75 lines
3.1 KiB
Python
75 lines
3.1 KiB
Python
|
import glob
|
||
|
|
|
||
|
|
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']
|
||
|
|
|
||
|
|
# Set path definitions
|
||
|
|
for pathdef, fn in {'TRANSFORM': 'transforms/transform.cl', 'LOADYUV': 'transforms/loadyuv.cl'}.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
|
||
|
|
snpemodel_lib = lenv.Library('snpemodel', ['runners/snpemodel.cc'])
|
||
|
|
commonmodel_lib = lenv.Library('commonmodel', common_src)
|
||
|
|
|
||
|
|
lenvCython.Program('runners/runmodel_pyx.so', 'runners/runmodel_pyx.pyx', LIBS=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)
|
||
|
|
|
||
|
|
tinygrad_files = ["#"+x for x in glob.glob(env.Dir("#tinygrad_repo").relpath + "/**", recursive=True, root_dir=env.Dir("#").abspath)]
|
||
|
|
|
||
|
|
# Get model metadata
|
||
|
|
fn = File("models/supercombo").abspath
|
||
|
|
cmd = f'python3 {Dir("#selfdrive/modeld").abspath}/get_model_metadata.py {fn}.onnx'
|
||
|
|
lenv.Command(fn + "_metadata.pkl", [fn + ".onnx"] + tinygrad_files, cmd)
|
||
|
|
|
||
|
|
# Build thneed model
|
||
|
|
if arch == "larch64" or GetOption('pc_thneed'):
|
||
|
|
tinygrad_opts = []
|
||
|
|
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/compile2.py {fn}.onnx {fn}.thneed"
|
||
|
|
|
||
|
|
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'])
|