.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "how_to/work_with_microtvm/micro_autotune.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note Click :ref:`here ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_how_to_work_with_microtvm_micro_autotune.py: .. _tutorial-micro-autotune: Autotuning with microTVM ========================= **Authors**: `Andrew Reusch `_, `Mehrdad Hessar `_ This tutorial explains how to autotune a model using the C runtime. .. GENERATED FROM PYTHON SOURCE LINES 29-41 .. code-block:: default import os import json import numpy as np import pathlib import tvm from tvm.relay.backend import Runtime use_physical_hw = bool(os.getenv("TVM_MICRO_USE_HW")) .. GENERATED FROM PYTHON SOURCE LINES 47-53 Defining the model ################### To begin with, define a model in Relay to be executed on-device. Then create an IRModule from relay model and fill parameters with random numbers. .. GENERATED FROM PYTHON SOURCE LINES 53-78 .. code-block:: default data_shape = (1, 3, 10, 10) weight_shape = (6, 3, 5, 5) data = tvm.relay.var("data", tvm.relay.TensorType(data_shape, "float32")) weight = tvm.relay.var("weight", tvm.relay.TensorType(weight_shape, "float32")) y = tvm.relay.nn.conv2d( data, weight, padding=(2, 2), kernel_size=(5, 5), kernel_layout="OIHW", out_dtype="float32", ) f = tvm.relay.Function([data, weight], y) relay_mod = tvm.IRModule.from_expr(f) relay_mod = tvm.relay.transform.InferType()(relay_mod) weight_sample = np.random.rand( weight_shape[0], weight_shape[1], weight_shape[2], weight_shape[3] ).astype("float32") params = {"weight": weight_sample} .. GENERATED FROM PYTHON SOURCE LINES 79-90 Defining the target ###################### Now we define the TVM target that describes the execution environment. This looks very similar to target definitions from other microTVM tutorials. Alongside this we pick the C Runtime to code generate our model against. When running on physical hardware, choose a target and a board that describe the hardware. There are multiple hardware targets that could be selected from PLATFORM list in this tutorial. You can chose the platform by passing --platform argument when running this tutorial. .. GENERATED FROM PYTHON SOURCE LINES 90-107 .. code-block:: default RUNTIME = Runtime("crt", {"system-lib": True}) TARGET = tvm.target.target.micro("host") # Compiling for physical hardware # -------------------------------------------------------------------------- # When running on physical hardware, choose a TARGET and a BOARD that describe the hardware. The # STM32L4R5ZI Nucleo target and board is chosen in the example below. if use_physical_hw: boards_file = pathlib.Path(tvm.micro.get_microtvm_template_projects("zephyr")) / "boards.json" with open(boards_file) as f: boards = json.load(f) BOARD = os.getenv("TVM_MICRO_BOARD", default="nucleo_l4r5zi") TARGET = tvm.target.target.micro(boards[BOARD]["model"]) .. GENERATED FROM PYTHON SOURCE LINES 108-117 Extracting tuning tasks ######################## Not all operators in the Relay program printed above can be tuned. Some are so trivial that only a single implementation is defined; others don't make sense as tuning tasks. Using `extract_from_program`, you can produce a list of tunable tasks. Because task extraction involves running the compiler, we first configure the compiler's transformation passes; we'll apply the same configuration later on during autotuning. .. GENERATED FROM PYTHON SOURCE LINES 117-123 .. code-block:: default pass_context = tvm.transform.PassContext(opt_level=3, config={"tir.disable_vectorize": True}) with pass_context: tasks = tvm.autotvm.task.extract_from_program(relay_mod["main"], {}, TARGET) assert len(tasks) > 0 .. GENERATED FROM PYTHON SOURCE LINES 124-134 Configuring microTVM ##################### Before autotuning, we need to define a module loader and then pass that to a `tvm.autotvm.LocalBuilder`. Then we create a `tvm.autotvm.LocalRunner` and use both builder and runner to generates multiple measurements for auto tunner. In this tutorial, we have the option to use x86 host as an example or use different targets from Zephyr RTOS. If you choose pass `--platform=host` to this tutorial it will uses x86. You can choose other options by choosing from `PLATFORM` list. .. GENERATED FROM PYTHON SOURCE LINES 134-172 .. code-block:: default module_loader = tvm.micro.AutoTvmModuleLoader( template_project_dir=pathlib.Path(tvm.micro.get_microtvm_template_projects("crt")), project_options={"verbose": False}, ) builder = tvm.autotvm.LocalBuilder( n_parallel=1, build_kwargs={"build_option": {"tir.disable_vectorize": True}}, do_fork=True, build_func=tvm.micro.autotvm_build_func, runtime=RUNTIME, ) runner = tvm.autotvm.LocalRunner(number=1, repeat=1, timeout=100, module_loader=module_loader) measure_option = tvm.autotvm.measure_option(builder=builder, runner=runner) # Compiling for physical hardware if use_physical_hw: module_loader = tvm.micro.AutoTvmModuleLoader( template_project_dir=pathlib.Path(tvm.micro.get_microtvm_template_projects("zephyr")), project_options={ "zephyr_board": BOARD, "west_cmd": "west", "verbose": False, "project_type": "host_driven", }, ) builder = tvm.autotvm.LocalBuilder( n_parallel=1, build_kwargs={"build_option": {"tir.disable_vectorize": True}}, do_fork=False, build_func=tvm.micro.autotvm_build_func, runtime=RUNTIME, ) runner = tvm.autotvm.LocalRunner(number=1, repeat=1, timeout=100, module_loader=module_loader) measure_option = tvm.autotvm.measure_option(builder=builder, runner=runner) .. GENERATED FROM PYTHON SOURCE LINES 173-177 Run Autotuning ######################### Now we can run autotuning separately on each extracted task on microTVM device. .. GENERATED FROM PYTHON SOURCE LINES 177-195 .. code-block:: default autotune_log_file = pathlib.Path("microtvm_autotune.log.txt") if os.path.exists(autotune_log_file): os.remove(autotune_log_file) num_trials = 10 for task in tasks: tuner = tvm.autotvm.tuner.GATuner(task) tuner.tune( n_trial=num_trials, measure_option=measure_option, callbacks=[ tvm.autotvm.callback.log_to_file(str(autotune_log_file)), tvm.autotvm.callback.progress_bar(num_trials, si_prefix="M"), ], si_prefix="M", ) .. GENERATED FROM PYTHON SOURCE LINES 196-202 Timing the untuned program ########################### For comparison, let's compile and run the graph without imposing any autotuning schedules. TVM will select a randomly-tuned implementation for each operator, which should not perform as well as the tuned operator. .. GENERATED FROM PYTHON SOURCE LINES 202-240 .. code-block:: default with pass_context: lowered = tvm.relay.build(relay_mod, target=TARGET, runtime=RUNTIME, params=params) temp_dir = tvm.contrib.utils.tempdir() project = tvm.micro.generate_project( str(tvm.micro.get_microtvm_template_projects("crt")), lowered, temp_dir / "project", {"verbose": False}, ) # Compiling for physical hardware if use_physical_hw: temp_dir = tvm.contrib.utils.tempdir() project = tvm.micro.generate_project( str(tvm.micro.get_microtvm_template_projects("zephyr")), lowered, temp_dir / "project", { "zephyr_board": BOARD, "west_cmd": "west", "verbose": False, "project_type": "host_driven", }, ) project.build() project.flash() with tvm.micro.Session(project.transport()) as session: debug_module = tvm.micro.create_local_debug_executor( lowered.get_graph_json(), session.get_system_lib(), session.device ) debug_module.set_input(**lowered.get_params()) print("########## Build without Autotuning ##########") debug_module.run() del debug_module .. rst-class:: sphx-glr-script-out .. code-block:: none ########## Build without Autotuning ########## Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us) --------- --- -------- ------- ----- ------ ------- ---------------- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.0 98.72 (1, 2, 10, 10, 3) 2 1 [311.0] tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.973 (1, 6, 10, 10) 1 1 [3.066] tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 0.307 (1, 1, 10, 10, 3) 1 1 [0.967] Total_time - 315.033 - - - - - .. GENERATED FROM PYTHON SOURCE LINES 241-244 Timing the tuned program ######################### Once autotuning completes, you can time execution of the entire program using the Debug Runtime: .. GENERATED FROM PYTHON SOURCE LINES 244-282 .. code-block:: default with tvm.autotvm.apply_history_best(str(autotune_log_file)): with pass_context: lowered_tuned = tvm.relay.build(relay_mod, target=TARGET, runtime=RUNTIME, params=params) temp_dir = tvm.contrib.utils.tempdir() project = tvm.micro.generate_project( str(tvm.micro.get_microtvm_template_projects("crt")), lowered_tuned, temp_dir / "project", {"verbose": False}, ) # Compiling for physical hardware if use_physical_hw: temp_dir = tvm.contrib.utils.tempdir() project = tvm.micro.generate_project( str(tvm.micro.get_microtvm_template_projects("zephyr")), lowered_tuned, temp_dir / "project", { "zephyr_board": BOARD, "west_cmd": "west", "verbose": False, "project_type": "host_driven", }, ) project.build() project.flash() with tvm.micro.Session(project.transport()) as session: debug_module = tvm.micro.create_local_debug_executor( lowered_tuned.get_graph_json(), session.get_system_lib(), session.device ) debug_module.set_input(**lowered_tuned.get_params()) print("########## Build with Autotuning ##########") debug_module.run() del debug_module .. rst-class:: sphx-glr-script-out .. code-block:: none ########## Build with Autotuning ########## Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us) --------- --- -------- ------- ----- ------ ------- ---------------- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 223.6 98.728 (1, 1, 10, 10, 6) 2 1 [223.6] tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.926 0.85 (1, 6, 10, 10) 1 1 [1.926] tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.422 (1, 1, 10, 10, 3) 1 1 [0.955] Total_time - 226.481 - - - - - .. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: micro_autotune.py ` .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: micro_autotune.ipynb ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_