CLgen is an open source application for generating runnable programs using deep learning. CLgen learns to program using neural networks which model the semantics and usage from large volumes of program fragments, generating many-core OpenCL programs that are representative of, but distinct from, the programs it learns from.
After following the install instructions for this project, I'd recommend running the test suite to ensure that everything is set up correctly:
$ bazel test //deeplearning/clgen/...Use our tiny example dataset to train and sample your first CLgen model:
$ bazel run //deeplearning/clgen -- \
--config $PWD/deeplearning/clgen/tests/data/tiny/config.pbtxt
Presentation slides:
Publication "Synthesizing Benchmarks for Predictive Modeling" (CGO'17).
Jupyter notebook containing experimental evaluation of an early version of CLgen.
Copyright 2016, 2017, 2018 Chris Cummins [email protected].
Released under the terms of the GPLv3 license. See LICENSE for details.