2019-12-22 13:25:02 +08:00
|
|
|
from __future__ import absolute_import
|
|
|
|
|
from __future__ import division
|
|
|
|
|
from __future__ import print_function
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
import os
|
2020-01-21 01:30:08 +08:00
|
|
|
import sys
|
2019-12-22 13:25:02 +08:00
|
|
|
import unittest
|
Compiling Models with Large Constant Arrays (#146)
* PoC works.
* MNist works.
* Clean up.
* Fix test.
* Make Linux work.
* Use consistent symbol name.
* Fix variable name.
* Fix array addr access.
* Bug fix.
* Bug fix.
* install before running e2e tests.
* Fix build config.
* Use sudo when installing.
* Make embeddedDataLoader position independent.
* Enable ResNet50.
* Format code.
* Format MainUtil.
* Try not using sudo to install.
* Supply runtime dir via environment variable.
* Dump problematic operation.
* Dump entire function.
* Debug.
* Dump input.
* Dump constant op.
* Debug.
* Debug.
* Debug.
* Print to stderr.
* take care of endianness.
* Use endianness-aware execution session.
* Fix ZLinux error.
* Include warning when desired output endianness can't be deduced.
* Remove debug code.
* Remove debug code in shape inference.
* Support binary-decoder for testing constants packing.
* Support filename, move-to-file, elision-threshold configurations in constant packing pass for easy testing.
* Add lit test, fix lit test type mismatch.
* Add more consts packing tests.
* Ensure intermediate files are properly cleaned up.
* No need for constant elimination.
* Link with threading libraries.
* Remove debug code.
* Format code.
* More tests.
* test nit.
* Remove debug code.
* Reduce hard-coded constants.
* Use temporary and unique working directory for hosting model parameters.
* Test if it works.
* Try to find objcopy.
* Rename symbols using objcopy.
* Move sanitized name to linux section.
* Use verbose mode for debugging.
* Disambiguate pass constructor.
* Fix symbol name.
* Use Command API to build and execute commands.
* Move linux to use Command API.
* Fix reset args.
* Execute redefine sym.
* Format code.
* Do not use verbose mode for CircleCI.
* Remove debug code.
* Prettify code, add comments.
* getSegmentData -> getEmbeddedConstPool
* vector -> std::vector.
* Make sure we properly clean up intermediate files.
* Fix test cases.
* Add runtime directory.
* Trigger rebuild.
* [Merge with master] fix debug script.
* Diable affine fusion pass for now.
* Support generic fallback const packing mechanism.
* Remove debug code.
* Handle the case where objcopy is not available.
* Fix Windows missing types.
* Support int64.
* Copy packed constant to a local directory for non-Linux/Mac platforms.
* Nit: remove debug code, refactor const pack preprocessing out as a separate function.
* Cannot make preprocessConstPack a standalone function because file removers are stack-allocated, and they are deallocated prematurely when function stack gets popped, deleteing intermediate files too early.
* Don't require executable filename.
* Import ONNX data types directly.
* Fix LIT test.
* Bug fix, use moved string value.
* Remove redundant filenames.
* Fix CMake script.
* Embed endianness information as a symbol, and check during runtime.
* More comments, update lit tests.
* Fix lit test on BE machine.
* Copyright notices.
2020-06-12 10:27:05 +08:00
|
|
|
import warnings
|
2019-12-22 13:25:02 +08:00
|
|
|
import onnx.backend.base
|
|
|
|
|
import onnx.backend.test
|
|
|
|
|
|
|
|
|
|
from onnx.backend.base import Device, DeviceType
|
|
|
|
|
import subprocess
|
2020-01-21 01:30:08 +08:00
|
|
|
import test_config
|
|
|
|
|
|
|
|
|
|
VERBOSE = bool(os.environ.get("VERBOSE"))
|
|
|
|
|
|
|
|
|
|
CXX = test_config.CXX_PATH
|
2020-03-17 21:16:33 +08:00
|
|
|
ONNX_MLIR = os.path.join(test_config.ONNX_MLIR_BUILD_PATH, "bin/onnx-mlir")
|
2020-01-21 01:30:08 +08:00
|
|
|
LLC = os.path.join(test_config.LLVM_PROJ_BUILD_PATH, "bin/llc")
|
|
|
|
|
|
|
|
|
|
# Make lib folder under build directory visible in PYTHONPATH
|
|
|
|
|
doc_check_base_dir = os.path.dirname(os.path.realpath(__file__))
|
2020-03-17 21:16:33 +08:00
|
|
|
RUNTIME_DIR = os.path.join(test_config.ONNX_MLIR_BUILD_PATH, "lib")
|
2020-01-21 01:30:08 +08:00
|
|
|
sys.path.append(RUNTIME_DIR)
|
2020-06-08 10:18:55 +08:00
|
|
|
from PyRuntime import ExecutionSession
|
2019-12-22 13:25:02 +08:00
|
|
|
|
2020-01-21 01:30:08 +08:00
|
|
|
|
|
|
|
|
def execute_commands(cmds):
|
|
|
|
|
if (VERBOSE):
|
|
|
|
|
print(" ".join(cmds))
|
Compiling Models with Large Constant Arrays (#146)
* PoC works.
* MNist works.
* Clean up.
* Fix test.
* Make Linux work.
* Use consistent symbol name.
* Fix variable name.
* Fix array addr access.
* Bug fix.
* Bug fix.
* install before running e2e tests.
* Fix build config.
* Use sudo when installing.
* Make embeddedDataLoader position independent.
* Enable ResNet50.
* Format code.
* Format MainUtil.
* Try not using sudo to install.
* Supply runtime dir via environment variable.
* Dump problematic operation.
* Dump entire function.
* Debug.
* Dump input.
* Dump constant op.
* Debug.
* Debug.
* Debug.
* Print to stderr.
* take care of endianness.
* Use endianness-aware execution session.
* Fix ZLinux error.
* Include warning when desired output endianness can't be deduced.
* Remove debug code.
* Remove debug code in shape inference.
* Support binary-decoder for testing constants packing.
* Support filename, move-to-file, elision-threshold configurations in constant packing pass for easy testing.
* Add lit test, fix lit test type mismatch.
* Add more consts packing tests.
* Ensure intermediate files are properly cleaned up.
* No need for constant elimination.
* Link with threading libraries.
* Remove debug code.
* Format code.
* More tests.
* test nit.
* Remove debug code.
* Reduce hard-coded constants.
* Use temporary and unique working directory for hosting model parameters.
* Test if it works.
* Try to find objcopy.
* Rename symbols using objcopy.
* Move sanitized name to linux section.
* Use verbose mode for debugging.
* Disambiguate pass constructor.
* Fix symbol name.
* Use Command API to build and execute commands.
* Move linux to use Command API.
* Fix reset args.
* Execute redefine sym.
* Format code.
* Do not use verbose mode for CircleCI.
* Remove debug code.
* Prettify code, add comments.
* getSegmentData -> getEmbeddedConstPool
* vector -> std::vector.
* Make sure we properly clean up intermediate files.
* Fix test cases.
* Add runtime directory.
* Trigger rebuild.
* [Merge with master] fix debug script.
* Diable affine fusion pass for now.
* Support generic fallback const packing mechanism.
* Remove debug code.
* Handle the case where objcopy is not available.
* Fix Windows missing types.
* Support int64.
* Copy packed constant to a local directory for non-Linux/Mac platforms.
* Nit: remove debug code, refactor const pack preprocessing out as a separate function.
* Cannot make preprocessConstPack a standalone function because file removers are stack-allocated, and they are deallocated prematurely when function stack gets popped, deleteing intermediate files too early.
* Don't require executable filename.
* Import ONNX data types directly.
* Fix LIT test.
* Bug fix, use moved string value.
* Remove redundant filenames.
* Fix CMake script.
* Embed endianness information as a symbol, and check during runtime.
* More comments, update lit tests.
* Fix lit test on BE machine.
* Copyright notices.
2020-06-12 10:27:05 +08:00
|
|
|
subprocess.run(cmds)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# There are two issues, which necessitates the adoption of this endianness
|
|
|
|
|
# aware wrapper around Execution Session:
|
|
|
|
|
# 1. Input arrays are given sometimes in native byte order, sometime in
|
|
|
|
|
# LE byte order, and as soon as the python array enters into py::array
|
|
|
|
|
# C++ objects through pybind, we will no longer be able to query their
|
|
|
|
|
# endianness. So we must intercept the inputs and convert them into
|
|
|
|
|
# native endianness.
|
|
|
|
|
# 2. Output arrays are compared with reference outputs, the comparison
|
|
|
|
|
# unfortunately includes checking that our outputs and reference outputs
|
|
|
|
|
# share the same endianness. So we try to figure out what is the desired
|
|
|
|
|
# reference output endianness, and convert our outputs to this desired
|
|
|
|
|
# endianness.
|
|
|
|
|
class EndiannessAwareExecutionSession(ExecutionSession):
|
|
|
|
|
def __init__(self, path, entry_point):
|
|
|
|
|
super().__init__(path, entry_point)
|
|
|
|
|
|
|
|
|
|
def is_input_le(self, inputs):
|
|
|
|
|
inputs_endianness = list(map(lambda x: x.dtype.byteorder, inputs))
|
|
|
|
|
endianness_is_consistent = len(set(inputs_endianness)) <= 1
|
|
|
|
|
assert endianness_is_consistent, \
|
|
|
|
|
"Input arrays contain a mixture of endianness configuration."
|
|
|
|
|
|
|
|
|
|
sys_is_le = sys.byteorder == 'little'
|
|
|
|
|
# To interpret character symbols indicating endianness:
|
|
|
|
|
# https://numpy.org/doc/stable/reference/generated/numpy.dtype.byteorder.html
|
|
|
|
|
explicitly_le = inputs_endianness[0] == "<"
|
|
|
|
|
implicitly_le = (inputs_endianness[0] == "=" and sys_is_le)
|
|
|
|
|
return explicitly_le or implicitly_le
|
|
|
|
|
|
|
|
|
|
def run(self, inputs, **kwargs):
|
|
|
|
|
if len(inputs):
|
|
|
|
|
# Deduce desired endianness of output from inputs.
|
|
|
|
|
sys_is_le = sys.byteorder == 'little'
|
|
|
|
|
inp_is_le = self.is_input_le(inputs)
|
|
|
|
|
if (sys_is_le != inp_is_le):
|
|
|
|
|
inputs = list(
|
|
|
|
|
map(lambda x: x.byteswap().newbyteorder(), inputs))
|
|
|
|
|
outputs = super().run(inputs)
|
|
|
|
|
if (sys_is_le != inp_is_le):
|
|
|
|
|
outputs = list(
|
|
|
|
|
map(lambda x: x.byteswap().newbyteorder(), outputs))
|
|
|
|
|
return outputs
|
|
|
|
|
else:
|
|
|
|
|
# Can't deduce desired output endianess, fingers crossed.
|
|
|
|
|
warnings.warn(
|
|
|
|
|
"Cannot deduce desired output endianness, using native endianness by default."
|
|
|
|
|
)
|
|
|
|
|
return super().run(inputs)
|
2020-01-21 01:30:08 +08:00
|
|
|
|
2019-12-22 13:25:02 +08:00
|
|
|
|
|
|
|
|
class DummyBackend(onnx.backend.base.Backend):
|
|
|
|
|
@classmethod
|
2020-01-21 01:30:08 +08:00
|
|
|
def prepare(cls, model, device='CPU', **kwargs):
|
2019-12-22 13:25:02 +08:00
|
|
|
super(DummyBackend, cls).prepare(model, device, **kwargs)
|
|
|
|
|
# Save model to disk as temp_model.onnx.
|
|
|
|
|
onnx.save(model, "temp_model.onnx")
|
|
|
|
|
# Call frontend to process temp_model.onnx, bit code will be generated.
|
2020-03-17 21:16:33 +08:00
|
|
|
execute_commands([ONNX_MLIR, "temp_model.onnx"])
|
Compiling Models with Large Constant Arrays (#146)
* PoC works.
* MNist works.
* Clean up.
* Fix test.
* Make Linux work.
* Use consistent symbol name.
* Fix variable name.
* Fix array addr access.
* Bug fix.
* Bug fix.
* install before running e2e tests.
* Fix build config.
* Use sudo when installing.
* Make embeddedDataLoader position independent.
* Enable ResNet50.
* Format code.
* Format MainUtil.
* Try not using sudo to install.
* Supply runtime dir via environment variable.
* Dump problematic operation.
* Dump entire function.
* Debug.
* Dump input.
* Dump constant op.
* Debug.
* Debug.
* Debug.
* Print to stderr.
* take care of endianness.
* Use endianness-aware execution session.
* Fix ZLinux error.
* Include warning when desired output endianness can't be deduced.
* Remove debug code.
* Remove debug code in shape inference.
* Support binary-decoder for testing constants packing.
* Support filename, move-to-file, elision-threshold configurations in constant packing pass for easy testing.
* Add lit test, fix lit test type mismatch.
* Add more consts packing tests.
* Ensure intermediate files are properly cleaned up.
* No need for constant elimination.
* Link with threading libraries.
* Remove debug code.
* Format code.
* More tests.
* test nit.
* Remove debug code.
* Reduce hard-coded constants.
* Use temporary and unique working directory for hosting model parameters.
* Test if it works.
* Try to find objcopy.
* Rename symbols using objcopy.
* Move sanitized name to linux section.
* Use verbose mode for debugging.
* Disambiguate pass constructor.
* Fix symbol name.
* Use Command API to build and execute commands.
* Move linux to use Command API.
* Fix reset args.
* Execute redefine sym.
* Format code.
* Do not use verbose mode for CircleCI.
* Remove debug code.
* Prettify code, add comments.
* getSegmentData -> getEmbeddedConstPool
* vector -> std::vector.
* Make sure we properly clean up intermediate files.
* Fix test cases.
* Add runtime directory.
* Trigger rebuild.
* [Merge with master] fix debug script.
* Diable affine fusion pass for now.
* Support generic fallback const packing mechanism.
* Remove debug code.
* Handle the case where objcopy is not available.
* Fix Windows missing types.
* Support int64.
* Copy packed constant to a local directory for non-Linux/Mac platforms.
* Nit: remove debug code, refactor const pack preprocessing out as a separate function.
* Cannot make preprocessConstPack a standalone function because file removers are stack-allocated, and they are deallocated prematurely when function stack gets popped, deleteing intermediate files too early.
* Don't require executable filename.
* Import ONNX data types directly.
* Fix LIT test.
* Bug fix, use moved string value.
* Remove redundant filenames.
* Fix CMake script.
* Embed endianness information as a symbol, and check during runtime.
* More comments, update lit tests.
* Fix lit test on BE machine.
* Copyright notices.
2020-06-12 10:27:05 +08:00
|
|
|
return EndiannessAwareExecutionSession("./temp_model.so",
|
Cleanup rtmemref api (#238)
* Detect llvm-project commit change in utils/clone-mlir.sh and rebuild llvm-project
for zLinux Jenkins build bot
* Cleanup RtMemRef API
- use forward declaration to hide private data fields
- RtMemRef.h: external user header, C/C++
- _RtMemRef.h: internal user header, C++ only
- RtMemRef.hpp and RtMemRef.cpp: implementation header and file
- add external APIs
OrderedRtMemRefDict *ormrd_create(RtMemRef **rmrs, int n)
RtMemRef **ormrd_getRmrs(OrderedRtMemRefDict *ormrd)
int ormrd_getNumOfRmrs(OrderedRtMemRefDict *ormrd)
for creating and querying OrderedRtMemRefDict with RtMemRef arrays
- data buffer installed by rmr_setData() will be managed by user
- unique_ptr<RtMemRef> must use custom deleter <RtMemRef,decltype(&rmr_destroy)>
* See if I have write access.
* Remove test CMake code.
* Use new API.
* Format code.
* Format code & rename variables for readability.
* Remove used API spec.
* Rename OrderedRtMemRefDict -> RtMemRefList, _dataMalloc -> _owningData.
* OrderedRtMemRefDict -> RtMemRefList
* Update KrnlToLLVM.cpp
* Trigger Jenkins
* Restart Jenkins
* OrderedRtMemRefDict -> RtRmrRefList
* More OrderedRtMemRefDict -> RtMemRefList.
* Format jni wrapper.
* Rename API functions to maintain stylistic consistency.
* Bug fix.
* Bug fix.
* Format code.
* Fix RtMemRefUtils.
* Format code.
* Using llvm function naming scheme.
* Rename runtime api file name to project name (onnx-mlir) as per convention.
* Include the new runtime header file.
* Reflect api header file name change in build script.
* Bug fix.
* Remove C++ code.
* Revert "Remove C++ code."
This reverts commit b217dfabae99e42db30721600cb5507866d4dc98.
* Clarify memory management responsibility.
* Add constructor to specify name & data ownership.
* Include stdbool.
* Remove dictionary semantics from RtMemRefList
* Bug fix.
* Format code.
* Format code.
* Use macro to define database of metadata.
* Prevent formatter from acting on metadata decl.
* Nit.
* Restore backend unit tests.
* Use spaces instead of tabs for better formatting.
* Use explicit template instantiation.
* Update RtMemRef struct doc.
* Make runtime compilable both in c and c++ mode.
Build two versions of the runtime library, one c version as the user-facing c runtime, and one c++ version as the one used inside this project.
* Bug fix, avoid stack allocation for output rmr list.
* Change _dyn_entry_point_main_graph -> run_main_graph for better memorability.
* Write a complete introductory tutorial on c99 Runtime and a test for it.
* Add onnx installation as dependency.
* Use target_include_directory to avoid installation.
* Format code.
* Fix cmake target_include_directories.
* Address compiler warning.
* First pass of RtMemRef->OMTensor.
* Second pass of RtMemRef -> OMTensor.
* nit, omtList -> omTensorList.
* omt -> omTensor for clarity.
* Rename OnnxMlirInternal.h -> OnnxMlirRuntime.hpp because there's no internal/external API, only C/C++ API.
* Format code.
* Restructure Runtime source code and move header -> /include and test -> /test/unit.
* Bugfix.
* Format code.
* Add unit test for OMTensor ctor.
* Update JNI CMake include directory.
* Bugfix.
* No need to re-declare ONNX types.
* Disable runtime doc test on non-x86 platforms.
* Rename OMTensor fields to be more sensible.
* Fix data type mismatch.
* size_t -> int64_t, prefer fixed width integers.
* Use consistent header guard style.
* Further tweak OMTensor API.
* Bugfix.
* Bugfix.
* Format code.
* Add doxygen config file.
* Tweak OMTensor API.
* Tweak API doc, hide OMTensorList implementation.
* Format code.
* Add new documentation item for Runtime API.
* Hide internal use only API declarations, move their comments to their implementations.
* Clarify ownership semantics in relevant API documentations.
* Fix PyRuntime.
* Remove alignment concerns from public API and include explaination of alignment issue in struct OMTensor definition.
* Print out unsupported numpy dtype.
* Use preferred way of type comparison in pybind11.
* Debug s390x issue.
* Remove debug code.
* Clarify semantics of strides/shape setter/getter, use \brief to include short description of API function.
* Improve documentation.
* Single out unpolished C++ API declarations.
* Clarify OMTensorList API.
* Bugfix.
* Bugfix.
* Assert after malloc.
* Handle malloc failures.
* Nit.
* Tweak legal notices.
* Format code.
* Remove doxygen generated files.
* Tweak legal notice format.
* Upgrade Cython
Numpy installation depends on Cython.
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-10-10 22:32:09 +08:00
|
|
|
"run_main_graph")
|
2019-12-22 13:25:02 +08:00
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def supports_device(cls, device):
|
|
|
|
|
d = Device(device)
|
|
|
|
|
if d.type == DeviceType.CPU:
|
|
|
|
|
return True
|
|
|
|
|
return False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
backend_test = onnx.backend.test.BackendTest(DummyBackend, __name__)
|
|
|
|
|
|
|
|
|
|
# Test directories:
|
|
|
|
|
# https://github.com/onnx/onnx/tree/master/onnx/backend/test/data/node
|
|
|
|
|
test_to_enable = [
|
2020-03-17 23:12:45 +08:00
|
|
|
# Abs Op:
|
|
|
|
|
"test_abs_cpu",
|
|
|
|
|
|
2019-12-22 13:25:02 +08:00
|
|
|
# Add Op:
|
|
|
|
|
"test_add_cpu",
|
|
|
|
|
"test_add_bcast_cpu",
|
|
|
|
|
|
|
|
|
|
# And Op:
|
|
|
|
|
|
|
|
|
|
# Sub Op:
|
|
|
|
|
"test_sub_cpu",
|
|
|
|
|
"test_sub_bcast_cpu",
|
|
|
|
|
"test_sub_example_cpu",
|
|
|
|
|
|
|
|
|
|
# Cosh Op:
|
|
|
|
|
"test_cosh_cpu",
|
|
|
|
|
"test_cosh_example_cpu",
|
|
|
|
|
|
2020-04-13 23:40:39 +08:00
|
|
|
# Concat
|
|
|
|
|
"test_concat_1d_axis_0_cpu",
|
|
|
|
|
"test_concat_2d_axis_0_cpu",
|
|
|
|
|
"test_concat_2d_axis_1_cpu",
|
|
|
|
|
"test_concat_3d_axis_0_cpu",
|
|
|
|
|
"test_concat_3d_axis_1_cpu",
|
|
|
|
|
"test_concat_3d_axis_2_cpu",
|
|
|
|
|
"test_concat_1d_axis_negative_1_cpu",
|
|
|
|
|
"test_concat_2d_axis_negative_1_cpu",
|
|
|
|
|
"test_concat_2d_axis_negative_2_cpu",
|
|
|
|
|
"test_concat_3d_axis_negative_1_cpu",
|
|
|
|
|
"test_concat_3d_axis_negative_2_cpu",
|
|
|
|
|
"test_concat_3d_axis_negative_3_cpu",
|
|
|
|
|
|
2020-04-09 14:22:36 +08:00
|
|
|
# Tanh:
|
|
|
|
|
"test_tanh_cpu",
|
|
|
|
|
"test_tanh_example_cpu",
|
|
|
|
|
|
2019-12-22 13:25:02 +08:00
|
|
|
# Div Op:
|
|
|
|
|
"test_div_cpu",
|
|
|
|
|
"test_div_bcast_cpu",
|
|
|
|
|
"test_div_example_cpu",
|
|
|
|
|
|
|
|
|
|
# Elu Op:
|
|
|
|
|
"test_elu_cpu",
|
|
|
|
|
"test_elu_default_cpu",
|
|
|
|
|
"test_elu_example_cpu",
|
|
|
|
|
|
|
|
|
|
# Exp Op:
|
|
|
|
|
"test_exp_cpu",
|
|
|
|
|
"test_exp_example_cpu",
|
|
|
|
|
|
2020-09-12 03:36:23 +08:00
|
|
|
# Gather Op:
|
2020-09-25 02:02:49 +08:00
|
|
|
"test_gather_0_cpu",
|
|
|
|
|
"test_gather_1_cpu",
|
|
|
|
|
"test_gather_negative_indices_cpu",
|
2020-09-12 03:36:23 +08:00
|
|
|
|
2020-01-30 00:11:49 +08:00
|
|
|
# Gemm Op:
|
|
|
|
|
"test_gemm_all_attributes_cpu",
|
|
|
|
|
"test_gemm_alpha_cpu",
|
|
|
|
|
"test_gemm_beta_cpu",
|
|
|
|
|
"test_gemm_default_matrix_bias_cpu",
|
2020-02-20 23:55:24 +08:00
|
|
|
"test_gemm_default_no_bias_cpu",
|
2020-02-13 13:50:05 +08:00
|
|
|
"test_gemm_default_scalar_bias_cpu",
|
2020-01-30 00:11:49 +08:00
|
|
|
"test_gemm_default_single_elem_vector_bias_cpu",
|
|
|
|
|
"test_gemm_default_vector_bias_cpu",
|
|
|
|
|
"test_gemm_default_zero_bias_cpu",
|
|
|
|
|
"test_gemm_transposeA_cpu",
|
|
|
|
|
"test_gemm_transposeB_cpu",
|
|
|
|
|
|
2019-12-22 13:25:02 +08:00
|
|
|
# Hard Sigmoid Op:
|
|
|
|
|
"test_hardsigmoid_cpu",
|
|
|
|
|
"test_hardsigmoid_default_cpu",
|
|
|
|
|
"test_hardsigmoid_example_cpu",
|
|
|
|
|
|
|
|
|
|
# Leaky Relu Op:
|
|
|
|
|
"test_leakyrelu_cpu",
|
|
|
|
|
"test_leakyrelu_default_cpu",
|
|
|
|
|
"test_leakyrelu_example_cpu",
|
|
|
|
|
|
|
|
|
|
# Max Op:
|
2020-01-28 21:48:11 +08:00
|
|
|
"test_max_example_cpu",
|
2019-12-22 13:25:02 +08:00
|
|
|
"test_max_one_input_cpu",
|
2020-01-28 21:48:11 +08:00
|
|
|
"test_max_two_inputs_cpu",
|
2019-12-22 13:25:02 +08:00
|
|
|
|
|
|
|
|
# Min Op:
|
2020-01-28 21:48:11 +08:00
|
|
|
"test_min_example_cpu",
|
2019-12-22 13:25:02 +08:00
|
|
|
"test_min_one_input_cpu",
|
2020-01-28 21:48:11 +08:00
|
|
|
"test_min_two_inputs_cpu",
|
2019-12-22 13:25:02 +08:00
|
|
|
|
|
|
|
|
# Mul Op:
|
|
|
|
|
"test_mul_cpu",
|
|
|
|
|
"test_mul_bcast_cpu",
|
|
|
|
|
"test_mul_example_cpu",
|
|
|
|
|
|
|
|
|
|
# Relu Op:
|
|
|
|
|
"test_relu_cpu",
|
|
|
|
|
|
2020-02-10 21:38:19 +08:00
|
|
|
# ReduceMax Op:
|
|
|
|
|
"test_reduce_max_default_axes_keepdim_example_cpu",
|
|
|
|
|
"test_reduce_max_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_max_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_max_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_max_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_max_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_max_negative_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_max_negative_axes_keepdims_random_cpu",
|
|
|
|
|
|
|
|
|
|
# ReduceMin Op:
|
|
|
|
|
"test_reduce_min_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_min_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_min_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_min_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_min_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_min_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_min_negative_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_min_negative_axes_keepdims_random_cpu",
|
|
|
|
|
|
|
|
|
|
# ReduceProd Op:
|
|
|
|
|
"test_reduce_prod_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_prod_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_prod_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_prod_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_prod_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_prod_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_prod_negative_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_prod_negative_axes_keepdims_random_cpu",
|
|
|
|
|
|
|
|
|
|
# ReduceSum Op:
|
|
|
|
|
"test_reduce_sum_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_sum_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_sum_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_sum_negative_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_negative_axes_keepdims_random_cpu",
|
|
|
|
|
|
2020-03-17 23:12:45 +08:00
|
|
|
# ReduceL1
|
|
|
|
|
"test_reduce_l1_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_l1_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_l1_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_l1_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_l1_keep_dims_example_cpu",
|
|
|
|
|
"test_reduce_l1_keep_dims_random_cpu",
|
|
|
|
|
"test_reduce_l1_negative_axes_keep_dims_example_cpu",
|
|
|
|
|
"test_reduce_l1_negative_axes_keep_dims_random_cpu",
|
2020-02-12 16:40:32 +08:00
|
|
|
|
|
|
|
|
# ReduceL2
|
|
|
|
|
"test_reduce_l2_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_l2_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_l2_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_l2_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_l2_keep_dims_example_cpu",
|
|
|
|
|
"test_reduce_l2_keep_dims_random_cpu",
|
|
|
|
|
"test_reduce_l2_negative_axes_keep_dims_example_cpu",
|
|
|
|
|
"test_reduce_l2_negative_axes_keep_dims_random_cpu",
|
|
|
|
|
|
|
|
|
|
# ReduceLogSum
|
|
|
|
|
"test_reduce_log_sum_asc_axes_cpu",
|
|
|
|
|
"test_reduce_log_sum_cpu",
|
|
|
|
|
"test_reduce_log_sum_default_cpu",
|
|
|
|
|
"test_reduce_log_sum_desc_axes_cpu",
|
|
|
|
|
|
|
|
|
|
# ReduceLogSumExp
|
|
|
|
|
"test_reduce_log_sum_exp_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_log_sum_exp_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_log_sum_exp_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_log_sum_exp_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_log_sum_exp_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_log_sum_exp_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_log_sum_exp_negative_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_log_sum_exp_negative_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_log_sum_negative_axes_cpu",
|
|
|
|
|
|
|
|
|
|
# ReduceSumSquare
|
|
|
|
|
"test_reduce_sum_square_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_square_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_sum_square_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_square_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_sum_square_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_square_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_sum_square_negative_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_sum_square_negative_axes_keepdims_random_cpu",
|
|
|
|
|
|
Lower ReduceMean op to Krnl dialect (#318)
* Improve support for krnl.dim (#317)
* Reorganize main function.
* Follow review comments.
* Emit constants are globals in Krnl and LLVM dialects.
* Make krnl dim more robust.
* Format.
* Update comments.
* Change pass name.
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
* Initial Location info support (#302)
* NFC: Attribute cleanup (remove references of attributes) (#286)
* Define krnl.permute op.
* Support krnl.permute operation.
* Properly remove loop references.
* Re-push, Github was down.
* Need to debug interpretOp error.
* Fix lowering bug by erasing ops after full krnl IR interpretation is done, and clean up & comment code.
* Introduce permute, unroll operations.
* More debug.
* Remove std::set.
* krnl.terminate fails to be converted.
* Pass all tests, need to add legal ops as well as part of the conversion target.
* Change test format to new permute spec.
* Bug fix for nested iterate op lowering.
* Simplify error reporting.
* Fix compilation error.
* Increase comments coverage.
* Remove unnecessary imports.
* Re-trigger Jenkins
* Add permute/unroll tests.
* Retrigger Jenkins
* remove & (ref) for Attributes
Co-authored-by: Tian Jin <tjingrant@gmail.com>
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Syntax highlighting for mlir code in README (#276)
* Syntax highlighting for mlir code in README
* Restart Jenkins
Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* use print not dump
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* add semicolon
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* syntax
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* add code to preserve locations
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* format
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Emit the dynamic memory pool (#290)
* Reorganize main function.
* Follow review comments.
* Emit constants are globals in Krnl and LLVM dialects.
* Add support for bundling dynamic memory pools.
* Add dynamic bundling.
* Clean-up code.
* Clean-up file.
* Add test for bundling dynamic memory pool.
* Fixes. Simplify data structure. Add mixed test.
* Remove unused import.
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Fix wrong type for llvm::loadop (#293)
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Update llvm commit ID to 1d01fc1 (#292)
* Fix for LLVM revision D85495
* Fix for LLVM revision DD86121
* Fix for LLVM revision D85622 (f9dc2b7)
TODO: Change preloadDialectsInContext to false
Memo for previous fixes: D86121 (250f43d), D85495 (575b22b)
* clang-format
* Update llvm commit ID of README and clone-mlir.sh
* Updated llvm commit ID of README.md
* Fix for passing backend tests
* Removed the commented code
* Empty commit for triggering rebuild
* Test multi-stage travis build
* Specify stage order.
* Empty commit for triggering rebuild
* Update prereq.s390x.Dockerfile
Make it possible to execute s390x prereq docker multiple times.
* Build prereq for each arch
* Fix multi-arch prereq build.
* timeout at 40m
* Update .travis.yml
* add ppc64le prereq builder
* Run ppc docker prereq build multiple times
* Do not test branch update unless it's mater.
* Fix dockerfile.
* Fix typo in travis.yml.
* Fix ppc64 docker file
* Update .travis.yml
* turn off metacopy on ppc64le
* Update .travis.yml
* Turn off metacopy.
* Turn off metacopy inside Dockerfile in ppc64.
* No sudo in Docker.
* Remove metacopy config from Dockerfile.
* Change base image to be bionic.
* Using newer linux distro for ppc64.
* Turn off metacopy in before_install.
* Fix sudo permission issue.
* Run docker info.
* Allow amd64 docker file to be built multiple times
* Support building amd64 prereq.
* Fix amd64 docker file typo.
* fix ppc64le dockerfile typo.
* timeout from 40m -> 30m
* 40m->30m
* 40m->30m
* fix bug preventing incremental build.
* fix bug preventing incremental build.
* Bump CircleCI cache version.
* Push to production prereq container repository and condition prereq docker rebuild on commit message.
* Rebuild prereq docker.
* Move default script to top-level.
* Python not properly installed.
* amd64 -> x86
* Rebuild prereq docker.
* Rebuild prereq docker.
* Rebuild prereq docker.
* Restart all CI.
* Disallow cache on Jenkins docker build.
* Restart zJenkins.
* Restart zJenkins.
Co-authored-by: Haruki Imai <imaihal@jp.ibm.com>
Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Using onnx-mlir through incremental stages (#257)
* Add lowering of Vector dialect for lower-all-llvm pass
* Fix generating CallOp instructions when return type is void
* Fix lowering of memref
* Reformat using clang-format
* Record more context.
* Reflow comments.
Co-authored-by: Tian Jin <tjingrant@gmail.com>
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Dropout elimination & Conv Bugfix (#297)
* Dropout elimination.
* Test VGG19.
* Add shufflenet.
* Fix grouped convolution bug.
* Fix lit test failure.
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Rewrite shape and size OP (#285)
* add shape inference
* Revert "add shape inference"
This reverts commit f9d42f39e68e14b5648abccfc8617fff00244d16.
* add rewrite rules
* test cases
* format
* add constraint
* response to review
* response to review
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* initial code for handling custom ops (#288)
* initial code for handling custom ops
* format
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* ShapeInference for SizeOp (#299)
* add shape inference
* Revert "add shape inference"
This reverts commit f9d42f39e68e14b5648abccfc8617fff00244d16.
* shape inference
* test case
* format
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Gather ONNX to Kernel Lowering (#294)
* Define krnl.permute op.
* Support krnl.permute operation.
* Properly remove loop references.
* Re-push, Github was down.
* Need to debug interpretOp error.
* Fix lowering bug by erasing ops after full krnl IR interpretation is done, and clean up & comment code.
* Introduce permute, unroll operations.
* More debug.
* Remove std::set.
* krnl.terminate fails to be converted.
* Pass all tests, need to add legal ops as well as part of the conversion target.
* Change test format to new permute spec.
* Bug fix for nested iterate op lowering.
* Simplify error reporting.
* Fix compilation error.
* Increase comments coverage.
* Remove unnecessary imports.
* Re-trigger Jenkins
* Add permute/unroll tests.
* Retrigger Jenkins
* initial implementation of gather
* added tests
* format
* remove affine load for second load, as it uses an indirection
* changes suggested by reviewers
* remove backend tests until I can verify them locally
Co-authored-by: Tian Jin <tjingrant@gmail.com>
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* add lit test
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* fix option spelling
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* braces in wrong place
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* add lit test
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* remove duplicate code from lit test Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* Simplify lit test Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* remove attributes from lit test Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* add onnx-mlir-opt to tool names
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* add printIR to second RUN
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* redo adding printIR
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* fix bug
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* format
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
* fix typo in test
Signed-off-by: Kevin O'Brien <caomhin@us.ibm.com>
Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
Co-authored-by: Tung D. Le <tung@jp.ibm.com>
Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
Co-authored-by: Haruki Imai <imaihal@jp.ibm.com>
Co-authored-by: Kevin Wu <6334443+kwu91@users.noreply.github.com>
Co-authored-by: chentong319 <chentong@us.ibm.com>
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
* Support ReduceMean
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
* Add lit tests
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
* Fix unknown dimensions for type f32
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
Co-authored-by: Kevin O'Brien <caomhin@us.ibm.com>
Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
Co-authored-by: Haruki Imai <imaihal@jp.ibm.com>
Co-authored-by: Kevin Wu <6334443+kwu91@users.noreply.github.com>
Co-authored-by: chentong319 <chentong@us.ibm.com>
2020-10-11 10:09:42 +08:00
|
|
|
# ReduceMean
|
|
|
|
|
"test_reduce_mean_default_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_mean_default_axes_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_mean_do_not_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_mean_do_not_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_mean_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_mean_keepdims_random_cpu",
|
|
|
|
|
"test_reduce_mean_negative_axes_keepdims_example_cpu",
|
|
|
|
|
"test_reduce_mean_negative_axes_keepdims_random_cpu",
|
|
|
|
|
|
2019-12-22 13:25:02 +08:00
|
|
|
# Selu Op:
|
|
|
|
|
"test_selu_cpu",
|
|
|
|
|
"test_selu_default_cpu",
|
|
|
|
|
"test_selu_example_cpu",
|
|
|
|
|
|
|
|
|
|
# Sigmoid Op:
|
|
|
|
|
"test_sigmoid_cpu",
|
|
|
|
|
"test_sigmoid_example_cpu",
|
2020-01-21 01:30:08 +08:00
|
|
|
|
2020-01-21 10:57:32 +08:00
|
|
|
# Softmax Op:
|
|
|
|
|
"test_softmax_axis_0_cpu",
|
|
|
|
|
"test_softmax_axis_1_cpu",
|
|
|
|
|
"test_softmax_axis_2_cpu",
|
|
|
|
|
"test_softmax_default_axis_cpu",
|
|
|
|
|
"test_softmax_example_cpu",
|
|
|
|
|
"test_softmax_large_number_cpu",
|
|
|
|
|
|
2020-01-29 00:10:47 +08:00
|
|
|
# Sqrt Op:
|
|
|
|
|
"test_sqrt_cpu",
|
|
|
|
|
"test_sqrt_example_cpu",
|
|
|
|
|
|
2019-12-22 13:25:02 +08:00
|
|
|
# Sum Op:
|
2020-01-28 21:48:11 +08:00
|
|
|
"test_sum_example_cpu",
|
2019-12-22 13:25:02 +08:00
|
|
|
"test_sum_one_input_cpu",
|
2020-01-28 21:48:11 +08:00
|
|
|
"test_sum_two_inputs_cpu",
|
2019-12-22 13:25:02 +08:00
|
|
|
|
2020-01-29 23:46:02 +08:00
|
|
|
# Unsqueeze Op:
|
|
|
|
|
"test_unsqueeze_axis_0_cpu",
|
|
|
|
|
"test_unsqueeze_axis_1_cpu",
|
|
|
|
|
"test_unsqueeze_axis_2_cpu",
|
|
|
|
|
"test_unsqueeze_axis_3_cpu",
|
|
|
|
|
"test_unsqueeze_negative_axes_cpu",
|
|
|
|
|
"test_unsqueeze_three_axes_cpu",
|
|
|
|
|
"test_unsqueeze_two_axes_cpu",
|
2020-01-31 00:44:56 +08:00
|
|
|
# "test_unsqueeze_unsorted_axes_cpu",
|
2020-01-29 23:46:02 +08:00
|
|
|
|
2019-12-22 13:25:02 +08:00
|
|
|
# Reciprocal Op:
|
2020-01-22 10:41:22 +08:00
|
|
|
"test_reciprocal_cpu",
|
|
|
|
|
"test_reciprocal_example_cpu",
|
2020-01-24 12:18:38 +08:00
|
|
|
|
|
|
|
|
# SoftplusOp:
|
|
|
|
|
"test_softplus_cpu",
|
|
|
|
|
"test_softplus_example_cpu",
|
|
|
|
|
|
|
|
|
|
# SoftsignOp:
|
|
|
|
|
"test_softsign_cpu",
|
|
|
|
|
"test_softsign_example_cpu",
|
2020-01-28 23:21:08 +08:00
|
|
|
|
|
|
|
|
# ReshapeOp:
|
2020-01-29 23:41:09 +08:00
|
|
|
"test_reshape_extended_dims_cpu",
|
2020-02-11 23:37:47 +08:00
|
|
|
"test_reshape_negative_dim_cpu",
|
|
|
|
|
"test_reshape_negative_extended_dims_cpu",
|
2020-01-29 23:41:09 +08:00
|
|
|
"test_reshape_one_dim_cpu",
|
|
|
|
|
"test_reshape_reduced_dims_cpu",
|
2020-01-28 23:21:08 +08:00
|
|
|
"test_reshape_reordered_all_dims_cpu",
|
2020-01-29 23:41:09 +08:00
|
|
|
"test_reshape_reordered_last_dims_cpu",
|
2020-02-11 23:37:47 +08:00
|
|
|
"test_reshape_zero_and_negative_dim_cpu",
|
2020-01-29 23:41:09 +08:00
|
|
|
"test_reshape_zero_dim_cpu",
|
2020-01-31 00:44:56 +08:00
|
|
|
|
|
|
|
|
# Transpose
|
|
|
|
|
"test_transpose_default_cpu",
|
|
|
|
|
"test_transpose_all_permutations_0_cpu",
|
|
|
|
|
"test_transpose_all_permutations_1_cpu",
|
|
|
|
|
"test_transpose_all_permutations_2_cpu",
|
|
|
|
|
"test_transpose_all_permutations_3_cpu",
|
|
|
|
|
"test_transpose_all_permutations_4_cpu",
|
|
|
|
|
"test_transpose_all_permutations_5_cpu",
|
2020-02-04 22:27:17 +08:00
|
|
|
|
2020-02-08 05:51:32 +08:00
|
|
|
# Conv
|
|
|
|
|
"test_basic_conv_without_padding_cpu",
|
2020-02-12 00:53:13 +08:00
|
|
|
"test_conv_with_strides_no_padding_cpu",
|
2020-02-08 05:51:32 +08:00
|
|
|
|
2020-02-04 22:27:17 +08:00
|
|
|
# Sign Op:
|
|
|
|
|
"test_sign_cpu",
|
2020-02-14 23:43:17 +08:00
|
|
|
|
|
|
|
|
# MatmulOp
|
|
|
|
|
"test_matmul_2d_cpu",
|
|
|
|
|
"test_matmul_3d_cpu",
|
|
|
|
|
"test_matmul_4d_cpu",
|
|
|
|
|
|
2020-02-21 00:45:40 +08:00
|
|
|
# BatchNormalization (test mode)
|
|
|
|
|
"test_batchnorm_epsilon_cpu",
|
|
|
|
|
"test_batchnorm_example_cpu",
|
|
|
|
|
|
2020-04-19 21:39:34 +08:00
|
|
|
# MaxPoolSingleOut
|
2020-03-05 03:27:21 +08:00
|
|
|
"test_maxpool_1d_default_cpu",
|
|
|
|
|
"test_maxpool_2d_ceil_cpu",
|
|
|
|
|
"test_maxpool_2d_default_cpu",
|
2020-03-18 21:55:50 +08:00
|
|
|
"test_maxpool_2d_dilations_cpu",
|
|
|
|
|
"test_maxpool_2d_pads_cpu",
|
|
|
|
|
"test_maxpool_2d_precomputed_pads_cpu",
|
|
|
|
|
"test_maxpool_2d_precomputed_same_upper_cpu",
|
|
|
|
|
"test_maxpool_2d_precomputed_strides_cpu",
|
|
|
|
|
"test_maxpool_2d_same_lower_cpu",
|
|
|
|
|
"test_maxpool_2d_same_upper_cpu",
|
2020-03-05 03:27:21 +08:00
|
|
|
"test_maxpool_2d_strides_cpu",
|
|
|
|
|
"test_maxpool_3d_default_cpu",
|
|
|
|
|
|
2020-04-19 21:39:34 +08:00
|
|
|
# AveragePool
|
|
|
|
|
"test_averagepool_1d_default_cpu",
|
|
|
|
|
"test_averagepool_2d_ceil_cpu",
|
|
|
|
|
"test_averagepool_2d_default_cpu",
|
|
|
|
|
"test_averagepool_2d_pads_count_include_pad_cpu",
|
|
|
|
|
"test_averagepool_2d_pads_cpu",
|
|
|
|
|
"test_averagepool_2d_precomputed_pads_count_include_pad_cpu",
|
|
|
|
|
"test_averagepool_2d_precomputed_pads_cpu",
|
|
|
|
|
"test_averagepool_2d_precomputed_same_upper_cpu",
|
|
|
|
|
"test_averagepool_2d_precomputed_strides_cpu",
|
|
|
|
|
"test_averagepool_2d_same_lower_cpu",
|
|
|
|
|
"test_averagepool_2d_same_upper_cpu",
|
|
|
|
|
"test_averagepool_2d_strides_cpu",
|
|
|
|
|
"test_averagepool_3d_default_cpu",
|
|
|
|
|
|
2020-05-13 21:08:06 +08:00
|
|
|
# LSTM
|
|
|
|
|
"test_lstm_defaults_cpu",
|
|
|
|
|
"test_lstm_with_initial_bias_cpu",
|
|
|
|
|
"test_lstm_with_peepholes_cpu",
|
|
|
|
|
|
2020-07-03 16:26:41 +08:00
|
|
|
# Squeeze
|
|
|
|
|
"test_squeeze_cpu",
|
|
|
|
|
"test_squeeze_negative_axes_cpu",
|
|
|
|
|
|
2020-06-11 10:57:20 +08:00
|
|
|
# Split
|
|
|
|
|
"test_split_equal_parts_1d_cpu",
|
|
|
|
|
"test_split_equal_parts_2d_cpu",
|
|
|
|
|
"test_split_equal_parts_default_axis_cpu",
|
|
|
|
|
"test_split_variable_parts_1d_cpu",
|
|
|
|
|
"test_split_variable_parts_2d_cpu",
|
|
|
|
|
"test_split_variable_parts_default_axis_cpu",
|
2020-10-05 12:50:59 +08:00
|
|
|
|
|
|
|
|
# Tile
|
|
|
|
|
"test_tile_cpu",
|
|
|
|
|
"test_tile_precomputed_cpu",
|
|
|
|
|
|
2020-09-20 00:47:39 +08:00
|
|
|
# ConstantOfShape
|
|
|
|
|
"test_constantofshape_float_ones_cpu",
|
2020-09-21 17:55:21 +08:00
|
|
|
|
|
|
|
|
# Size
|
|
|
|
|
# TODO(tjingrant): fix unit test for size ops.
|
|
|
|
|
# "test_size_cpu",
|
|
|
|
|
# "test_size_example_cpu",
|
|
|
|
|
|
2020-09-20 00:47:39 +08:00
|
|
|
# Error:
|
|
|
|
|
# Items are not equal:
|
|
|
|
|
# ACTUAL: dtype('int32')
|
|
|
|
|
# DESIRED: dtype('uint8')
|
|
|
|
|
# In this test, 'int32' was specified for value attribute as in
|
|
|
|
|
# onnx/onnx/backend/test/case/node/constantofshape.py
|
|
|
|
|
# and onnx-mlir correctly imported and converted the model.
|
|
|
|
|
# It is unknown why 'uint8' came from.
|
|
|
|
|
#"test_constantofshape_int_zeros_cpu",
|
|
|
|
|
|
2020-09-10 14:47:30 +08:00
|
|
|
# Model
|
Compiling Models with Large Constant Arrays (#146)
* PoC works.
* MNist works.
* Clean up.
* Fix test.
* Make Linux work.
* Use consistent symbol name.
* Fix variable name.
* Fix array addr access.
* Bug fix.
* Bug fix.
* install before running e2e tests.
* Fix build config.
* Use sudo when installing.
* Make embeddedDataLoader position independent.
* Enable ResNet50.
* Format code.
* Format MainUtil.
* Try not using sudo to install.
* Supply runtime dir via environment variable.
* Dump problematic operation.
* Dump entire function.
* Debug.
* Dump input.
* Dump constant op.
* Debug.
* Debug.
* Debug.
* Print to stderr.
* take care of endianness.
* Use endianness-aware execution session.
* Fix ZLinux error.
* Include warning when desired output endianness can't be deduced.
* Remove debug code.
* Remove debug code in shape inference.
* Support binary-decoder for testing constants packing.
* Support filename, move-to-file, elision-threshold configurations in constant packing pass for easy testing.
* Add lit test, fix lit test type mismatch.
* Add more consts packing tests.
* Ensure intermediate files are properly cleaned up.
* No need for constant elimination.
* Link with threading libraries.
* Remove debug code.
* Format code.
* More tests.
* test nit.
* Remove debug code.
* Reduce hard-coded constants.
* Use temporary and unique working directory for hosting model parameters.
* Test if it works.
* Try to find objcopy.
* Rename symbols using objcopy.
* Move sanitized name to linux section.
* Use verbose mode for debugging.
* Disambiguate pass constructor.
* Fix symbol name.
* Use Command API to build and execute commands.
* Move linux to use Command API.
* Fix reset args.
* Execute redefine sym.
* Format code.
* Do not use verbose mode for CircleCI.
* Remove debug code.
* Prettify code, add comments.
* getSegmentData -> getEmbeddedConstPool
* vector -> std::vector.
* Make sure we properly clean up intermediate files.
* Fix test cases.
* Add runtime directory.
* Trigger rebuild.
* [Merge with master] fix debug script.
* Diable affine fusion pass for now.
* Support generic fallback const packing mechanism.
* Remove debug code.
* Handle the case where objcopy is not available.
* Fix Windows missing types.
* Support int64.
* Copy packed constant to a local directory for non-Linux/Mac platforms.
* Nit: remove debug code, refactor const pack preprocessing out as a separate function.
* Cannot make preprocessConstPack a standalone function because file removers are stack-allocated, and they are deallocated prematurely when function stack gets popped, deleteing intermediate files too early.
* Don't require executable filename.
* Import ONNX data types directly.
* Fix LIT test.
* Bug fix, use moved string value.
* Remove redundant filenames.
* Fix CMake script.
* Embed endianness information as a symbol, and check during runtime.
* More comments, update lit tests.
* Fix lit test on BE machine.
* Copyright notices.
2020-06-12 10:27:05 +08:00
|
|
|
"test_resnet50_cpu",
|
2020-09-10 14:47:30 +08:00
|
|
|
"test_vgg19_cpu",
|
|
|
|
|
"test_shufflenet_cpu",
|
2019-12-22 13:25:02 +08:00
|
|
|
]
|
|
|
|
|
|
|
|
|
|
# Extract name of all test cases.
|
|
|
|
|
import inspect
|
Compiling Models with Large Constant Arrays (#146)
* PoC works.
* MNist works.
* Clean up.
* Fix test.
* Make Linux work.
* Use consistent symbol name.
* Fix variable name.
* Fix array addr access.
* Bug fix.
* Bug fix.
* install before running e2e tests.
* Fix build config.
* Use sudo when installing.
* Make embeddedDataLoader position independent.
* Enable ResNet50.
* Format code.
* Format MainUtil.
* Try not using sudo to install.
* Supply runtime dir via environment variable.
* Dump problematic operation.
* Dump entire function.
* Debug.
* Dump input.
* Dump constant op.
* Debug.
* Debug.
* Debug.
* Print to stderr.
* take care of endianness.
* Use endianness-aware execution session.
* Fix ZLinux error.
* Include warning when desired output endianness can't be deduced.
* Remove debug code.
* Remove debug code in shape inference.
* Support binary-decoder for testing constants packing.
* Support filename, move-to-file, elision-threshold configurations in constant packing pass for easy testing.
* Add lit test, fix lit test type mismatch.
* Add more consts packing tests.
* Ensure intermediate files are properly cleaned up.
* No need for constant elimination.
* Link with threading libraries.
* Remove debug code.
* Format code.
* More tests.
* test nit.
* Remove debug code.
* Reduce hard-coded constants.
* Use temporary and unique working directory for hosting model parameters.
* Test if it works.
* Try to find objcopy.
* Rename symbols using objcopy.
* Move sanitized name to linux section.
* Use verbose mode for debugging.
* Disambiguate pass constructor.
* Fix symbol name.
* Use Command API to build and execute commands.
* Move linux to use Command API.
* Fix reset args.
* Execute redefine sym.
* Format code.
* Do not use verbose mode for CircleCI.
* Remove debug code.
* Prettify code, add comments.
* getSegmentData -> getEmbeddedConstPool
* vector -> std::vector.
* Make sure we properly clean up intermediate files.
* Fix test cases.
* Add runtime directory.
* Trigger rebuild.
* [Merge with master] fix debug script.
* Diable affine fusion pass for now.
* Support generic fallback const packing mechanism.
* Remove debug code.
* Handle the case where objcopy is not available.
* Fix Windows missing types.
* Support int64.
* Copy packed constant to a local directory for non-Linux/Mac platforms.
* Nit: remove debug code, refactor const pack preprocessing out as a separate function.
* Cannot make preprocessConstPack a standalone function because file removers are stack-allocated, and they are deallocated prematurely when function stack gets popped, deleteing intermediate files too early.
* Don't require executable filename.
* Import ONNX data types directly.
* Fix LIT test.
* Bug fix, use moved string value.
* Remove redundant filenames.
* Fix CMake script.
* Embed endianness information as a symbol, and check during runtime.
* More comments, update lit tests.
* Fix lit test on BE machine.
* Copyright notices.
2020-06-12 10:27:05 +08:00
|
|
|
all_tests = []
|
|
|
|
|
all_tests += inspect.getmembers(
|
|
|
|
|
backend_test.test_cases["OnnxBackendRealModelTest"])
|
|
|
|
|
all_tests += inspect.getmembers(
|
2019-12-22 13:25:02 +08:00
|
|
|
backend_test.test_cases["OnnxBackendNodeModelTest"])
|
|
|
|
|
all_test_names = list(map(lambda x: x[0], all_tests))
|
2020-01-21 01:30:08 +08:00
|
|
|
|
|
|
|
|
# Ensure that test names specified in test_to_enable actually exist.
|
2019-12-22 13:25:02 +08:00
|
|
|
for test_name in test_to_enable:
|
2020-01-31 00:44:56 +08:00
|
|
|
assert test_name in all_test_names, """test name {} not found, it is likely
|
|
|
|
|
that you may have misspelled the test name or the specified test does not
|
Compiling Models with Large Constant Arrays (#146)
* PoC works.
* MNist works.
* Clean up.
* Fix test.
* Make Linux work.
* Use consistent symbol name.
* Fix variable name.
* Fix array addr access.
* Bug fix.
* Bug fix.
* install before running e2e tests.
* Fix build config.
* Use sudo when installing.
* Make embeddedDataLoader position independent.
* Enable ResNet50.
* Format code.
* Format MainUtil.
* Try not using sudo to install.
* Supply runtime dir via environment variable.
* Dump problematic operation.
* Dump entire function.
* Debug.
* Dump input.
* Dump constant op.
* Debug.
* Debug.
* Debug.
* Print to stderr.
* take care of endianness.
* Use endianness-aware execution session.
* Fix ZLinux error.
* Include warning when desired output endianness can't be deduced.
* Remove debug code.
* Remove debug code in shape inference.
* Support binary-decoder for testing constants packing.
* Support filename, move-to-file, elision-threshold configurations in constant packing pass for easy testing.
* Add lit test, fix lit test type mismatch.
* Add more consts packing tests.
* Ensure intermediate files are properly cleaned up.
* No need for constant elimination.
* Link with threading libraries.
* Remove debug code.
* Format code.
* More tests.
* test nit.
* Remove debug code.
* Reduce hard-coded constants.
* Use temporary and unique working directory for hosting model parameters.
* Test if it works.
* Try to find objcopy.
* Rename symbols using objcopy.
* Move sanitized name to linux section.
* Use verbose mode for debugging.
* Disambiguate pass constructor.
* Fix symbol name.
* Use Command API to build and execute commands.
* Move linux to use Command API.
* Fix reset args.
* Execute redefine sym.
* Format code.
* Do not use verbose mode for CircleCI.
* Remove debug code.
* Prettify code, add comments.
* getSegmentData -> getEmbeddedConstPool
* vector -> std::vector.
* Make sure we properly clean up intermediate files.
* Fix test cases.
* Add runtime directory.
* Trigger rebuild.
* [Merge with master] fix debug script.
* Diable affine fusion pass for now.
* Support generic fallback const packing mechanism.
* Remove debug code.
* Handle the case where objcopy is not available.
* Fix Windows missing types.
* Support int64.
* Copy packed constant to a local directory for non-Linux/Mac platforms.
* Nit: remove debug code, refactor const pack preprocessing out as a separate function.
* Cannot make preprocessConstPack a standalone function because file removers are stack-allocated, and they are deallocated prematurely when function stack gets popped, deleteing intermediate files too early.
* Don't require executable filename.
* Import ONNX data types directly.
* Fix LIT test.
* Bug fix, use moved string value.
* Remove redundant filenames.
* Fix CMake script.
* Embed endianness information as a symbol, and check during runtime.
* More comments, update lit tests.
* Fix lit test on BE machine.
* Copyright notices.
2020-06-12 10:27:05 +08:00
|
|
|
exist in the version of onnx package you installed.""".format(test_name)
|
2019-12-22 13:25:02 +08:00
|
|
|
backend_test.include(r"^{}$".format(test_name))
|
|
|
|
|
|
|
|
|
|
# import all test cases at global scope to make them visible to python.unittest
|
|
|
|
|
globals().update(backend_test.test_cases)
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
unittest.main()
|
