The search functionality is under construction.
The search functionality is under construction.

Adaptive Lossy Data Compression Extended Architecture for Memory Bandwidth Conservation in SpMV

Siyi HU, Makiko ITO, Takahide YOSHIKAWA, Yuan HE, Hiroshi NAKAMURA, Masaaki KONDO

  • Full Text Views

    0

  • Cite this

Summary :

Widely adopted by machine learning and graph processing applications nowadays, sparse matrix-Vector multiplication (SpMV) is a very popular algorithm in linear algebra. This is especially the case for fully-connected MLP layers, which dominate many SpMV computations and play a substantial role in diverse services. As a consequence, a large fraction of data center cycles is spent on SpMV kernels. Meanwhile, despite having efficient storage options against sparsity (such as CSR or CSC), SpMV kernels still suffer from the problem of limited memory bandwidth during data transferring because of the memory hierarchy of modern computing systems. In more detail, we find that both integer and floating-point data used in SpMV kernels are handled plainly without any necessary pre-processing. Therefore, we believe bandwidth conservation techniques, such as data compression, may dramatically help SpMV kernels when data is transferred between the main memory and the Last Level Cache (LLC). Furthermore, we also observe that convergence conditions in some typical scientific computation benchmarks (based on SpMV kernels) will not be degraded when adopting lower precision floating-point data. Based on these findings, in this work, we propose a simple yet effective data compression scheme that can be extended to general purpose computing architectures or HPC systems preferably. When it is adopted, a best-case speedup of 1.92x is made. Besides, evaluations with both the CG kernel and the PageRank algorithm indicate that our proposal introduces negligible overhead on both the convergence speed and the accuracy of final results.

Publication
IEICE TRANSACTIONS on Information Vol.E106-D No.12 pp.2015-2025
Publication Date
2023/12/01
Publicized
2023/07/20
Online ISSN
1745-1361
DOI
10.1587/transinf.2023PAP0008
Type of Manuscript
Special Section PAPER (Special Section on Forefront Computing)
Category

Authors

Siyi HU
  University of Tokyo
Makiko ITO
  Fujitsu Ltd.
Takahide YOSHIKAWA
  Fujitsu Ltd.
Yuan HE
  Keio University
Hiroshi NAKAMURA
  University of Tokyo
Masaaki KONDO
  Keio University,RIKEN

Keyword