mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-26 22:35:43 +00:00
4f2096be38
### Description
<!-- Describe your changes. -->
Update XNNPACK to latest version
- adds fp16 kernels and various other improvements
- requires pthreadpool update as well
Most code updates in the XNNPACK EP are to adjust to the new XNNPACK API
- 'setup' is split into 'reshape' and 'setup'
- some ops use a workspace buffer
- copied workspace allocation from XNNPACK unit test code
- some suffixes changed
Added wrapper for XNNPACK caches to base XNNPACK EP kernel
- simplifies usage
- XNNPACK split out the code and weights caches, but the code cache
isn't currently usable via the public API
- we could use the internal types if we think it's required for
performance reasons. non-trivial though as we'd need to propagate ifdef
values from the XNNPACK build up to the ORT build.
- using XNNPACK internals would also mean we would not be able to
support using a pre-build XNNPACK package
- not an issue currently
Fixed opset registration for internal NHWC domain
- was not being tied to the ONNX version, so nodes inserted by layout
transformation had the incorrect opset
- a number of other places needed updating once this issue was fixed
Remove support for NCHW Resize from XNNPACK EP so it's NHWC only
- we only supported NCHW for fp32,
- doing so adds complexity in multiple places (XNNPACK EP kernel
implementation, layout transformation and transpose optimization)
- unclear if that complexity provides any benefit. can add back if
required by production scenario
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
We're looking at enabling fp16 support for CoreML and NNAPI. If we do
that we need a good fallback story if the CPU EP will be used. The
XNNPACK fp16 kernels will hopefully provide that.
NOTE: This PR doesn't add fp16 support to the XNNPACK EP kernels. That
can be done as required in separate EPs and should be relatively simple
to do.
39 lines
1.8 KiB
CMake
39 lines
1.8 KiB
CMake
# Copyright (c) Microsoft Corporation. All rights reserved.
|
|
# Licensed under the MIT License.
|
|
|
|
add_compile_definitions(USE_XNNPACK=1)
|
|
|
|
file(GLOB_RECURSE onnxruntime_providers_xnnpack_cc_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_INCLUDE_DIR}/core/providers/xnnpack/*.h"
|
|
"${ONNXRUNTIME_ROOT}/core/providers/xnnpack/*.h"
|
|
"${ONNXRUNTIME_ROOT}/core/providers/xnnpack/*.cc"
|
|
# utils for handling QDQ models
|
|
"${ONNXRUNTIME_ROOT}/core/providers/shared/node_unit/node_unit.h"
|
|
"${ONNXRUNTIME_ROOT}/core/providers/shared/node_unit/node_unit.cc"
|
|
)
|
|
|
|
source_group(TREE ${REPO_ROOT} FILES ${onnxruntime_providers_xnnpack_cc_srcs})
|
|
onnxruntime_add_static_library(onnxruntime_providers_xnnpack ${onnxruntime_providers_xnnpack_cc_srcs})
|
|
onnxruntime_add_include_to_target(onnxruntime_providers_xnnpack
|
|
onnxruntime_common onnxruntime_framework onnx onnx_proto ${PROTOBUF_LIB} XNNPACK pthreadpool
|
|
flatbuffers::flatbuffers Boost::mp11 safeint_interface
|
|
)
|
|
|
|
add_dependencies(onnxruntime_providers_xnnpack onnx ${onnxruntime_EXTERNAL_DEPENDENCIES})
|
|
set_target_properties(onnxruntime_providers_xnnpack PROPERTIES FOLDER "ONNXRuntime")
|
|
|
|
set_target_properties(onnxruntime_providers_xnnpack PROPERTIES LINKER_LANGUAGE CXX)
|
|
|
|
if (NOT onnxruntime_BUILD_SHARED_LIB)
|
|
install(TARGETS onnxruntime_providers_xnnpack
|
|
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
|
|
FRAMEWORK DESTINATION ${CMAKE_INSTALL_BINDIR})
|
|
endif()
|
|
|
|
# TODO fix shorten-64-to-32 warnings
|
|
# there are some in builds where sizeof(size_t) != sizeof(int64_t), e.g., in 'ONNX Runtime Web CI Pipeline'
|
|
if (HAS_SHORTEN_64_TO_32 AND NOT CMAKE_SIZEOF_VOID_P EQUAL 8)
|
|
target_compile_options(onnxruntime_providers_xnnpack PRIVATE -Wno-error=shorten-64-to-32)
|
|
endif()
|