Ryan Hill 0d0eb2c85c Change OpKernel class to be shared with shared providers (#6837) ... In the previous shared providers there aren't many OpKernel classes, and the existing Provider_OpKernel wrapper was fine. With the opposibility of making Cuda a shared provider, having this need to be changed per OpKernel adds a lot of complexity. It was fairly straightforward to make OpKernel work with shared providers with minimal changes. In this change, the ONNX_OPERATOR_* macros can also be shared with the shared providers.		2021-03-02 00:53:48 -08:00
..
allocation_planner.cc	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
allocation_planner.h
allocator.cc	Share allocator between CUDA EP & TRT EP. (#6332)	2021-01-27 00:14:43 -08:00
allocatormgr.cc	Share allocator between CUDA EP & TRT EP. (#6332)	2021-01-27 00:14:43 -08:00
allocatormgr.h	Share allocator between CUDA EP & TRT EP. (#6332)	2021-01-27 00:14:43 -08:00
arena.h
arena_extend_strategy.h	Deprecate Python global configuration functions [Part 2] (#6171)	2021-01-07 10:10:55 -08:00
bfc_arena.cc	Fix edge case in BFCArena where allocation failures could lead to an infinite loop. (#6145)	2020-12-17 07:52:31 +10:00
bfc_arena.h	Fix some compile warnings (#6316)	2021-01-21 16:40:42 -08:00
callback.cc
callback.h
cblas.h
compute_capability.h
customregistry.cc	Add support for custom ops to minimal build. (#6228)	2021-01-25 10:41:00 +10:00
data_transfer.cc
data_transfer.h
data_transfer_manager.cc
data_transfer_manager.h
data_transfer_utils.h	Remove condition from ORT_RETURN_IF[_NOT] macro output. (#6563)	2021-02-05 17:33:29 -08:00
data_types.cc	Cast Op performance fix. (#6509)	2021-02-04 14:52:37 -08:00
debug_node_inputs_outputs_utils.cc	Fix DEBUG_NODE_INPUTS_OUTPUTS test by putting it in a separate process, clean up unused test_main.cc files. (#5949)	2020-12-11 11:36:58 -08:00
debug_node_inputs_outputs_utils.h	Allow turning off printing of shape when compiled with onnxruntime_DEBUG_NODE_INPUTS_OUTPUTS. (#5768)	2020-11-11 18:59:04 -08:00
empty.cc
endian_utils.cc	Reduce tensorprotoutils binary size (#6634)	2021-02-12 16:48:13 +10:00
endian_utils.h	Reduce tensorprotoutils binary size (#6634)	2021-02-12 16:48:13 +10:00
error_code.cc
error_code_helper.h
ex_lib_loader.cc
ex_lib_loader.h
execution_frame.cc	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
execution_frame.h
execution_plan_base.h
execution_provider.cc	Share allocator between CUDA EP & TRT EP. (#6332)	2021-01-27 00:14:43 -08:00
execution_providers.h
fallback_cpu_capability.cc	Refine force CPU fallback logic in the CUDA EP (#6849)	2021-03-01 19:59:07 -08:00
fallback_cpu_capability.h	Reduce amount of compiled CUDA device code (#6118)	2020-12-14 15:27:40 -08:00
feeds_fetches_manager.cc
feeds_fetches_manager.h
func_kernel.cc
func_kernel.h	Support EPs that compile nodes in a minimal build. (#5776)	2020-11-17 13:52:22 +10:00
fuse_nodes_funcs.cc	Support EPs that compile nodes in a minimal build. (#5776)	2020-11-17 13:52:22 +10:00
fuse_nodes_funcs.h	Prevent saving a model containing fused nodes as we don't have any way to save the compiled kernels so the saved model will be invalid. (#5840)	2020-11-18 16:17:07 +10:00
graph_partitioner.cc	Let execution fall back to CPU EP if Compile of a partition on current EP fails (#6580)	2021-02-05 12:14:55 -08:00
graph_partitioner.h	Support EPs that compile nodes in a minimal build. (#5776)	2020-11-17 13:52:22 +10:00
iexecutor.h
kernel_def_builder.cc	Make kernel hash stable in type reduced build (#6603)	2021-02-09 12:00:08 +10:00
kernel_registry.cc
kernel_registry_manager.cc	Require explicit inclusion of custom op support in a minimal build (#6663)	2021-02-13 12:42:33 +10:00
kernel_registry_manager.h	Require explicit inclusion of custom op support in a minimal build (#6663)	2021-02-13 12:42:33 +10:00
mem_buffer.h
mem_pattern.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
mem_pattern_planner.h	Exclude some training specific code from the minimal build. Cleanup some related aspects of allocation planner. (#5861)	2020-11-20 20:25:46 +10:00
memcpy.cc	Rename MakeString and ParseString functions. (#6272)	2021-01-07 15:43:42 -08:00
memcpy.h
memory_info.cc	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
memory_info.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
mimalloc_arena.cc
mimalloc_arena.h
mldata_type_utils.cc
mldata_type_utils.h
murmurhash3.cc
murmurhash3.h
node_index_info.cc
node_index_info.h	Factor out IAllocator so that it can be shared with shared providers (#5567)	2020-10-27 17:28:17 -07:00
onnxruntime_map_type_info.cc
onnxruntime_map_type_info.h
onnxruntime_sequence_type_info.cc
onnxruntime_sequence_type_info.h
onnxruntime_typeinfo.cc	Add LearningModelBuilder to WinML Experimental Namespace along with various Audio operators (#6623)	2021-02-12 14:17:10 -08:00
onnxruntime_typeinfo.h	Add LearningModelBuilder to WinML Experimental Namespace along with various Audio operators (#6623)	2021-02-12 14:17:10 -08:00
op_kernel.cc	Change OpKernel class to be shared with shared providers (#6837)	2021-03-02 00:53:48 -08:00
op_kernel_context_internal.h	Move GetUseDeterministicCompute() to OpKernelContext to avoid need to downcast to OpKernelContextInternal. (#5729)	2020-11-09 11:37:06 -08:00
op_kernel_info.cc	Support EPs that compile nodes in a minimal build. (#5776)	2020-11-17 13:52:22 +10:00
op_node_proto_helper.cc	Allow Kernels refer to some attribute data directly in the protobuf (#5624)	2020-10-29 16:12:54 -07:00
ort_stl_allocator.h
ort_value_name_idx_map.h
ort_value_pattern_planner.cc	Exclude some training specific code from the minimal build. Cleanup some related aspects of allocation planner. (#5861)	2020-11-20 20:25:46 +10:00
ort_value_pattern_planner.h	Exclude some training specific code from the minimal build. Cleanup some related aspects of allocation planner. (#5861)	2020-11-20 20:25:46 +10:00
ort_value_tensor_slicer.cc
ort_value_tensor_slicer.h
parallel_executor.cc	Unify activation and initializer alignment value (#6109)	2020-12-14 13:13:41 -08:00
parallel_executor.h
provider_bridge_ort.cc	Change OpKernel class to be shared with shared providers (#6837)	2021-03-02 00:53:48 -08:00
random_generator.cc
random_generator.h
random_seed.cc
random_seed.h
run_options.cc
sequential_execution_plan.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
sequential_executor.cc	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
sequential_executor.h
session_options.cc	Fix some compile warnings (#6316)	2021-01-21 16:40:42 -08:00
session_options.h	Fix some compile warnings (#6316)	2021-01-21 16:40:42 -08:00
session_state.cc	Continue memory planning when unknown shape tensor is encountered. (#6413)	2021-01-22 14:37:53 -08:00
session_state.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
session_state_utils.cc	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
session_state_utils.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
simple_tensor_allocator.cc	Unify activation and initializer alignment value (#6109)	2020-12-14 13:13:41 -08:00
simple_tensor_allocator.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
sparse_tensor.cc	Support for Sparse Initializers (#5540)	2020-10-27 10:32:06 -07:00
tensor.cc
tensor_allocator.cc
tensor_allocator.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
tensor_allocator_with_mem_pattern.h	Wezuo/memory analysis (#5658)	2021-01-19 08:30:55 -08:00
tensor_external_data_info.cc
tensor_external_data_info.h
tensor_shape.cc
tensor_type_and_shape.cc	Add LearningModelBuilder to WinML Experimental Namespace along with various Audio operators (#6623)	2021-02-12 14:17:10 -08:00
tensor_type_and_shape.h
tensorprotoutils.cc	Address warning in data_types_internal.h (#6704)	2021-02-16 12:41:48 -08:00
tensorprotoutils.h	Reduce tensorprotoutils binary size (#6634)	2021-02-12 16:48:13 +10:00
TensorSeq.h	Support opset-13 specs of controlflow ops (Loop, If) (#5665)	2020-11-11 23:44:14 -08:00
utils.cc	Initial version of CoreML EP (#6392)	2021-01-27 10:43:17 -08:00
utils.h	Exclude some training specific code from the minimal build. Cleanup some related aspects of allocation planner. (#5861)	2020-11-20 20:25:46 +10:00