Skip to content

Latest commit

 

History

History
17 lines (12 loc) · 821 Bytes

README.md

File metadata and controls

17 lines (12 loc) · 821 Bytes

DRACO

Implementation of Digital Oscillator-inspired Ising Machine for solving Combinatroial Optimization Problems (DRACO: Digital and Reliable Accelerator for solving Combinatorial Optimization problems)

Required environment

python with Scipy and Pytorch

This codebase includes the following components:

  1. SystemVerilog-based microarchitectural RTL model of the accelerator (in ./hw/rtl/) and testbench files (in ./hw/tb/).
  2. Python-based Subgraph Updating Scheme (in ./src/)
  3. Maxcut problems for experiments (in ./data/)

Main Reference:

Maxcut Problem downloaded from: http://biqbin.eu/Home/Benchmarks?page=1

  1. https://github.com/vardigroup/GradSAT.git from Rice University for software solvers
  2. https://github.com/nimish15shah/DAG_Processor.git from MICAS, KU Leuven for hardware implementations