[onnx,onnxruntime] new port for v1.19.2 with onnx 1.16.0

ports/libtorch/fix-build.patch

@@ -50,13 +50,15 @@ index b46a444..255d7f4 100644
 -    endif()
 -    set_property(TARGET onnx_proto PROPERTY IMPORTED_LOCATION ${ONNX_PROTO_LIBRARY})
 -    message("-- Found onnx: ${ONNX_LIBRARY} ${ONNX_PROTO_LIBRARY}")
+-    list(APPEND Caffe2_DEPENDENCY_LIBS onnx_proto onnx)
 +    find_package(ONNX REQUIRED)
-+    set(ONNX_LIBRARY onnx)
-+    set(ONNX_PROTO_LIBRARY onnx_proto)
++    set(ONNX_LIBRARY ONNX::onnx)
++    set(ONNX_PROTO_LIBRARY ONNX::onnx_proto)
 +    message("-- Found onnx")
-     list(APPEND Caffe2_DEPENDENCY_LIBS onnx_proto onnx)
++    list(APPEND Caffe2_DEPENDENCY_LIBS ONNX::onnx_proto ONNX::onnx)
    endif()
    include_directories(${FOXI_INCLUDE_DIRS})
+   list(APPEND Caffe2_DEPENDENCY_LIBS "${FOXI_LOADER_LIBPATH}")
 diff --git a/pyproject.toml b/pyproject.toml
 index eb764cb..c70f317 100644
 --- a/pyproject.toml

ports/libtorch/vcpkg.json

@@ -1,7 +1,7 @@
 {
   "name": "libtorch",
   "version": "2.1.2",
-  "port-version": 6,
+  "port-version": 7,
   "description": "Tensors and Dynamic neural networks in Python with strong GPU acceleration",
   "homepage": "https://pytorch.org/",
   "license": null,

ports/onnx-optimizer/portfile.cmake

@@ -30,6 +30,7 @@ vcpkg_cmake_configure(
     OPTIONS
         ${FEATURE_OPTIONS}
         -DONNX_USE_MSVC_STATIC_RUNTIME=${USE_STATIC_RUNTIME}
+        -DONNX_TARGET_NAME=ONNX::onnx # after 1.16.0
 )
 if("pybind11" IN_LIST FEATURES)
     # This target is not in install/export

ports/onnx-optimizer/vcpkg.json

@@ -1,6 +1,7 @@
 {
   "name": "onnx-optimizer",
   "version-semver": "0.3.18",
+  "port-version": 1,
   "description": "Actively maintained ONNX Optimizer",
   "homepage": "https://github.com/onnx/optimizer",
   "license": "Apache-2.0",

ports/onnx/fix-cmakelists.patch

@@ -1,10 +1,18 @@
 diff --git a/CMakeLists.txt b/CMakeLists.txt
-index 4dd56b6..2ff3e29 100644
+index 6d7ca84..b72646f 100644
 --- a/CMakeLists.txt
 +++ b/CMakeLists.txt
-@@ -65,6 +65,27 @@ endif()
+@@ -129,6 +129,7 @@ if(ONNX_BUILD_TESTS)
+   endif()
+ endif()
 
- include(GNUInstallDirs)
++find_package(protobuf CONFIG REQUIRED)
+ if((ONNX_USE_LITE_PROTO AND TARGET protobuf::libprotobuf-lite) OR ((NOT ONNX_USE_LITE_PROTO) AND TARGET protobuf::libprotobuf))
+   # Sometimes we need to use protoc compiled for host architecture while linking
+   # libprotobuf against target architecture. See https://github.com/caffe2/caffe
+@@ -711,6 +712,27 @@ install(DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/onnx
+         FILES_MATCHING
+         PATTERN "*.h")
 
 +# install protobuf files
 +install(FILES ${CMAKE_CURRENT_BINARY_DIR}/onnx/onnx-data.proto
@@ -27,41 +35,22 @@ index 4dd56b6..2ff3e29 100644
 +  )
 +endif()
 +
- set(ONNX_ROOT ${PROJECT_SOURCE_DIR})
-
- # Read ONNX version
-@@ -116,7 +137,8 @@ endif()
- # find_package Python has replaced PythonInterp and PythonLibs since cmake 3.12
- # Use the following command in the future; now this is only compatible with the latest pybind11
- # find_package(Python ${PY_VERSION} COMPONENTS Interpreter Development REQUIRED)
--find_package(PythonInterp ${PY_VERSION} REQUIRED)
-+find_package(Python3 ${PY_VERSION} COMPONENTS Interpreter REQUIRED)
-+set(PYTHON_EXECUTABLE ${Python3_EXECUTABLE})
- if(BUILD_ONNX_PYTHON)
-   find_package(PythonLibs ${PY_VERSION})
- endif()
-@@ -434,6 +456,7 @@ target_link_libraries(onnx PUBLIC onnx_proto)
- add_onnx_global_defines(onnx)
+ configure_file(
+   ${PROJECT_SOURCE_DIR}/cmake/ONNXConfigVersion.cmake.in
+   ${PROJECT_BINARY_DIR}/ONNXConfigVersion.cmake
+diff --git a/cmake/ONNXConfig.cmake.in b/cmake/ONNXConfig.cmake.in
+index d588f8a..dbd4398 100644
+--- a/cmake/ONNXConfig.cmake.in
++++ b/cmake/ONNXConfig.cmake.in
+@@ -6,9 +6,8 @@
+ # library version information
+ set(ONNX_VERSION "@ONNX_VERSION@")
 
- if(BUILD_ONNX_PYTHON)
-+  find_package(Python3 ${PY_VERSION} COMPONENTS Development REQUIRED)
-   if("${PY_EXT_SUFFIX}" STREQUAL "")
-     if(MSVC)
-       set(PY_EXT_SUFFIX ".pyd")
-@@ -452,10 +475,14 @@ if(BUILD_ONNX_PYTHON)
-   target_include_directories(onnx_cpp2py_export PRIVATE
-                              $<BUILD_INTERFACE:${ONNX_ROOT}>
-                              $<BUILD_INTERFACE:${CMAKE_CURRENT_BINARY_DIR}>
--                             $<INSTALL_INTERFACE:include>)
-+                             ${Python3_INCLUDE_DIRS})
-+  target_link_directories(onnx_cpp2py_export PRIVATE
-+                          ${Python3_LIBRARY_DIRS})
-+  target_link_libraries(onnx_cpp2py_export PRIVATE
-+                        ${Python3_LIBRARIES})
+-list(APPEND CMAKE_PREFIX_PATH "@PROTOBUF_DIR@")
+-set(Protobuf_INCLUDE_DIR "@PROTOBUF_INCLUDE_DIR@")
+-find_package(Protobuf REQUIRED)
++include(CMakeFindDependencyMacro)
++find_dependency(protobuf CONFIG)
 
-   # pybind11 is a header only lib
--  find_package(pybind11 2.2 CONFIG)
-+  find_package(pybind11 2.2 CONFIG REQUIRED)
-   if(NOT pybind11_FOUND)
-     if(EXISTS "${ONNX_ROOT}/third_party/pybind11/include/pybind11/pybind11.h")
-       add_subdirectory("${ONNX_ROOT}/third_party/pybind11")
+ # import targets
+ include ("${CMAKE_CURRENT_LIST_DIR}/ONNXTargets.cmake")

ports/onnx/portfile.cmake

@@ -4,10 +4,9 @@ vcpkg_from_github(
     OUT_SOURCE_PATH SOURCE_PATH
     REPO onnx/onnx
     REF "v${VERSION}"
-    SHA512 b46a4ab70af88053318eba45251c1f71528f15e45a33042877570e8d857febd3ec66e2e811fcda2105a4f17b84c9a1c6a0aaa22756c3287321b3ea29e83127fd
+    SHA512 ef641447d8d6c4ed9f083793fe14a8568d6aa7b9b7e7b859a4082e9b892acd801230da2027d097ceaa0d68bbd37b2422b89bb7d1d55d5c3b5955c0f9c7c657c5
     PATCHES
         fix-cmakelists.patch
-        fix-dependency-protobuf.patch
 )
 
 string(COMPARE EQUAL "${VCPKG_CRT_LINKAGE}" "static" USE_STATIC_RUNTIME)
@@ -64,10 +63,6 @@ vcpkg_cmake_install()
 vcpkg_cmake_config_fixup(CONFIG_PATH lib/cmake/ONNX)
 
 vcpkg_install_copyright(FILE_LIST "${SOURCE_PATH}/LICENSE")
-vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/share/${PORT}/ONNXConfig.cmake" "# import targets" 
-[[# import targets
-include(CMakeFindDependencyMacro)
-find_dependency(protobuf CONFIG)]])
 
 file(REMOVE_RECURSE
     "${CURRENT_PACKAGES_DIR}/debug/include"

ports/onnx/vcpkg.json

@@ -1,7 +1,6 @@
 {
   "name": "onnx",
-  "version-semver": "1.15.0",
-  "port-version": 1,
+  "version-semver": "1.16.0",
   "description": "Open standard for machine learning interoperability",
   "homepage": "https://onnx.ai",
   "license": "Apache-2.0",

ports/onnxruntime-gpu/portfile.cmake

@@ -1,102 +1,2 @@
-vcpkg_check_linkage(ONLY_DYNAMIC_LIBRARY)
-
-vcpkg_download_distfile(ARCHIVE
-    URLS "https://github.com/microsoft/onnxruntime/releases/download/v${VERSION}/onnxruntime-win-x64-gpu-${VERSION}.zip"
-    FILENAME "onnxruntime-win-x64-gpu-${VERSION}.zip"
-    SHA512 7ab350a2ede0fc8c716cf083e16a9303acbcc855982e53900f8843773ec32fd20a7396f0bde82bb29f382012b1d05dea41708797f112d9096c8b5048fc5eb7d8
-)
-
-vcpkg_extract_source_archive(
-    SOURCE_PATH
-    ARCHIVE "${ARCHIVE}"
-    NO_REMOVE_ONE_LEVEL
-)
-
-# Download repo for experimental features
-vcpkg_from_github(
-    OUT_SOURCE_PATH REPO_PATH
-    REPO microsoft/onnxruntime
-    REF v${VERSION}
-    SHA512 f2fec4ded88da6bf67ae7d0aa3082736cb3b8ba29e723b5a516d7632b68ce02aed461f24d3e82cbab20757729e0ab45d736bd986c9b7395f2879b16a091c12a1
-)
-
-file(COPY
-        ${REPO_PATH}/include/onnxruntime/core/session/experimental_onnxruntime_cxx_api.h 
-        ${REPO_PATH}/include/onnxruntime/core/session/experimental_onnxruntime_cxx_inline.h
-        DESTINATION ${CURRENT_PACKAGES_DIR}/include
-    )
-
-file(MAKE_DIRECTORY
-        ${CURRENT_PACKAGES_DIR}/include
-        ${CURRENT_PACKAGES_DIR}/lib
-        ${CURRENT_PACKAGES_DIR}/bin
-        ${CURRENT_PACKAGES_DIR}/debug/lib
-        ${CURRENT_PACKAGES_DIR}/debug/bin
-    )
-
-file(COPY
-        ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/include
-        DESTINATION ${CURRENT_PACKAGES_DIR}
-    )
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/lib)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/lib)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_cuda.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/lib)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_cuda.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/lib)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_cuda.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_cuda.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_shared.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_shared.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_tensorrt.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_tensorrt.pdb
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_shared.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/lib)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_shared.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/lib)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_tensorrt.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/lib)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_tensorrt.lib
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/lib)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_shared.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_shared.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_tensorrt.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_tensorrt.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_cuda.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/bin)
-file(COPY ${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/lib/onnxruntime_providers_cuda.dll
-    DESTINATION ${CURRENT_PACKAGES_DIR}/debug/bin)
-# # Handle copyright
-vcpkg_install_copyright(FILE_LIST "${SOURCE_PATH}/onnxruntime-win-x64-gpu-${VERSION}/LICENSE")
+set(VCPKG_POLICY_EMPTY_PACKAGE enabled)
+message(WARNING "${PORT} is deprecated. Please use port onnxruntime instead.")

ports/onnxruntime-gpu/vcpkg.json

@@ -1,8 +1,16 @@
 {
   "name": "onnxruntime-gpu",
-  "version": "1.16.3",
-  "description": "onnxruntime (GPU)",
+  "version": "1.18.0",
+  "description": "Build onnxruntime port with all available GPU related features",
   "homepage": "https://github.com/microsoft/onnxruntime",
   "license": "MIT",
-  "supports": "windows & !x86 & !uwp & !static & !arm"
+  "supports": "windows & !x86 & !uwp & !static & !arm",
+  "dependencies": [
+    {
+      "name": "onnxruntime",
+      "features": [
+        "cuda"
+      ]
+    }
+  ]
 }

ports/onnxruntime/fix-clang-cl-simd-compile.patch

@@ -0,0 +1,70 @@
+diff --git a/cmake/onnxruntime_mlas.cmake b/cmake/onnxruntime_mlas.cmake
+index 682dcfc..405c65b 100644
+--- a/cmake/onnxruntime_mlas.cmake
++++ b/cmake/onnxruntime_mlas.cmake
+@@ -158,15 +158,31 @@ function(setup_mlas_source_for_windows)
+     )
+     set_source_files_properties(${mlas_platform_srcs_avx2} PROPERTIES COMPILE_FLAGS "/arch:AVX2")
+
++    file(GLOB_RECURSE mlas_platform_srcs_avx512 CONFIGURE_DEPENDS
++      "${MLAS_SRC_DIR}/intrinsics/avx512/*.cpp"
++    )
++    set(mlas_platform_srcs_amx "${MLAS_SRC_DIR}/qgemm_kernel_amx.cpp")
++
++    # clang-cl requires us to enable the platform feature flags explicitly to compile the intrinsics code
++    # unlike MSVC. See: https://github.com/llvm/llvm-project/issues/53520
++    if (CMAKE_CXX_COMPILER_ID MATCHES "Clang")
++      set_source_files_properties(${mlas_platform_srcs_avx512} PROPERTIES COMPILE_FLAGS "/arch:AVX512")
++      set_source_files_properties(${mlas_platform_srcs_amx} PROPERTIES COMPILE_FLAGS "/arch:AVX512 -mamx-tile -mamx-int8")
++      # https://clang.llvm.org/docs/UsersManual.html#cpu-architectures-features-and-limitations
++      set_source_files_properties(${MLAS_SRC_DIR}/qgemm_kernel_sse.cpp PROPERTIES COMPILE_FLAGS "-march=x86-64")
++      set_source_files_properties(${MLAS_SRC_DIR}/qgemm_kernel_sse41.cpp PROPERTIES COMPILE_FLAGS "-march=x86-64-v2")
++    endif()
++
+     target_sources(onnxruntime_mlas PRIVATE
+       ${MLAS_SRC_DIR}/dgemm.cpp
+       ${mlas_platform_srcs_avx}
+       ${mlas_platform_srcs_avx2}
+-      ${MLAS_SRC_DIR}/qgemm_kernel_amx.cpp
++      ${mlas_platform_srcs_avx512}
++      ${mlas_platform_srcs_amx}
++      # ...
+       ${MLAS_SRC_DIR}/qgemm_kernel_avx2.cpp
+       ${MLAS_SRC_DIR}/qgemm_kernel_sse.cpp
+       ${MLAS_SRC_DIR}/qgemm_kernel_sse41.cpp
+-      ${MLAS_SRC_DIR}/intrinsics/avx512/quantize_avx512f.cpp
+       ${MLAS_SRC_DIR}/sqnbitgemm_kernel_avx2.cpp
+       ${MLAS_SRC_DIR}/sqnbitgemm_kernel_avx512.cpp
+       ${MLAS_SRC_DIR}/sqnbitgemm_kernel_avx512vnni.cpp
+@@ -208,9 +224,15 @@ function(setup_mlas_source_for_windows)
+       ${MLAS_SRC_DIR}/amd64/ErfKernelFma3.asm
+     )
+     if (NOT onnxruntime_ORT_MINIMAL_BUILD)
+-      target_sources(onnxruntime_mlas PRIVATE
++      set(onnxruntime_mlas_q4gemm_avx512
+         ${MLAS_SRC_DIR}/q4gemm_avx512.cpp
+       )
++      if (CMAKE_CXX_COMPILER_ID MATCHES "Clang")
++        # clang-cl requires us to enable the platform feature flags explicitly to compile the intrinsics code
++        # unlike MSVC. See: https://github.com/llvm/llvm-project/issues/53520
++        set_source_files_properties(${onnxruntime_mlas_q4gemm_avx512} PROPERTIES COMPILE_FLAGS "/arch:AVX512 -mavx512vnni")
++      endif()
++      target_sources(onnxruntime_mlas PRIVATE ${onnxruntime_mlas_q4gemm_avx512})
+     endif()
+   else()
+     target_sources(onnxruntime_mlas PRIVATE
+diff --git a/onnxruntime/core/mlas/lib/qgemm_kernel_sse41.cpp b/onnxruntime/core/mlas/lib/qgemm_kernel_sse41.cpp
+index 68931c5..6c095bd 100644
+--- a/onnxruntime/core/mlas/lib/qgemm_kernel_sse41.cpp
++++ b/onnxruntime/core/mlas/lib/qgemm_kernel_sse41.cpp
+@@ -16,6 +16,10 @@ Abstract:
+
+ #include "mlasi.h"
+ #include "qgemm.h"
++#if defined(__clang__)
++#include <smmintrin.h>
++#include <tmmintrin.h>
++#endif
+
+ // N.B. MSVC does not require turning on SSE 4.1 intrinsics and the current use
+ // for this code is Windows only, so restrict this kernel to that environment.