Agenda

Porting Codes to the NextSilicon Maverick-2 Dataflow Architecture: Early Experience, Best Practice and Performance
Chekuri Choudary, Steffen Christgau, Daniel Gecasek, Ronaldo Rodrigues Pela, Kevin Olson, Mathias Pütz, Florian Schintke, Lewin Stein, and Thomas Steinke

Wafer Scale Acceleration of Unstructured Finite Element Methods
Emma Urquhart

To SIMD Or Not To SIMD: Comparing RVV vs. CGRA SoCs For Non-Linear Functions In AI
Sameer Deshmukh, Naoya Mizuki, and Takumi Honda

A Highly Optimized Double-Word Arithmetic Implementation using Versal DSPs
David Volz, Torben Kalkhof, Tim Noack, and Andreas Koch

Morning Break

Energy-Efficient Streaming FPGA Accelerator for DeepSeek Sparse Attention Decode
Jiakang Fan, Rakshith Jayanth, and Viktor Prasanna

SOO, MOO, and FOO: Transformer-Layer Execution on Ryzen AI NPUs
Curt John Bansil, Kaustubh Manohar Mhatre, Aviral Shrivastava, and Aman Arora

Rapid Dataflow Buffer Sizing for DNNs via Parallel RTL Control-Flow Simulation for FINN
Linus Jungemann, Bjarne Wintermann, Heinrich Riebler, Felix Jentzsch, Christoph Berganski, and Christian Plessl

High Speed Network Processing for Scientific Computing in the Open Cloud Testbed
Miriam Leeser, Michael Zink, Suranga Handagala, Carlos Ruben Dell’Aquila, Verena Martinez Outschoorn, and Rafael Coelho Lopes de Sa

Profiling and Optimization Opportunities for SmartNIC-Assisted MoE Inference
Shining Yang and Martin Herbordt

GarageWork: A Shared Testbench Abstraction for Software Simulation and FPGA Testing
Kazutomo Yoshii

BASE: A Reusable Streaming Preprocessing Accelerator for Heterogeneous FPGA Systems
Rye Stahle-Smith, Carter Antley, Jason Bakos, and Rasha Karakchi

Machine Learning for a Gamma-Ray Telescope Using Stream-HLS
Jackie Wu, Ye Htet, Marion Sudvarg, Jeremy D. Buhler, and Roger D. Chamberlain