Publications

TaiChi: A Hybrid Compression Format for Binary Sparse Matrix-Vector Multiplication on GPU

Published in IEEE Transactions on Parallel and Distributed Systems, 2022

This paper proposes a new compression format for binary sparse matrix.

Recommended citation: Jianhua Gao, Weixing Ji, Zhaonian Tan, Yizhuo Wang, Feng Shi. (2022). "TaiChi: A Hybrid Compression Format for Binary Sparse Matrix-Vector Multiplication on GPU." IEEE Transactions on Parallel and Distributed Systems. 33(12):3732-3745. https://ieeexplore.ieee.org/document/9763312

Towards Optimal Fast Matrix Multiplication on CPU-GPU Platforms

Published in International Conference on Parallel and Distributed Computing: Applications and Technologies (PDCAT), 2021

This paper proposes a CPU-GPU heterogenous implementation for the Winograd algorithm.

Recommended citation: Senhao Shao, Yizhuo Wang, Weixing Ji, Jianhua Gao. (2022). "Towards Optimal Fast Matrix Multiplication on CPU-GPU Platforms." International Conference on Parallel and Distributed Computing: Applications and Technologies (PDCAT). 223–236. https://link.springer.com/chapter/10.1007/978-3-030-96772-7_21

AMF-CSR: Adaptive Multi-Row Folding of CSR for SpMV on GPU

Published in 2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS), 2021

This paper proposes a new GPU-based SpMV algorithm AMF-CSR.

Recommended citation: Jianhua Gao, Weixing Ji, Senhao Shao, Yizhuo Wang, Feng Shi. (2021). "AMF-CSR: Adaptive Multi-Row Folding of CSR for SpMV on GPU." 2021 IEEE 27th International Conference on Parallel and Distributed Systems. 418-425. https://ieeexplore.ieee.org/document/9763779