ASADI: Accelerating Sparse Attention using Diagonal-based In-situ Computing

Published in HPCA, 2024

Recommended citation: Huize Li, Zhaoying Li, Zhenyu Bai, and Tulika Mitra. (2024). "ASADI: Accelerating Sparse Attention using Diagonal-based In-situ Computing." In Proceedings of the 30th IEEE International Symposium on High-Performance Computer Architecture (HPCA). pp. 774-787.
Download Paper | Download Slides