lee-bin opened a new issue, #13226:
URL: https://github.com/apache/tvm/issues/13226
### Expected behavior
tvmc compile succeed.
### Actual behavior
tvmc compile failed.
```Traceback (most recent call last):
File "/Users/someone/anaconda3/envs/tvm/lib/python3.8/runpy.py", line 194,
in _run_module_as_main
return _run_code(code, main_globals, None,
File "/Users/someone/anaconda3/envs/tvm/lib/python3.8/runpy.py", line 87,
in _run_code
exec(code, run_globals)
File
"/Users/someone/workspace/code/tvm/python/tvm/driver/tvmc/__main__.py", line
24, in <module>
tvmc.main.main()
File "/Users/someone/workspace/code/tvm/python/tvm/driver/tvmc/main.py",
line 115, in main
sys.exit(_main(sys.argv[1:]))
File "/Users/someone/workspace/code/tvm/python/tvm/driver/tvmc/main.py",
line 103, in _main
return args.func(args)
File
"/Users/someone/workspace/code/tvm/python/tvm/driver/tvmc/compiler.py", line
180, in drive_compile
compile_model(
File
"/Users/someone/workspace/code/tvm/python/tvm/driver/tvmc/compiler.py", line
353, in compile_model
graph_module = build(
File
"/Users/someone/workspace/code/tvm/python/tvm/driver/tvmc/compiler.py", line
428, in build
return relay.build(
File "/Users/someone/workspace/code/tvm/python/tvm/relay/build_module.py",
line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/Users/someone/workspace/code/tvm/python/tvm/relay/build_module.py",
line 161, in build
self._build(
File
"/Users/someone/workspace/code/tvm/python/tvm/_ffi/_ctypes/packed_func.py",
line 237, in __call__
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
[bt] (8) 9 libtvm.dylib 0x000000013d17caf4
tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::relay::backend::RelayBuildModule::GetFunction(std::__1::basic_string<char,
std::__1::char_traits<char>, std::__1::allocator<char> > const&,
tvm::runtime::ObjectPtr<tvm::runtime::Object>
const&)::'lambda1'(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>
>::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs,
tvm::runtime::TVMRetValue*) + 40
[bt] (7) 8 libtvm.dylib 0x000000013d17cd90
tvm::relay::backend::RelayBuildModule::GetFunction(std::__1::basic_string<char,
std::__1::char_traits<char>, std::__1::allocator<char> > const&,
tvm::runtime::ObjectPtr<tvm::runtime::Object>
const&)::'lambda1'(tvm::runtime::TVMArgs,
tvm::runtime::TVMRetValue*)::operator()(tvm::runtime::TVMArgs,
tvm::runtime::TVMRetValue*) const + 656
[bt] (6) 7 libtvm.dylib 0x000000013d17d568
tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule,
tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&,
tvm::relay::Executor const&, tvm::relay::Runtime const&,
tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&,
tvm::runtime::String) + 1028
[bt] (5) 6 libtvm.dylib 0x000000013d17e18c
tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule,
tvm::runtime::String const&) + 2512
[bt] (4) 5 libtvm.dylib 0x000000013bac85ec
tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void>
const&, tvm::Target const&) + 2884
[bt] (3) 4 libtvm.dylib 0x000000013c7ea53c
tvm::codegen::Build(tvm::IRModule, tvm::Target) + 1392
[bt] (2) 3 libtvm.dylib 0x000000013d424a70
tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<void
tvm::runtime::TypedPackedFunc<tvm::runtime::Module (tvm::IRModule,
tvm::Target)>::AssignTypedLambda<tvm::codegen::$_4>(tvm::codegen::$_4,
std::__1::basic_string<char, std::__1::char_traits<char>,
std::__1::allocator<char> >)::'lambda'(tvm::runtime::TVMArgs const&,
tvm::runtime::TVMRetValue*)> >::Call(tvm::runtime::PackedFuncObj const*,
tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) + 872
[bt] (1) 2 libtvm.dylib 0x000000013d421334
tvm::codegen::LLVMModuleNode::Init(tvm::IRModule const&, tvm::Target const&) +
3604
[bt] (0) 1 libtvm.dylib 0x000000013b803a7c
tvm::runtime::detail::LogFatal::Entry::Finalize() + 84
File "/Users/someone/workspace/code/tvm/src/target/llvm/llvm_module.cc",
line 331
TVMError: LLVM module verification failed with the following errors:
Incorrect alignment of return type to called function!
%30 = tail call <4320 x float> @llvm.fmuladd.v4320f32(<4320 x float> %24,
<4320 x float> %29, <4320 x float> %21)
Incorrect alignment of argument passed to called function!
%30 = tail call <4320 x float> @llvm.fmuladd.v4320f32(<4320 x float> %24,
<4320 x float> %29, <4320 x float> %21)
Incorrect alignment of argument passed to called function!
%30 = tail call <4320 x float> @llvm.fmuladd.v4320f32(<4320 x float> %24,
<4320 x float> %29, <4320 x float> %21)
Incorrect alignment of argument passed to called function!
%30 = tail call <4320 x float> @llvm.fmuladd.v4320f32(<4320 x float> %24,
<4320 x float> %29, <4320 x float> %21)
```
### Environment
macOS Monterey, Apple M1 pro
TVM version: v0.10.0, 7b50b2d0ddf45d9114715aad16b867e8be6b2230
### Steps to reproduce
The onnx model is
[here](https://github.com/lee-bin/test/blob/master/onnx-example.onnx).
```
python -m tvm.driver.tvmc compile --target "llvm" --input-shapes
"X:[1,32,4320]" --output onnx-example-tvm.tar onnx-example.onnx
```
### Triage
Please refer to the list of label tags
[here](https://github.com/apache/tvm/wiki/Issue-Triage-Labels) to find the
relevant tags and add them below in a bullet format (example below).
* backend: llvm
* core:ffi
* frontend:onnx
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
