General
Multilevel Graph Partitioning on GPU Supercomputers
arXiv cs.DC0 views
arXiv:2611.24264v1 Announce Type: new Abstract: Graph partitioning is a key enabler in computational science, with applications to sparse linear algebra, load-balanced parallel computation, and graph computations. In recent years, graphics processing units (GPUs) have become the preferred accelerator on the world's top supercomputers. Despite this, most existing distributed graph partitioners do not utilize GPUs. In this work, we develop a new multi-GPU distributed partitioner based on Jet, a prior single-GPU partitioner. We seek to optimize scalability without sacrificing quality. Our partitioner utilizes CUDA-aware MPI, one-sided communication routines, and an overall bulk-synchronous parallel structure. We demonstrate solution quality comparable to Jet. Our experiments show excellent weak scaling up to 256 GPUs, enabling partitioning of instances significantly larger than a single-GPU partitioner can handle.
Source:https://arxiv.org/abs/2611.24264PreviouseFAIR: Fair LLM Serving under Hourly Electricity CommitmentsNextScaleBench: An Extensible and Reproducible Experimental Platform for Kubernetes Autoscaling Research
Related posts
If nobody writes it down, it did not get decided
0dev.to Productivity
Micrograph B-factor estimation via Wilson statistics
0arXiv eess.IV
Greedy Vector Approximation Based on Rotation for Multiplierless Complex Products
0arXiv eess.SP
Toward Massive MIMO HAPS Networks: Antenna Architectures and Design
0arXiv eess.SP
Deep-Learning-Assisted Full Waveform Inversion for Attenuation Reconstruction in Ultrasound Computed Tomography
0arXiv eess.SP
Two is better than one: optimizing binary rating scales for online platforms
0arXiv cs.MA