{
  description = "cuda kernel compilation with nix";

  nixConfig = {
    extra-substituters = [
      "https://nix-community.cachix.org"
    ];
    extra-trusted-public-keys = [
      "nix-community.cachix.org-1:mB9FSh9qf2dCimDSUo8Zy7bkq5CX+/rkCWyvRCYg3Fs="
    ];
  };

  inputs = {
    nixpkgs.url = "github:nixos/nixpkgs/nixpkgs-unstable";
  };
  outputs = {
    self,
    nixpkgs,
    ...
  }: let
    system = "x86_64-linux";
    pkgs = import nixpkgs {
      inherit system;
      config.allowUnfree = true;
      config.cudaSupport = true;
      config.nvidia.acceptLicense = true;
    };
  in {
    packages."${system}" = {
      # just one main.cu file for now
      # compile it and place it to $out/bin/cuda-kernel
      cuda-kernel = let
        # Use CUDA 12.0 which should be compatible with driver 580.76.05
        cudaPackages = pkgs.cudaPackages;
        cudatoolkit = cudaPackages.cudatoolkit;
      in
        cudaPackages.backendStdenv.mkDerivation {
          name = "cuda";
          src = ./main.cu;
          unpackPhase = "true";
          buildInputs = [
            cudatoolkit
            cudaPackages.cuda_cudart
          ];
          nativeBuildInputs = [
            cudatoolkit
            pkgs.autoAddDriverRunpath
          ];
          LD_LIBRARY_PATH = "${cudatoolkit}/lib:${cudaPackages.cuda_cudart}/lib";
          buildPhase = ''
            echo "GCC Version:"
            gcc --version
            echo "NVCC Version:"
            nvcc --version

            echo "Building CUDA program..."
            nvcc -arch=sm_89 -o main $src
            mkdir -p $out/bin
            cp main $out/bin/
          '';
          meta = {
            mainProgram = "main";
            platforms = ["x86_64-linux"];
          };
        };
      default = self.packages."${system}".cuda-kernel;
    };
  };
}