onnxruntime/cmake
Patrice Vignola 3482180ec2
DML EP add a registration for Shape and Size (#13442)
### Description
Add a DML registration for Shape to avoid copying back to the CPU just
to get the shape of a GPU tensor.



### Motivation and Context
When using free dimensions, many Transformers models extensively use the
`Shape` operator. This causes hundreds of GPU->CPU copy that should be
completely avoidable. Note that this change also uses the same
heuristics as other providers (e.g. CUDA) to force some tensors on the
CPU in certain situations.

Co-authored-by: Patrice Vignola <pavignol@microsoft.com>
2022-11-08 19:29:37 -08:00
..
external [tvm] Add support for int8 models, update TVM revision (#13519) 2022-11-08 11:28:32 -08:00
patches Remove the cmake option: onnxruntime_DEV_MODE (#13573) 2022-11-07 09:06:28 -08:00
tensorboard Disable two warnings raised by tensorboard on Visual Studio (#12773) 2022-09-06 20:42:52 +02:00
CMakeLists.txt Remove the cmake option: onnxruntime_DEV_MODE (#13573) 2022-11-07 09:06:28 -08:00
CMakeSettings.json
codeconv.runsettings
EnableVisualStudioCodeAnalysis.props
find_snpe.cmake cmake changes for SNPE EP (#11821) 2022-06-13 08:15:37 -07:00
gdk_toolchain.cmake
Info.plist.in
libonnxruntime.pc.cmake.in
nuget_helpers.cmake
onnxruntime.cmake Remove miscellaneous nuphar configs (#13070) 2022-09-26 13:41:28 -07:00
onnxruntime_codegen_tvm.cmake
onnxruntime_common.cmake Switch GSL to MS GSL 4.0.0 (#13416) 2022-10-29 04:15:20 -07:00
onnxruntime_config.h.in
onnxruntime_csharp.cmake Remove miscellaneous nuphar configs (#13070) 2022-09-26 13:41:28 -07:00
onnxruntime_eager.cmake
onnxruntime_flatbuffers.cmake Switch GSL to MS GSL 4.0.0 (#13416) 2022-10-29 04:15:20 -07:00
onnxruntime_framework.cmake ATen Fallback for Inference (#11597) 2022-06-09 16:07:30 +08:00
onnxruntime_fuzz_test.cmake
onnxruntime_graph.cmake ONNX Protobuf natvis with some google::protobuf (#12580) 2022-08-15 09:59:07 -07:00
onnxruntime_ios.toolchain.cmake
onnxruntime_java.cmake
onnxruntime_java_unittests.cmake
onnxruntime_kernel_explorer.cmake Update CK and fix performance issue on dev machine (#13531) 2022-11-03 19:32:30 +08:00
onnxruntime_language_interop_ops.cmake
onnxruntime_mlas.cmake Switch GSL to MS GSL 4.0.0 (#13416) 2022-10-29 04:15:20 -07:00
onnxruntime_nodejs.cmake
onnxruntime_objectivec.cmake Remove the cmake option: onnxruntime_DEV_MODE (#13573) 2022-11-07 09:06:28 -08:00
onnxruntime_opschema_lib.cmake
onnxruntime_optimizer.cmake
onnxruntime_providers.cmake DML EP add a registration for Shape and Size (#13442) 2022-11-08 19:29:37 -08:00
onnxruntime_pyop.cmake
onnxruntime_python.cmake Update CK and fix performance issue on dev machine (#13531) 2022-11-03 19:32:30 +08:00
onnxruntime_rocm_hipify.cmake Drop hip_add_library (#13406) 2022-10-25 12:57:48 +08:00
onnxruntime_session.cmake Update CK and fix performance issue on dev machine (#13531) 2022-11-03 19:32:30 +08:00
onnxruntime_snpe_provider.cmake cmake changes for SNPE EP (#11821) 2022-06-13 08:15:37 -07:00
onnxruntime_training.cmake Update CK and fix performance issue on dev machine (#13531) 2022-11-03 19:32:30 +08:00
onnxruntime_unittests.cmake oneDNN ep bf16 enabling (#13484) 2022-11-04 18:25:09 -07:00
onnxruntime_util.cmake
onnxruntime_webassembly.cmake increase max memory to 4G for wasm (#12798) 2022-09-06 17:07:13 -07:00
precompiled_header.cmake
protobuf_function.cmake
Sdl.ruleset Update Sdl.ruleset to remove C26812 from the rules (#12695) 2022-09-01 20:05:20 -07:00
set_winapi_family_desktop.h
target_delayload.cmake
uwp_stubs.h
wcos_rules_override.cmake
wil.cmake
winml.cmake Switch GSL to MS GSL 4.0.0 (#13416) 2022-10-29 04:15:20 -07:00
winml_cppwinrt.cmake
winml_sdk_helpers.cmake
winml_unittests.cmake Switch GSL to MS GSL 4.0.0 (#13416) 2022-10-29 04:15:20 -07:00