Source Code For ShaderNet New App Efficiency

Sample shader graphs

• The sample graphs of disassembly shaders can be found here [sample graph edgelist] [sample graph nodelist]

Scripts explanation

All the scripts are written in python 3.8. To run the script, please lunch a python tools like Anaconda or directly run "python xx.py"

1. Frequent subgraph result analysis
   Frequent subgraph mining utilized the library of gSpan in the link listed in useful link.
   An example to convert gSpan output text to edgelist and nodelist: [code]

   The input to this script is the gspan output file, the outputs are the subgraphs represented by edgelist and nodelist in separate folders.



2. Classify frequent sub-structures into high/low efficiency [code]

RandomForest algorithm is applied.

Input dataset: row is each shader subgraph, columns are the occurance of hardwares within the subgraphs

Useful Link

1. gSpan algorithm [code]