Performs autotuning on program approximation knobs using an error-predictive proxy in place of the
`predtuner` performs autotuning on program approximation knobs using an error-predictive proxy
original program, to greatly speedup autotuning while getting results comparable in quality.
in place of the original program, to greatly speedup autotuning while getting results
comparable in quality.
Work in progress.
Work in progress.
## Requirements
## Requirements
Prerequisite packages are listed in `./env.yaml`. Conda is the validated and recommended way to set
`pip` is needed for installing this package. At the root directory of this repo, do:
up a working environment. If you're using conda, do
```bash
```bash
conda env create -n predtuner -f env.yaml
pip install-e .
conda activate predtuner
```
```
`-e` can be omitted if you don't intend to modify the code in this package.
## Model Data for Example / Testing
`predtuner` contains 10 demo models which are also used in tests.
- Download and extract [this](https://drive.google.com/file/d/1V_yd9sKcZQ7zhnO5YhRpOsaBPLEEvM9u/view?usp=sharing) file containing all 10 models, for testing purposes.
- The example only uses VGG16-CIFAR10. If you don't need the other models, get the data for VGG16-CIFAR10 [here](https://drive.google.com/file/d/1Z84z-nsv_nbrr8t9i28UoxSJg-Sd_Ddu/view?usp=sharing).
In either case, there should be a `model_params/` folder at the root of repo after extraction.
