Transferable Graph Optimizers for ML Compilers

yanqiz Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Wong, Peter Ma, Qiumin Xu, Hanxiao Liu, Phitchaya Phothilimtha, Shen Wang, Anna Goldie, Azalia Mirhoseini, James Laudon

Oral presentation: Orals & Spotlights Track 33: Health/AutoML/(Soft|Hard)ware
on 2020-12-10T18:30:00-08:00 - 2020-12-10T18:45:00-08:00
Poster Session 7 (more posters)
on 2020-12-10T21:00:00-08:00 - 2020-12-10T23:00:00-08:00
GatherTown: AutoML ( Town C0 - Spot B2 )
Join GatherTown
Only iff poster is crowded, join Zoom . Authors have to start the Zoom call from their Profile page / Presentation History.
Abstract: Most compilers for machine learning (ML) frameworks need to solve many correlated optimization problems to generate efficient machine code. Current ML compilers rely on heuristics based algorithms to solve these optimization problems one at a time. However, this approach is not only hard to maintain but often leads to sub-optimal solutions especially for newer model architectures. Existing learning based approaches in the literature are sample inefficient, tackle a single optimization problem, and do not generalize to unseen graphs making them infeasible to be deployed in practice. To address these limitations, we propose an end-to-end, transferable deep reinforcement learning method for computational graph optimization (GO), based on a scalable sequential attention mechanism over an inductive graph neural network. GO generates decisions on the entire graph rather than on each individual node autoregressively, drastically speeding up the search compared to prior methods. Moreover, we propose recurrent attention layers to jointly optimize dependent graph optimization tasks and demonstrate 33%-60% speedup on three graph optimization tasks compared to TensorFlow default optimization. On a diverse set of representative graphs consisting of up to 80,000 nodes, including Inception-v3, Transformer-XL, and WaveNet, GO achieves on average 21% improvement over human experts and 18% improvement over the prior state of the art with 15x faster convergence, on a device placement task evaluated in real systems.

Preview Video and Chat

Chat is not available.