Di Mu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Architecture×1
Frequent co-authors
Research Timeline
2026
ComFuse: Fusing Complex Memory-Intensive Subgraphs with Compute-Intensive Kernels For Modern GPU Architectures
This paper presents ComFuse, an automated GPU compilation system that optimizes heterogeneous deep learning computation graphs by fusing compute-intensive and memory-intensive operators.
Highlighted terms show continued research focus across papers
Papers
cs.AREmpiricalRecentAug 4, 2026
ComFuse: Fusing Complex Memory-Intensive Subgraphs with Compute-Intensive Kernels For Modern GPU Architectures
Di Mu, Tengyuan Jin, Zhenkun Wang, Jialin Yang +5 more
This paper presents ComFuse, an automated GPU compilation system that optimizes heterogeneous deep learning computation graphs by fusing compute-intensive and memory-intensive operators.
View →