26038

TCUDB: Accelerating Database with Tensor Processors

Yu-Ching Hu, Yuliang Li, Hung-Wei Tseng
University of California, Riverside
arXiv:2112.07552 [cs.DB], (14 Dec 2021)

@misc{hu2021tcudb,

   title={TCUDB: Accelerating Database with Tensor Processors},

   author={Yu-Ching Hu and Yuliang Li and Hung-Wei Tseng},

   year={2021},

   eprint={2112.07552},

   archivePrefix={arXiv},

   primaryClass={cs.DB}

}

Download Download (PDF)   View View   Source Source   

337

views

The emergence of novel hardware accelerators has powered the tremendous growth of machine learning in recent years. These accelerators deliver incomparable performance gains in processing high-volume matrix operators, particularly matrix multiplication, a core component of neural network training and inference. In this work, we explored opportunities of accelerating database systems using NVIDIA’s Tensor Core Units (TCUs). We present TCUDB, a TCU-accelerated query engine processing a set of query operators including natural joins and group-by aggregates as matrix operators within TCUs. Matrix multiplication was considered inefficient in the past; however, this strategy has remained largely unexplored in conventional GPU-based databases, which primarily rely on vector or scalar processing. We demonstrate the significant performance gain of TCUDB in a range of real-world applications including entity matching, graph query processing, and matrix-based data analytics. TCUDB achieves up to 288x speedup compared to a baseline GPU-based query engine.
No votes yet.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: