A Slice and Dice Approach to Accelerate Compound Sparse Attention on GPU

Hailong Li, Jaewan Choi, Jung Ho Ahn. A Slice and Dice Approach to Accelerate Compound Sparse Attention on GPU. In IEEE International Symposium on Workload Characterization, IISWC 2022, Austin, TX, USA, November 6-8, 2022. pages 104-116, IEEE, 2022. [doi]

Authors

Hailong Li

This author has not been identified. Look up 'Hailong Li' in Google

Jaewan Choi

This author has not been identified. Look up 'Jaewan Choi' in Google

Jung Ho Ahn

This author has not been identified. Look up 'Jung Ho Ahn' in Google