Resources
Conferences
ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP)
IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM)
International Conference on Computer-Aided Design (ICCAD)
International Conference on Field-Programmable Logic and Applications (FPL)
Graph Neural Networks
"A Gentle Introduction to Graph Neural Networks"
CS224W: Machine Learning with Graphs (Stanford)
"E(n) Equivariant Graph Neural Networks"
"EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction"
"Equivariant Graph Neural Networks for 3D Macromolecular Structure"
ESE 514: Graph Neural Networks (UPenn)
"ETA Prediction with Graph Neural Networks in Google Maps"
"Forecasting Global Weather with Graph Neural Networks"
GNNs Recipe
"Message passing all the way up"
"Parameter Prediction for Unseen Deep Architectures"
"Understanding Convolutions on Graphs"
"Universal Invariant and Equivariant Graph Neural Networks"
Hardware Accelerators
"GenGNN: A Generic FPGA Framework for Graph Neural Network Acceleration"
"Survey on Graph Neural Network Acceleration: An Algorithmic Perspective"
High-Level Synthesis
"An Empirical Study of the Reliability of High-Level Synthesis Tools"
"Parallel Programming for FPGAs"
"Synthesizable Higher-Order Functions for C++"
Vitis HLS Comprehensive Documentation
Linux / Unix
Machine Learning
CS 221 ― Artificial Intelligence (Stanford)
CS 229 ― Machine Learning (Stanford)
CS 230 ― Deep Learning (Stanford)
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
"Geometric deep learning on molecular representations"
"MetaFormer is Actually What You Need for Vision"
"MLP-Mixer: An all-MLP Architecture for Vision"
"NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis"
"Patches Are All You Need?"
"SIREN: Implicit Neural Representations with Periodic Activation Functions"
"Supercharged high-resolution ocean simulation with JAX"
"Using JAX to accelerate our research"