2024/04/30 by Nabil Abubaker, Torsten Hoefler, Abubaker, Nabil +1 · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #Distributed #FOS: Computer and information sciences #Face recognition and analysis #Parallel #Video Analysis and Summarization #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.2404.19638
openalex publication_date 2024/04/30 · openalex created_date 2024/05/11 · openalex updated_date 2026/07/28
Existing 3D algorithms for distributed-memory sparse kernels suffer from limited scalability due to reliance on bulk sparsity-agnostic communication. While easier to use, sparsity-agnostic communication leads to unnecessary bandwidth and memory consumption. We present SpComm3D, a framework for enabling sparsity-aware communication and minimal memory footprint such that no unnecessary data is communicated or stored in memory. SpComm3D performs sparse communication efficiently with minimal or no communication buffers to further reduce memory consumption. SpComm3D detaches the local computation at each processor from the communication, allowing flexibility in choosing the best accelerated version for computation. We build 3D algorithms with SpComm3D for the two important sparse ML kernels: Sampled Dense-Dense Matrix Multiplication (SDDMM) and Sparse matrix-matrix multiplication (SpMM). Experimental evaluations on up to 1800 processors demonstrate that SpComm3D has superior scalability and outperforms state-of-the-art sparsity-agnostic methods with up to 20x improvement in terms of communication, memory, and runtime of SDDMM and SpMM. The code is available at: https://github.com/nfabubaker/SpComm3D