new --runtime=c fails for uTVM

[tom-gall]

@areusch

The failure looks like
graph, c_mod, params = relay.build(mod, target=target, params=params)
Traceback (most recent call last):
File "./working-micro-st-tflite.py", line 48, in
micro_mod = micro.create_micro_mod(c_mod, dev_config)
File "/home/tgall/tvm/tvm/python/tvm/micro/base.py", line 213, in create_micro_mod
micro_mod = tvm.runtime.load_module(lib_obj_path)
File "/home/tgall/tvm/tvm/python/tvm/runtime/module.py", line 407, in load_module
return _ffi_api.ModuleLoadFromFile(path, fmt)
File "/home/tgall/tvm/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line 225, in call
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
[bt] (6) /home/tgall/tvm/tvm/build/libtvm.so(TVMFuncCall+0x63) [0x7f0b6f5594e3]
[bt] (5) /home/tgall/tvm/tvm/build/libtvm.so(std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), tvm::runtime::TypedPackedFunc<tvm::runtime::Module (std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&)>::AssignTypedLambda<tvm::runtime::Module ()(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&)>(tvm::runtime::Module ()(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&))::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)+0xa3) [0x7f0b6f57a9e3]
[bt] (4) /home/tgall/tvm/tvm/build/libtvm.so(tvm::runtime::Module::LoadFromFile(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&)+0x1d8) [0x7f0b6f575c38]
[bt] (3) /home/tgall/tvm/tvm/build/libtvm.so(+0x18a270a) [0x7f0b6f5f070a]
[bt] (2) /home/tgall/tvm/tvm/build/libtvm.so(tvm::runtime::MicroSession::LoadBinary(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool)+0x14f) [0x7f0b6f5f5e9f]
[bt] (1) /home/tgall/tvm/tvm/build/libtvm.so(tvm::runtime::MicroSession::AllocateInSection(tvm::runtime::SectionKind, unsigned long)+0x1a5) [0x7f0b6f5f5795]
[bt] (0) /home/tgall/tvm/tvm/build/libtvm.so(+0x18a4898) [0x7f0b6f5f2898]
File "/home/tgall/tvm/tvm/src/runtime/micro/micro_section_allocator.h", line 68
TVMError: Check failed: size + size < capacity: cannot alloc 208 bytes in section "rodata" (start_addr=0x20004650, used=0, capacity=100)

I think we've seen this before haven't we?

code

import os
import numpy as np
import tvm
import tvm.micro as micro
from tvm.contrib import graph_runtime, util

from tvm import relay
from tvm.contrib.download import download_testdata

target = "c --system-lib --runtime=c"
model_dir ="/home/tgall/tvm/utvm-exp/"
tflite_model_file = os.path.join(model_dir, "sine_model.tflite")
tflite_model_buf = open(tflite_model_file, "rb").read()

try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
version = tflite_model.Version()
print ("Model Version: " + version)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
version = tflite_model.Version()
print ("Model Version: " + str(version))

input_tensor = "dense_4_input"
input_shape = (1,)
input_dtype = "float32"

dev_config = micro.device.arm.stm32f746xx.generate_config("127.0.0.1", 6666)

mod, params = relay.frontend.from_tflite(tflite_model,
shape_dict={input_tensor: input_shape},
dtype_dict={input_tensor: input_dtype})

with micro.Session(dev_config) as sess:
ctx = tvm.micro_dev(0)

with tvm.transform.PassContext(disabled_pass={'FuseOps'}, config={"tir.disable_vectorize": True}):
    graph, c_mod, params = relay.build(mod, target=target, params=params)

micro_mod = micro.create_micro_mod(c_mod, dev_config)
mod = graph_runtime.create(graph, micro_mod, ctx)

mod.set_input(**params)

#throw a simple single bogus number at the model
mod.set_input(input_tensor, tvm.nd.array(np.array([0.5], dtype="float32")))

mod.run()

tvm_output = mod.get_output(0).asnumpy()

print("result is: "+str(tvm_output))