graph-processing

Input-aware CUDA auto-scheduler for CSR SpMM, SDDMM, and sparse attention in graph neural networks.

Exploring computational scaling of spiking neural network simulations across hardware architectures

Official CUDA implementation of "Streaming Right Multiplication over Grammar-Compressed Matrices: A Memory-Bounded GPU Engine for Genotype and Graph Data" (ALENEX 2027). Enables memory-bounded matrix-vector products and graph algorithms on massive dataset via grammar compression.

CUDA/PyTorch operator for fused neighborhood sampling and mean aggregation, with reproducible KSEM 2026 experiments.

A Python wrapper over the GraphGen system