Skip to content (access key 's')
Logo of Technion
Logo of CS Department


ceClub: Deep Reinforcement Learning in Compiler
event speaker icon
Ameer Haj Ali (UC Berkeley)
event date icon
Wednesday, 8.1.2020, 15:30
event location icon
Electrical Eng. Building 815
Compilers are designed today to use fixedAbstract -cost models that are based on heuristics to make different code optimizations. However, these models are unable to capture the data dependency, the computation graph, or the organization of instructions. Therefore, with these models compilers achieve suboptimal performance. In his talk, Ameer will show how to use deep reinforcement learning to overcome such hard compiler challenges. This includes the NP-Hard compiler phase ordering challenge (AutoPhase, FCCM2019, SysML2020) and automatically tuning compiler pragmas such as vectorization (NeuroVectorizer, CGO2020).
[Back to the index of events]