dragonpilot/selfdrive/modeld/SConscript

Import('env', 'envCython', 'arch', 'cereal', 'messaging', 'common', 'gpucommon', 'visionipc', 'transformations')
lenv = env.Clone()
lenvCython = envCython.Clone()

libs = [cereal, messaging, visionipc, gpucommon, common, 'capnp', 'zmq', 'kj', 'pthread']
frameworks = []

common_src = [
  "models/commonmodel.cc",
  "transforms/loadyuv.cc",
  "transforms/transform.cc",
]

thneed_src_common = [
  "thneed/thneed_common.cc",
  "thneed/serialize.cc",
]

thneed_src_qcom = thneed_src_common + ["thneed/thneed_qcom2.cc"]
thneed_src_pc = thneed_src_common + ["thneed/thneed_pc.cc"]
thneed_src = thneed_src_qcom if arch == "larch64" else thneed_src_pc

# SNPE except on Mac and ARM Linux
snpe_lib = []
if arch != "Darwin" and arch != "aarch64":
  common_src += ['runners/snpemodel.cc']
  snpe_lib += ['SNPE']

# OpenCL is a framework on Mac
if arch == "Darwin":
  frameworks += ['OpenCL']
else:
  libs += ['OpenCL']

# Use onnx on PC
if arch != "larch64" and not GetOption('snpe'):
  common_src += ['runners/onnxmodel.cc']
  lenv['CFLAGS'].append("-DUSE_ONNX_MODEL")
  lenv['CXXFLAGS'].append("-DUSE_ONNX_MODEL")

# Set path definitions
for pathdef, fn in {'TRANSFORM': 'transforms/transform.cl', 'LOADYUV': 'transforms/loadyuv.cl', 'ONNXRUNNER': 'runners/onnx_runner.py'}.items():
  for xenv in (lenv, lenvCython):
    xenv['CXXFLAGS'].append(f'-D{pathdef}_PATH=\\"{File(fn).abspath}\\"')

# Compile cython
snpe_rpath_qcom = "/data/pythonpath/third_party/snpe/larch64"
snpe_rpath_pc = f"{Dir('#').abspath}/third_party/snpe/x86_64-linux-clang"
snpe_rpath = lenvCython['RPATH'] + [snpe_rpath_qcom if arch == "larch64" else snpe_rpath_pc]

cython_libs = envCython["LIBS"] + libs
onnxmodel_lib = lenv.Library('onnxmodel', ['runners/onnxmodel.cc'])
snpemodel_lib = lenv.Library('snpemodel', ['runners/snpemodel.cc'])
commonmodel_lib = lenv.Library('commonmodel', common_src)
driving_lib = lenv.Library('driving', ['models/driving.cc'])

lenvCython.Program('runners/runmodel_pyx.so', 'runners/runmodel_pyx.pyx', LIBS=cython_libs, FRAMEWORKS=frameworks)
lenvCython.Program('runners/onnxmodel_pyx.so', 'runners/onnxmodel_pyx.pyx', LIBS=[onnxmodel_lib, *cython_libs], FRAMEWORKS=frameworks)
lenvCython.Program('runners/snpemodel_pyx.so', 'runners/snpemodel_pyx.pyx', LIBS=[snpemodel_lib, snpe_lib, *cython_libs], FRAMEWORKS=frameworks, RPATH=snpe_rpath)
lenvCython.Program('models/commonmodel_pyx.so', 'models/commonmodel_pyx.pyx', LIBS=[commonmodel_lib, *cython_libs], FRAMEWORKS=frameworks)
lenvCython.Program('models/driving_pyx.so', 'models/driving_pyx.pyx', LIBS=[driving_lib, commonmodel_lib, *cython_libs], FRAMEWORKS=frameworks)

# Compile binaries
lenv['FRAMEWORKS'] = frameworks
common_model = lenv.Object(common_src)

lenv.Program('_dmonitoringmodeld', [
    "dmonitoringmodeld.cc",
    "models/dmonitoring.cc",
  ]+common_model, LIBS=libs + snpe_lib)

# Build thneed model
if arch == "larch64" or GetOption('pc_thneed'):
  fn = File("models/supercombo").abspath

  tinygrad_opts = ["NATIVE_EXPLOG=1", "VALIDHACKS=1", "OPTLOCAL=1", "IMAGE=2", "GPU=1", "ENABLE_METHOD_CACHE=1"]
  if not GetOption('pc_thneed'):
    # use FLOAT16 on device for speed + don't cache the CL kernels for space
    tinygrad_opts += ["FLOAT16=1", "PYOPENCL_NO_CACHE=1"]
  cmd = f"cd {Dir('#').abspath}/tinygrad_repo && " + ' '.join(tinygrad_opts) + f" python3 openpilot/compile.py {fn}.onnx {fn}.thneed"

  tinygrad_files = sum([lenv.Glob("#"+x) for x in open(File("#release/files_common").abspath).read().split("\n") if x.startswith("tinygrad_repo/")], [])
  lenv.Command(fn + ".thneed", [fn + ".onnx"] + tinygrad_files, cmd)

  thneed_lib = env.SharedLibrary('thneed', thneed_src, LIBS=[gpucommon, common, 'zmq', 'OpenCL', 'dl'])
  thneedmodel_lib = env.Library('thneedmodel', ['runners/thneedmodel.cc'])
  lenvCython.Program('runners/thneedmodel_pyx.so', 'runners/thneedmodel_pyx.pyx', LIBS=envCython["LIBS"]+[thneedmodel_lib, thneed_lib, gpucommon, common, 'dl', 'zmq', 'OpenCL'])