FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection
Published in HPCA 2026, 2025
FlashFuser extends kernel fusion to the distributed shared memory domain through inter-core connection on modern GPUs.
Recommended citation: Ziyu Huang, Yangjie Zhou, Zihan Liu, Xinhao Luo, Yijia Diao, Minyi Guo, Jidong Zhai, Yu Feng, Chen Zhang, Anbang Wu, and Jingwen Leng. (2026). "FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection." HPCA 2026.
Download Paper