Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance Ranking
This work proposes an autotuning framework that designs a machine learning-based ensemble LLVM Intermediate Representation ranker, Neural Configuration Scorer (NCS), which ranks the performance of IRs sampled by a transfer-learning-based autotuner, improving the efficiency of the tuning process by reducing tuning overh...
Md Arafat Hossain, Thomas Randall, Akashnil Dutta et al.
· 0 citations