saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-18 21:21:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/cmake/onnxruntime_codegen_tvm.cmake

26 lines
1.4 KiB
CMake
Raw Normal View History

Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
Implementation of TVM codegen library (#888) Description: This change adds the common part of TVM based codegen library. It includes following parts: * Microsoft TVM Inventory (MTI): a set of TVM ops for neural networks, similar to TOPI * Compiler pass for traversing ONNX graph and generate TVM ops * Compiler pass for traversing generated graph and specify TVM schedule * Compiler pass for handling weight layout * Utils for debugging Motivation and Context: TVM is an open deep learning compiler stack for cpu, gpu and specialized accelerators. To leverage it in ONNX, we built an execution provider named Nuphar. Currently, Nuphar gets good performance on CPUs with AVX2 on quantized LSTM models. This codegen library was part of Nuphar execution provider. It is split out for sharing with other execution providers, as we'd like to reuse TVM in more devices.
2019-07-03 17:32:59 +00:00
file(GLOB_RECURSE onnxruntime_codegen_common_srcs
"${ONNXRUNTIME_ROOT}/core/codegen/common/*.h"
"${ONNXRUNTIME_ROOT}/core/codegen/common/*.cc"
)
make builds more robust (#906) (#932)
2019-04-29 19:58:20 +00:00
file(GLOB_RECURSE onnxruntime_codegen_tvm_srcs CONFIGURE_DEPENDS
Implementation of TVM codegen library (#888) Description: This change adds the common part of TVM based codegen library. It includes following parts: * Microsoft TVM Inventory (MTI): a set of TVM ops for neural networks, similar to TOPI * Compiler pass for traversing ONNX graph and generate TVM ops * Compiler pass for traversing generated graph and specify TVM schedule * Compiler pass for handling weight layout * Utils for debugging Motivation and Context: TVM is an open deep learning compiler stack for cpu, gpu and specialized accelerators. To leverage it in ONNX, we built an execution provider named Nuphar. Currently, Nuphar gets good performance on CPUs with AVX2 on quantized LSTM models. This codegen library was part of Nuphar execution provider. It is split out for sharing with other execution providers, as we'd like to reuse TVM in more devices.
2019-07-03 17:32:59 +00:00
"${ONNXRUNTIME_ROOT}/core/codegen/mti/*.h"
"${ONNXRUNTIME_ROOT}/core/codegen/mti/*.cc"
"${ONNXRUNTIME_ROOT}/core/codegen/passes/*.h"
"${ONNXRUNTIME_ROOT}/core/codegen/passes/*.cc"
Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
)
Implementation of TVM codegen library (#888) Description: This change adds the common part of TVM based codegen library. It includes following parts: * Microsoft TVM Inventory (MTI): a set of TVM ops for neural networks, similar to TOPI * Compiler pass for traversing ONNX graph and generate TVM ops * Compiler pass for traversing generated graph and specify TVM schedule * Compiler pass for handling weight layout * Utils for debugging Motivation and Context: TVM is an open deep learning compiler stack for cpu, gpu and specialized accelerators. To leverage it in ONNX, we built an execution provider named Nuphar. Currently, Nuphar gets good performance on CPUs with AVX2 on quantized LSTM models. This codegen library was part of Nuphar execution provider. It is split out for sharing with other execution providers, as we'd like to reuse TVM in more devices.
2019-07-03 17:32:59 +00:00
source_group(TREE ${ONNXRUNTIME_ROOT}/core FILES ${onnxruntime_codegen_common_srcs} ${onnxruntime_codegen_tvm_srcs})
Build system upgrades (#281) * update * runas normal user
2019-01-07 21:15:24 +00:00
#onnxruntime_codegen_tvm depends on onnxruntime framework
Add static code analyzer to Windows CPU/GPU CI builds and fix the warnings (#7489)
2021-04-29 18:54:57 +00:00
onnxruntime_add_static_library(onnxruntime_codegen_tvm ${onnxruntime_codegen_common_srcs} ${onnxruntime_codegen_tvm_srcs})
Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
set_target_properties(onnxruntime_codegen_tvm PROPERTIES FOLDER "ONNXRuntime")
Implementation of TVM codegen library (#888) Description: This change adds the common part of TVM based codegen library. It includes following parts: * Microsoft TVM Inventory (MTI): a set of TVM ops for neural networks, similar to TOPI * Compiler pass for traversing ONNX graph and generate TVM ops * Compiler pass for traversing generated graph and specify TVM schedule * Compiler pass for handling weight layout * Utils for debugging Motivation and Context: TVM is an open deep learning compiler stack for cpu, gpu and specialized accelerators. To leverage it in ONNX, we built an execution provider named Nuphar. Currently, Nuphar gets good performance on CPUs with AVX2 on quantized LSTM models. This codegen library was part of Nuphar execution provider. It is split out for sharing with other execution providers, as we'd like to reuse TVM in more devices.
2019-07-03 17:32:59 +00:00
target_include_directories(onnxruntime_codegen_tvm PRIVATE ${ONNXRUNTIME_ROOT} ${TVM_INCLUDES} ${MKLML_INCLUDE_DIR} ${eigen_INCLUDE_DIRS})
Use target name for flatbuffers (#13991) ### Description Use target name for flatbuffers. Add version range for flatbuffers. It is similar to #13870 ### Motivation and Context To fix a build error: ``` CMake Error at onnxruntime_graph.cmake:88 (add_dependencies): The dependency target "flatbuffers" of target "onnxruntime_graph" does not exist. Call Stack (most recent call first): CMakeLists.txt:1490 (include) ``` It happens when flatbuffers library is already installed. For example, on Ubuntu people may get it from apt-get. But, the one provided by Ubuntu 20.04 is not compatible with our code. The one in Ubuntu 22.04 works fine.
2022-12-20 19:44:02 +00:00
onnxruntime_add_include_to_target(onnxruntime_codegen_tvm onnxruntime_common onnxruntime_framework onnx onnx_proto ${PROTOBUF_LIB} flatbuffers::flatbuffers safeint_interface Boost::mp11)
Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
target_compile_options(onnxruntime_codegen_tvm PRIVATE ${DISABLED_WARNINGS_FOR_TVM})
# need onnx to build to create headers that this project includes
Build system upgrades (#281) * update * runas normal user
2019-01-07 21:15:24 +00:00
add_dependencies(onnxruntime_codegen_tvm ${onnxruntime_EXTERNAL_DEPENDENCIES})
Reference in a new issue Copy permalink