This repository contains the artifact for the SC '25 paper submission "KAMI: Communication-Avoiding General Matrix Multiplication within a Single GPU." The NVIDIA GH200 is installed with Ubuntu 22.04 ...

INT32 Data Range Limitation: The original cumm matrix multiplication operation raises an error when encountering int32 data ranges. When the mesh is very large, this ...

Abstract: Graph convolutional networks (GCNs) are emerging neural network models designed to process graph-structured data. Due to massively parallel computations using irregular data structures by ...

Abstract: Sparse matrices have recently played a significant and impactful role in scientific computing, including artificial intelligence-related fields. According to historical studies on sparse ...