import os 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', 'kj', 'pthread'] frameworks = [] common_src = [ "models/commonmodel.cc", "transforms/loadyuv.cc", "transforms/transform.cc", ] # OpenCL is a framework on Mac if arch == "Darwin": frameworks += ['OpenCL'] else: libs += ['OpenCL'] # Set path definitions to repository-relative paths so prebuilt artifacts stay relocatable. for pathdef, fn in {'TRANSFORM': 'selfdrive/modeld/transforms/transform.cl', 'LOADYUV': 'selfdrive/modeld/transforms/loadyuv.cl'}.items(): for xenv in (lenv, lenvCython): xenv['CXXFLAGS'].append(f'-D{pathdef}_PATH=\\"{fn}\\"') # Compile cython cython_libs = envCython["LIBS"] + libs commonmodel_lib = lenv.Library('commonmodel', common_src) 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) if 'pycache' not in x] skip_dm_tinygrad_pkl = os.getenv("SP_SKIP_DM_TINYGRAD_PKL", "").lower() in {"1", "true", "yes", "on"} allow_host_tinygrad_pkl = os.getenv("SP_ALLOW_HOST_TINYGRAD_PKL", "").lower() in {"1", "true", "yes", "on"} build_model_tinygrad_pkl = os.getenv("SP_BUILD_MODEL_TINYGRAD_PKL", "").lower() in {"1", "true", "yes", "on"} has_qcom_gpu = os.path.exists('/dev/kgsl-3d0') # Compile camera warp artifacts used by modeld/dmonitoringmodeld on C4. if arch == 'larch64': compile_warp_flags = 'DEV=QCOM FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0' \ if os.path.exists('/dev/kgsl-3d0') else 'DEV=CPU CPU=1 THREADS=0 NOLOCALS=1 DEBUG=0 HOME=/tmp' else: compile_warp_flags = { 'Darwin': f'DEV=CPU THREADS=0 NOLOCALS=1 DEBUG=0 HOME={os.path.expanduser("~")}', }.get(arch, 'DEV=CPU CPU_LLVM=1 THREADS=0 NOLOCALS=1 DEBUG=0') build_warp_artifacts = os.getenv("SP_BUILD_WARP_ARTIFACTS", "").lower() in {"1", "true", "yes", "on"} if build_warp_artifacts: default_warp_resolutions = [(1928, 1208), (1344, 760)] raw_warp_resolutions = os.getenv("SP_WARP_RESOLUTIONS", "").strip() if raw_warp_resolutions: selected_warp_resolutions = [] seen_warp_resolutions = set() for token in raw_warp_resolutions.replace(";", ",").split(","): token = token.strip().lower() if not token: continue w_str, h_str = token.split("x", 1) wh = (int(w_str), int(h_str)) if wh not in seen_warp_resolutions: seen_warp_resolutions.add(wh) selected_warp_resolutions.append(wh) if not selected_warp_resolutions: selected_warp_resolutions = default_warp_resolutions else: selected_warp_resolutions = default_warp_resolutions compile_warp_script = "#selfdrive/modeld/compile_warp.py" warp_targets = [] # Camera resolutions required by modeld compile_warp.py for w, h in selected_warp_resolutions: warp_targets += [File(f"models/warp_{w}x{h}_tinygrad.pkl").abspath, File(f"models/dm_warp_{w}x{h}_tinygrad.pkl").abspath] lenv.Command( warp_targets, tinygrad_files + [compile_warp_script], f'{compile_warp_flags} python3 selfdrive/modeld/compile_warp.py', ) else: print("Skipping model warp precompile (set SP_BUILD_WARP_ARTIFACTS=1 to enable)") # Get model metadata for model_name in ['driving_vision', 'driving_policy', 'dmonitoring_model']: model_rel_path = f"selfdrive/modeld/models/{model_name}" model_node_path = f"#{model_rel_path}" metadata_script = "#selfdrive/modeld/get_model_metadata.py" cmd = f'python3 selfdrive/modeld/get_model_metadata.py {model_rel_path}.onnx' lenv.Command(model_node_path + "_metadata.pkl", [model_node_path + ".onnx"] + tinygrad_files + [metadata_script], cmd) def tg_compile(flags, model_name): tinygrad_root = "tinygrad_repo" compile_script = "#tinygrad_repo/examples/openpilot/compile3.py" pythonpath_string = 'PYTHONPATH="${PYTHONPATH}:' + tinygrad_root + '"' model_rel_path = f"selfdrive/modeld/models/{model_name}" model_node_path = f"#{model_rel_path}" model_input = f"./{model_rel_path}.onnx" return lenv.Command( model_node_path + "_tinygrad.pkl", [model_node_path + ".onnx"] + tinygrad_files + [compile_script], f'{pythonpath_string} {flags} python3 tinygrad_repo/examples/openpilot/compile3.py {model_input} {model_rel_path}_tinygrad.pkl' ) compile_model_tinygrad_pkl = build_model_tinygrad_pkl or allow_host_tinygrad_pkl if not compile_model_tinygrad_pkl: print("Skipping tinygrad model PKL compile (set SP_BUILD_MODEL_TINYGRAD_PKL=1 or SP_ALLOW_HOST_TINYGRAD_PKL=1 to enable)") # Compile small models for model_name in ['driving_vision', 'driving_policy', 'dmonitoring_model']: if model_name == 'dmonitoring_model' and skip_dm_tinygrad_pkl: print("Skipping dmonitoring_model_tinygrad.pkl compile (SP_SKIP_DM_TINYGRAD_PKL enabled)") continue if not compile_model_tinygrad_pkl: continue if arch == 'larch64': # On real devices keep QCOM codegen. flags = 'DEV=QCOM QCOM=1 FLOAT16=1 NOLOCALS=1 IMAGE=2 JIT_BATCH_SIZE=0 DEBUG=0' else: # Opt-in host compile (for debugging only). flags = { 'Darwin': 'DEV=CPU CPU=1 IMAGE=0 NOLOCALS=1 DEBUG=0 HOME=/tmp', }.get(arch, 'DEV=CPU CPU=1 IMAGE=0 NOLOCALS=1 DEBUG=0') tg_compile(flags, model_name) # Compile BIG model if USB GPU is available if "USBGPU" in os.environ: import subprocess # because tg doesn't support multi-process devs = subprocess.check_output('python3 -c "from tinygrad import Device; print(list(Device.get_available_devices()))"', shell=True, cwd=env.Dir('#').abspath) if b"AMD" in devs: print("USB GPU detected... building") flags = "DEV=AMD AMD=1 AMD_IFACE=USB AMD_LLVM=1 NOLOCALS=0 IMAGE=0 DEBUG=0" bp = tg_compile(flags, "big_driving_policy") bv = tg_compile(flags, "big_driving_vision") lenv.SideEffect('lock', [bp, bv]) # tg doesn't support multi-process so build serially else: print("USB GPU not detected... skipping")