Fix microTVM demos

Author: Mousius

docs/arch/microtvm_design.rst

@@ -127,18 +127,24 @@ logs use it to rank measured performance (but see Future Work).
 Targets are currently represented as strings structured similarly to command-line arguments. An
 example target is shown below:
 
-    ``c -keys=arm_cpu -mcpu=cortex-m7 -link-params -model=stm32f746xx -runtime=c -system-lib=1``
+    ``c -keys=arm_cpu -mcpu=cortex-m7 -model=stm32f746xx``
 
 The relevant parts to microTVM are:
 
  * Code generator (``llvm`` or ``c``)
  * ``-mcpu=cortex-m7``: used by TOPI to enable Cortex-M schedules, and, when the C source code
    generator is selected, included in the output as a comment to help identify the code and
    configure the downstream C compiler.
- * ``-link-params``: include parameters as global constants to load from flash.
- * ``-runtime=c``: build glue code to allow operators to work with the C runtime
- * ``-system-lib=1``: emit a system library (i.e. which can be loaded by calling the PackedFunc
-   ``runtime.SystemLib``.
+
+Runtime and Executor configuration for microTVM
+-----------------------------------------------
+
+When using microTVM, it's important to use the C Runtime (``Runtime('crt')``), which is the runtime that works best on micro devices rather than the more dynamic C++ Runtime. Alongside this, there are two executors which you could use in combination with the C runtime:
+
+* ``Executor("aot")`` - The Ahead of Time (AOT) executor precompiles the network into a runnable function which you can add directly into your micro application
+* ``Executor("graph", {"link-params": True})`` - The Graph executor provides a JSON representation of your network and requires the C Runtime's system library to be generated to find functions in the function registry (``Runtime("crt", {"system-lib": True})``). ``{"link-params":True}`` enables parameters to be linked into the generated files rather than provided externally.
+
+These are specified when building a runtime module: ``relay.build(..., runtime=..., executor=...)``.
 
 Writing Schedules for microTVM
 ------------------------------

gallery/how_to/work_with_microtvm/micro_autotune.py

@@ -32,6 +32,7 @@
 import pathlib
 
 import tvm
+from tvm.relay.backend import Executor, Runtime
 
 ####################
 # Defining the model
@@ -69,13 +70,15 @@
 # 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.
+# 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.
 #
+RUNTIME = Runtime("crt", {"system-lib": True})
 TARGET = tvm.target.target.micro("host")
 
 # Compiling for physical hardware
@@ -126,6 +129,7 @@
     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)
 
@@ -178,7 +182,7 @@
 # the tuned operator.
 
 with pass_context:
-    lowered = tvm.relay.build(relay_mod, target=TARGET, params=params)
+    lowered = tvm.relay.build(relay_mod, target=TARGET, runtime=RUNTIME, params=params)
 
 temp_dir = tvm.contrib.utils.tempdir()
 
@@ -221,7 +225,7 @@
 
 with tvm.autotvm.apply_history_best("microtvm_autotune.log.txt"):
     with pass_context:
-        lowered_tuned = tvm.relay.build(relay_mod, target=TARGET, params=params)
+        lowered_tuned = tvm.relay.build(relay_mod, target=TARGET, runtime=RUNTIME, params=params)
 
 temp_dir = tvm.contrib.utils.tempdir()
 

gallery/how_to/work_with_microtvm/micro_tflite.py

@@ -124,12 +124,9 @@
 
 import os
 import numpy as np
-import logging
 
 import tvm
-import tvm.micro as micro
 from tvm.contrib.download import download_testdata
-from tvm.contrib import graph_executor, utils
 from tvm import relay
 
 model_url = "https://people.linaro.org/~tom.gall/sine_model.tflite"
@@ -179,9 +176,10 @@
 # Now we create a build config for relay, turning off two options and then calling relay.build which
 # will result in a C source file for the selected TARGET. When running on a simulated target of the
 # same architecture as the host (where this Python script is executed) choose "host" below for the
-# TARGET and a proper board/VM to run it (Zephyr will create the right QEMU VM based on BOARD. In
-# the example below the x86 arch is selected and a x86 VM is picked up accordingly:
+# TARGET, the C Runtime as the RUNTIME and a proper board/VM to run it (Zephyr will create the right
+# QEMU VM based on BOARD. In the example below the x86 arch is selected and a x86 VM is picked up accordingly:
 #
+RUNTIME = tvm.relay.backend.Runtime("crt", {"system-lib": True})
 TARGET = tvm.target.target.micro("host")
 BOARD = "qemu_x86"
 #
@@ -210,7 +208,7 @@
 with tvm.transform.PassContext(
     opt_level=3, config={"tir.disable_vectorize": True}, disabled_pass=["AlterOpLayout"]
 ):
-    module = relay.build(mod, target=TARGET, params=params)
+    module = relay.build(mod, target=TARGET, runtime=RUNTIME, params=params)
 
 
 # Inspecting the compilation output

tests/micro/arduino/test_arduino_rpc_server.py

@@ -22,7 +22,6 @@
 
 """
 
-import datetime
 import pathlib
 import sys
 
@@ -31,8 +30,9 @@
 import pytest
 import tvm
 from PIL import Image
-from tvm import micro, relay
+from tvm import relay
 from tvm.relay.testing import byoc
+from tvm.relay.backend import Executor, Runtime
 
 import conftest
 
@@ -191,9 +191,11 @@ def test_onnx(board, arduino_cli_cmd, tvm_debug, workspace_dir):
     relay_mod, params = relay.frontend.from_onnx(onnx_model, shape=shape, freeze_params=True)
     relay_mod = relay.transform.DynamicToStatic()(relay_mod)
 
-    target = tvm.target.target.micro(model, options=["-link-params=1"])
+    target = tvm.target.target.micro(model)
     with tvm.transform.PassContext(opt_level=3, config={"tir.disable_vectorize": True}):
-        lowered = relay.build(relay_mod, target, params=params)
+        executor = Executor("graph", {"link-params": True})
+        runtime = Runtime("crt", {"system-lib": True})
+        lowered = relay.build(relay_mod, target, params=params, executor=executor, runtime=runtime)
         graph = lowered.get_graph_json()
 
     with _make_session(

tests/micro/zephyr/test_zephyr.py

@@ -17,7 +17,6 @@
 import logging
 import os
 import pathlib
-import subprocess
 import sys
 import logging
 
@@ -220,7 +219,7 @@ def test_onnx(temp_dir, board, west_cmd, tvm_debug):
     relay_mod, params = relay.frontend.from_onnx(onnx_model, shape=shape, freeze_params=True)
     relay_mod = relay.transform.DynamicToStatic()(relay_mod)
 
-    # We add the -link-params=1 option to ensure the model parameters are compiled in.
+    # We add the link-params=True option to ensure the model parameters are compiled in.
     # There is currently a bug preventing the host_driven environment from receiving
     # the model weights when set using graph_mod.set_input().
     # See: https://github.com/apache/tvm/issues/7567

tests/micro/zephyr/test_zephyr_armv7m.py

@@ -35,6 +35,7 @@
 
 from tvm.contrib.download import download_testdata
 from tvm.micro.model_library_format import generate_c_interface_header
+from tvm.relay.backend import Executor, Runtime
 
 import conftest
 
@@ -187,14 +188,10 @@ def test_armv7m_intrinsic(temp_dir, board, west_cmd, tvm_debug):
 
     target = tvm.target.target.micro(
         model,
-        options=[
-            "-keys=arm_cpu,cpu",
-            "-link-params=1",
-            "--executor=aot",
-            "--unpacked-api=1",
-            "--interface-api=c",
-        ],
+        options=["-keys=arm_cpu,cpu"],
     )
+    executor = Executor("aot", {"unpacked-api": True, "interface-api": "c"})
+    runtime = Runtime("crt")
 
     temp_dir_simd = temp_dir / "simd"
     temp_dir_no_simd = temp_dir / "nosimd"
@@ -204,7 +201,9 @@ def test_armv7m_intrinsic(temp_dir, board, west_cmd, tvm_debug):
 
     with tvm.transform.PassContext(opt_level=3, config={"tir.disable_vectorize": True}):
         lowered_simd = relay.build(relay_mod_simd, target, params=params)
-        lowered_no_simd = relay.build(relay_mod_no_simd, target, params=params)
+        lowered_no_simd = relay.build(
+            relay_mod_no_simd, target, params=params, runtime=runtime, executor=executor
+        )
         result_simd, time_simd = _run_model(
             temp_dir_simd, board, west_cmd, lowered_simd, build_config, sample, output_shape
         )