares insights from developing an audio AI ASIC, covering critical design considerations and practical solutions.
We begin with the ASIC architecture, followed by the challenge of data scarcity: leveraging limited public datasets, effective data collection strategies, and ensuring data quality. Next, we explore selecting and evaluating optimal AI networks by balancing memory size and number of operations vs performance, and robustness to input noise, signal amplitude, and DC offset.
Verification and validation strategies are discussed across multiple levels: IP-level testing using Cocotb, ASIC-level prototyping on FPGA, and system-level validation in a test environment inspired by Amazon Alexa qualification testing. We emphasize the value of rapid feedback through continuous integration and early customer engagement to refine designs. Finally, we highlight the role of a robust software development kit (SDK) in enabling seamless system integration for edge AI solutions.
This talk provides actionable insights for engineers tackling the complexities of edge AI ASIC design, fostering efficient and scalable solutions.

https://tinyurl.com/starwaredesign-ew26

Ready to transform your embedded systems