Yufan Xu, Saurabh Raje, Atanas Rountev, Gerald Sabin, Aravind Sukumaran-Rajam, P. Sadayappan. Training of deep learning pipelines on memory-constrained GPUs via segmented fused-tiled execution. In Bernhard Egger, Aaron Smith, editors, CC '22: 31st ACM SIGPLAN International Conference on Compiler Construction, Seoul, South Korea, April 2 - 3, 2022. pages 104-116, ACM, 2022. [doi]
Abstract is missing.