- evaluate various prediction models for DSE of CPU.
- a hypervolume-improvement-based multi-objective optimization method and a uniformity-aware selection algorithm to select design points. Further, AdaBoost is first introduced to GBRT model to improve the prediction accuracy.
This project uses torch, skopt, math, and several basic python packages. Go check them out if you don't have them locally installed.
This is only a documentation package.
# run main() in main.python
$ python main.pythonMajor running configurations are defined in config.py Performance metric dataset is listed in data_all_simpoint/ . For now, it only includes a demo sample record in 500.1-refrate-1.txt