/ml-in-compilers

ML in compilers, Hot Topics.

Primary LanguageTeXGNU General Public License v3.0GPL-3.0

πŸŽ–οΈ

ML in compilers, Hot Topics.

πŸ“š Contents [General]:

  • (πŸ“˜, 2006, MIT PhD thesis) Stephenson: "Automating the Construction of Compiler Heuristics Using Machine Learning" - a doctoral dissertation in 2006 describing the basic techniques used at that time.

  • (πŸ“œ, 2018, CoRR journal) Wang and O'Boyle: "Machine Learning in Compiler Optimization" - a great ml survey

  • (πŸ“œ, 2009, Chapter from Languages and Compilers for Parallel Computing) Thomson, O'Boyle, Fursin and Franke: "Reducing Training Time in a One-shot Machine Learning-based Compiler" - boost ml in iterative compilation

  • (πŸ“œ, 2014, Proceedings of the 23rd International Conference on Parallel Architectures and Compilation) Magni, Dybach and O'Boyle: "Automatic Optimization of Thread-Coarsening for Graphics Processors" - the usage of PCA for the purpose of dimensionality reduction

  • (πŸ“œ, 2005, Proc. Int. Symp. Code Generat. Optim. CGO) M. Stephenson and S. Amarasinghe, β€œPredicting unroll factors using supervised classification" - feature selection mechanism from '05 MIT

  • (πŸ“œ, 2013, Proc. Int. Symp. Code Generat. Optim. CGO) S. Kulkarni, J. Cavazos, C. Wimmer and D. Simon, "Automatic Construction of Inlining Heuristics using Machine Learning" - combine NEAT and Decision Tree

  • (πŸ“œ, 2020, Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI) M. Allamanis, E. T. Barr, S. Ducousso and Z. Gao, "Typilus: Neural Type Hints" - graph neural network that predict types based on a program structure

🎯 Contents [Attributes extraction]:

  • (πŸ“œ, 2018, ACM Computing Surveys), A. Ashouri, W. Killian, J. Cavazos, G. Palermo, C. Silvano, "A Survey on Compiler Autotuning using Machine Learning" - detailer survey

  • (πŸ“œ, 2012, International Symposium on Code Generation and Optimization, CGO), E. Park, J. Cavazos, M. Alvarez, "Using Graph-Based Program Characterization for Predictive Modeling"

  • (πŸ“œ, 2010, International Symposium on Code Generation and Optimization, CGO), Y. Jiang, E. Zhang, K. Tian, F. Mao, M. Gethers, X. Shen, Y. Gao, "Exploiting Statistical Correlations for Proactive Prediction of Program Behaviors"

  • (πŸ“œ, 2017, ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems, LCTES), B. Taylor, M. Vicent Sanz, Z. Wang, "Adaptive Optimization for OpenCL Programs on Embedded Heterogeneous Systems"

  • (πŸ“œ, 2009, 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP), Z. Wang, M. F. P. O'Boyle, "Mapping Parallelism to Multi-cores: A Machine Learning Based Approach"

➿ Contents [Graph Neural Networks]:

  • (πŸ“Ί, 2020, YouTube) MSR Cambridge, AI Residency Advanced Lecture Series, "An Introduction to Graph Neural Networks: Models and Applications" - gentle introduction into the Graph Neural Networks - link

  • (πŸ“Ί, 2020, YouTube), Programming Language Design and Implementation Conference (PLDI), MAPL Session Talks - overview of a Graph Neural Network and currently active research topics - link (tutorial begins @56:00)

  • *πŸ“Ί, 2020, YouTube) 21st ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES 2020), Prof. Saman Amarasinghe, MIT "Using Machine Learning to Modernize Compiler Technology" - inspiring talk - link

  • (πŸ“œ, 2005, Proceedings of the International Joint Conference on Neural Networks), M. Gori, G. Monfardini and F. Scarselli "A new model for earning in graph domains" - GNN intro paper

  • (πŸ“œ, 2009, IEEE Transactions on Neural Networks), F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner and G. Monfardini, "The Graph Neural Network Model" - GNN intro paper

  • (πŸ“œ, 2018, CoRR Journal), J. Zhou, G. Cui, Z. Zhang, C. Yang, Z. Liu and M. Sun, "Graph Neural Networks: A Review of Methods and Applications" - Nice review paper

  • (πŸŒ€, 2017 CoRR Journal), A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser and I. Polosukhin, "Attention Is All You Need" - attention mechanism

  • (πŸŒ€, 2020, ICLR), N. Kitaev, L. Kaiser and A. Levskaya, "Reformer: The Efficient Transformer" - transforming mechanisms (Google AI Blog: link)

  • (πŸŒ€, 2017 ICLR), T. Kipf and M. Welling, "Semi-Supervised Classification with Graph Convolutional Networks" - Graph Convolutional Networks (Additional tutorial: link)

  • (πŸŒ€, 2016 NIPS), M. Defferrard, X. Bresson and P. Vandergheynst, "Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering" - Graph Convoutional Networks

  • (πŸŒ€, 2018, arXiv print), P. VeličkoviΔ‡, G. Cucurull, A. Casanova, A. Romero, P. Lio and Y. Bengio, "Graph attention networks" - Great paper that introduce Graph Attention Networks (blog post: link)