.png){kind=icon}
返回
TaiChi: A Hybrid Compression Format for Binary Sparse Matrix-Vector Multiplication on GPU
.png){kind=icon}
PRE
AI
DOI：10.1109/TPDS.2022.3170501.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Binary Sparse Matrix-Vector Multiplication (SpMV) is a heavy computational kernel in weblink analysis, integer factorization, compressed sensing, spectral graph theory, and other domains. Testing several popular GPU-based SpMV implementations on 400 sparse matrices, we observed that data transfer to GPU memory accounts for a large part of the total computation time. The transfer of constant value 1s can be easily eliminated for binary sparse matrices. However, compressing index arrays has always been a great challenge. This article proposes a new compression format TaiChi to further reduce index data copies and improve the performance of SpMV, especially for diagonally dominant binary sparse matrices. Input matrices are first partitioned into relatively dense and ultra-sparse areas. Then the dense areas are encoded inversely by marking 0s, while the ultra-sparse area is encoded by marking 1s. We also designed a new SpMV algorithm only using addition and subtraction for binary matrices based on our partition and encoding format. Evaluation results on real-world binary sparse matrices show that our hybrid encoding for binary matrix significantly reduces the data transfer and speeds up the kernel execution. It achieves the highest transfer and kernel execution speedups of 5.63x and 3.84x on GTX 1080 Ti, 3.39x and 3.91x on Tesla V100.
Keyword:
Sparse matrices
Kernel
Graphics processing units
Indexes
Arrays
Encoding
Partitioning algorithms
Binary sparse matrix
SpMV
GPU
parallel computing
mathematical morphology
期刊
IF:
6
论文数:
5.2K
被引数:
1.1W
机构
引用论文
Active commute to school: does distance from school or walkability of the home neighbourhood matter? A national cross-sectional study of children aged 10–11 years, Scotland, UK.png)
BMJ Open
OAAI
BMJ OpenIF0
OAAI分享收藏分享收藏Performance Optimization Using Partitioned SpMV on GPUs and Multicore CPUs在gpu和多核cpu上使用分区SpMV进行性能优化
PREAI
分享收藏分享收藏分享收藏
查看更多内容