mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-23 22:13:38 +00:00
d9eeb48393
* Disable training code in DNNL LayerNorm code The capability code already does not claim the LayerNorm and SkipLayerNorm that require more than one output. However, building with training enabled was causing issues. The training specific code has been removed even when building with training enabled. Signed-off-by: George Nash <george.nash@intel.com> * Fix for DNNL FusedMatMul op. The bug was in the transpose code. Signed-off-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com> * Use agreed upon memory format type when runnig Pooling Gradient in dnnl ep The dnnl ep does not currently have a way to pass memory_format information between the forward pooling primitive to the backward pooling primitive. This change explicitly sets the memory_format to use match that of Onnxruntime. For both the forward and backward pooling code. This will prevent using un-matched memory format that could result in an `unimplemented` error from dnnl ep. Signed-off-by: George Nash <george.nash@intel.com> * Update dnnl ep to use OneDNN v2.6 Do not run ReduceInfLogSum on the kDnnlExecutionProvider due to a calculation bug when doing Log or infinity valuse. The fix for this issue will be part of the next OneDNN release. Signed-off-by: George Nash <george.nash@intel.com> * Update PrintMemory function in dnnl ep This modification can be used to enable/disable memory printing for dnnl ep develpers. This is considered a developer only feature and is disabled by default. It must be enabled and code recompiled to use. Even if it is enabled it will not actually print any memory because the developer needs to take the extra step of spefifying the memory that will be printed to the screen. Signed-off-by: George Nash <george.nash@intel.com> * Update binary ops to run on intel GPU when using dnnl ep Binary ops (i.e. Add, Div, Mul, and Sub ) was updated to no longer call GetMemoryAndReshape in the past this would move the memory from CPU to the GPU. This extra call is no longer needed since it is taken care of by the GetMemoryInOrtFormat call. Removing the GetMemoryAndReshape prevented copying the memory to GPU twice. Signed-off-by: George Nash <george.nash@intel.com> Co-authored-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com>
57 lines
2.5 KiB
CMake
57 lines
2.5 KiB
CMake
include (ExternalProject)
|
|
|
|
set(DNNL_URL https://github.com/oneapi-src/onednn.git)
|
|
# If DNNL_TAG is updated, check if MKLML_VERSION and platform.cmake.patch need to be updated.
|
|
set(DNNL_TAG v2.6)
|
|
|
|
if(WIN32)
|
|
set(DNNL_SHARED_LIB dnnl.dll)
|
|
set(DNNL_IMPORT_LIB dnnl.lib)
|
|
else()
|
|
if (APPLE)
|
|
set(DNNL_SHARED_LIB libdnnl.2.dylib)
|
|
else()
|
|
set(DNNL_SHARED_LIB libdnnl.so.2)
|
|
endif()
|
|
endif()
|
|
|
|
if(onnxruntime_USE_DNNL AND onnxruntime_DNNL_GPU_RUNTIME STREQUAL "ocl" AND onnxruntime_DNNL_OPENCL_ROOT STREQUAL "")
|
|
message(FATAL_ERROR "--dnnl_opencl_root required")
|
|
elseif(onnxruntime_USE_DNNL AND onnxruntime_DNNL_GPU_RUNTIME STREQUAL "" AND NOT (onnxruntime_DNNL_OPENCL_ROOT STREQUAL ""))
|
|
message(FATAL_ERROR "--dnnl_gpu_runtime required")
|
|
elseif(onnxruntime_USE_DNNL AND onnxruntime_DNNL_GPU_RUNTIME STREQUAL "ocl" AND NOT (onnxruntime_DNNL_OPENCL_ROOT STREQUAL ""))
|
|
file(TO_CMAKE_PATH ${onnxruntime_DNNL_OPENCL_ROOT} onnxruntime_DNNL_OPENCL_ROOT)
|
|
set(DNNL_OCL_INCLUDE_DIR ${onnxruntime_DNNL_OPENCL_ROOT}/include)
|
|
set(DNNL_GPU_CMAKE_ARGS "-DDNNL_GPU_RUNTIME=OCL " "-DOPENCLROOT=${onnxruntime_DNNL_OPENCL_ROOT}")
|
|
endif()
|
|
|
|
if (onnxruntime_USE_DNNL)
|
|
set(DNNL_SOURCE ${CMAKE_CURRENT_BINARY_DIR}/dnnl/src/dnnl/src)
|
|
set(DNNL_INSTALL ${CMAKE_CURRENT_BINARY_DIR}/dnnl/install)
|
|
set(DNNL_LIB_DIR ${DNNL_INSTALL}/${CMAKE_INSTALL_LIBDIR})
|
|
if(WIN32)
|
|
set(DNNL_DLL_PATH ${DNNL_INSTALL}/${CMAKE_INSTALL_BINDIR}/${DNNL_SHARED_LIB})
|
|
else()
|
|
set(DNNL_DLL_PATH ${DNNL_LIB_DIR}/${DNNL_SHARED_LIB})
|
|
endif()
|
|
set(DNNL_INCLUDE_DIR ${DNNL_INSTALL}/include)
|
|
set(DNNL_CMAKE_EXTRA_ARGS)
|
|
# set(DNNL_PATCH_COMMAND git apply ${CMAKE_SOURCE_DIR}/patches/mkldnn/constexpr.patch)
|
|
# discard prior changes due to patching in mkldnn source to unblock incremental builds.
|
|
# set(MKLDNN_PATCH_DISCARD_COMMAND cd ${DNNL_SOURCE} && git checkout -- .)
|
|
# if(NOT onnxruntime_BUILD_FOR_NATIVE_MACHINE)
|
|
# pre-v1.0
|
|
# list(APPEND DNNL_CMAKE_EXTRA_ARGS "-DARCH_OPT_FLAGS=")
|
|
# v1.0
|
|
# list(APPEND DNNL_CMAKE_EXTRA_ARGS "-DDNNL_ARCH_OPT_FLAGS=")
|
|
# endif()
|
|
ExternalProject_Add(project_dnnl
|
|
PREFIX dnnl
|
|
GIT_REPOSITORY ${DNNL_URL}
|
|
GIT_TAG ${DNNL_TAG}
|
|
# PATCH_COMMAND ${MKLDNN_PATCH_DISCARD_COMMAND} COMMAND ${DNNL_PATCH_COMMAND}
|
|
SOURCE_DIR ${DNNL_SOURCE}
|
|
CMAKE_ARGS -DDNNL_BUILD_TESTS=OFF -DDNNL_ENABLE_CONCURRENT_EXEC=ON -DDNNL_BUILD_EXAMPLES=OFF -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DCMAKE_INSTALL_PREFIX=${DNNL_INSTALL} ${DNNL_GPU_CMAKE_ARGS}
|
|
)
|
|
link_directories(${DNNL_LIB_DIR})
|
|
endif()
|