Matrix 'poisson1d' for "CPU- and GPU-initiated Communication Strategies for Conjugate Gradient Methods on Large GPU Clusters"

This dataset contains a large, tridiagonal matrix, which is used for large-scale experiments in the paper: “CPU- and GPU-initiated Communication Strategies for Conjugate Gradient Methods on Large GPU Clusters” The matrix is stored in a binary format (based on the Matrix Market ASCII format), which can be loaded and used by the aCG benchmark (https://github.com/ParCoreLab/aCG/) for testing various iterative linear solver implementations.