版权声明：
除非注明，本博文章均为原创，转载请以链接形式标明本文地址。

Create 2024-06-04

以针对的算法为分类对象，总结目前与性能相关的矩阵特征文献

SpMV

  • (PPoPP’23)Yesil S, Heidarshenas A, Morrison A, et al. WISE: Predicting the performance of sparse matrix vector multiplication with machine learning[C]//Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming. 2023: 329-341.
    • 文章主要创新点：提出了更丰富的矩阵特征，包括结构特征
  • (PPoPP’18)Zhao Y, Li J, Liao C, et al. Bridging the gap between deep learning and sparse matrix format selection[C]//Proceedings of the 23rd ACM SIGPLAN symposium on principles and practice of parallel programming. 2018: 94-108.
    • 提出了除CNN外的一种矩阵结构特征
  • (SC’23)Trotter J D, Ekmekçibaşı S, Langguth J, et al. Bringing Order to Sparsity: A Sparse Matrix Reordering Study on Multicore CPUs[C]//Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 2023: 1-13.
    • 探究了矩阵特征与SpMV性能之间的关系

SpTRSV

  • Ahmad N, Yilmaz B, Unat D. A prediction framework for fast sparse triangular solves[C]//European Conference on Parallel Processing. Cham: Springer International Publishing, 2020: 529-545.

AMG

  • Wang Y, Chang F, Wei B, et al. Optimization of Sparse Matrix Computation for Algebraic Multigrid on GPUs[J]. ACM Transactions on Architecture and Code Optimization, 2024.
    • 提出了一个新的SpGEMM
    • 基于GPU丰富的实现，使用ML选择AMG每层的SpGEMM和SpMV实现