WPIA: accelerating DNN warm-up in Web browsers by precompiling WebGL programs

Deyu Tian, Yun Ma, Yudong Han, Qi Yang, Haochen Yang, Gang Huang

Abstract: In this paper, we study the long warm-up time of GPU acceleration of DNN inference in Web browsers. We analyzed the reason behind the long warm-up time through a measurement study and revealed that compiling WebGL programs takes most of the warm-up time. Inspired by this finding, we proposed WPIA, an approach that suggests precompiling WebGL programs on the server side to avoid compiling them in Web browsers. WPIA tackles the challenges of precompiling by merging WebGL programs and using a record-and-replay technique. Evaluation experiment results show that WPIA can accelerate the DNN warm-up time to an order of magnitude.