| .. |
|
allocation_planner.cc
|
Make sure fenced tensor could not reuse other tensor. (#2561)
|
2019-12-11 12:04:54 -08:00 |
|
allocation_planner.h
|
Introduce execution mode enum for clarity and extensibility; Change Python, C and C# APIs accordingly; Removed EnableSequentialExecution, DisableSequentialExecution in favor of the more general SetExecutionModeAPI. (#2098)
|
2019-10-14 09:48:19 -07:00 |
|
allocator.cc
|
Ignore allocator type in ExecutionProviders allocator map. Make default initialization of OrtMemoryInfo more clearly invalid. (#2768)
|
2020-01-14 18:14:55 +10:00 |
|
allocatormgr.cc
|
Revert "Remove DeviceAllocatorRegistry class (#2451)"
|
2019-11-25 23:43:10 -08:00 |
|
allocatormgr.h
|
Revert "Remove DeviceAllocatorRegistry class (#2451)"
|
2019-11-25 23:43:10 -08:00 |
|
arena.h
|
mimalloc allocator (#2071)
|
2019-10-23 22:34:00 -07:00 |
|
bfc_arena.cc
|
Revert "Use IArenaAllocator::Reserve for initializers and mem pattern planner blocks (#2835)" (#2904)
|
2020-01-24 14:02:30 +10:00 |
|
bfc_arena.h
|
Fix some warnings on Windows (#2560)
|
2020-01-22 15:59:11 -08:00 |
|
callback.cc
|
Remove unneeded C APIs + some refactoring. (#1555)
|
2019-08-07 11:05:29 -07:00 |
|
callback.h
|
Fixed tensor reference to const data and cleaned up Env API. (#1979)
|
2019-10-24 10:28:13 -07:00 |
|
cblas.h
|
|
|
|
compute_capability.h
|
|
|
|
customregistry.cc
|
|
|
|
data_transfer.cc
|
add interface to copy batch tensors. (#2807)
|
2020-01-09 16:52:34 -08:00 |
|
data_transfer.h
|
add interface to copy batch tensors. (#2807)
|
2020-01-09 16:52:34 -08:00 |
|
data_transfer_manager.cc
|
Move CopyTensor out of IExecutionProvider interface. (#1268)
|
2019-07-11 14:49:20 -07:00 |
|
data_transfer_manager.h
|
Move CopyTensor out of IExecutionProvider interface. (#1268)
|
2019-07-11 14:49:20 -07:00 |
|
data_types.cc
|
Import Featurizers (#2643)
|
2019-12-13 16:07:12 -08:00 |
|
empty.cc
|
|
|
|
endian_utils.cc
|
Improved documentation for onnxruntime::utils::SwapByteOrderCopy(), added precondition check.
|
2019-11-19 11:03:40 -08:00 |
|
endian_utils.h
|
Improved documentation for onnxruntime::utils::SwapByteOrderCopy(), added precondition check.
|
2019-11-19 11:03:40 -08:00 |
|
error_code.cc
|
Ryanunderhill/api interface (#1855)
|
2019-09-20 13:39:11 -07:00 |
|
error_code_helper.h
|
Ryanunderhill/api interface (#1855)
|
2019-09-20 13:39:11 -07:00 |
|
ex_lib_loader.cc
|
|
|
|
ex_lib_loader.h
|
|
|
|
execution_frame.cc
|
Revert "Use IArenaAllocator::Reserve for initializers and mem pattern planner blocks (#2835)" (#2904)
|
2020-01-24 14:02:30 +10:00 |
|
execution_frame.h
|
Rename OrtAllocatorInfo to OrtMemoryInfo to make it more obvious. (#1758)
|
2019-09-05 14:20:37 -07:00 |
|
execution_plan_base.h
|
Rename OrtAllocatorInfo to OrtMemoryInfo to make it more obvious. (#1758)
|
2019-09-05 14:20:37 -07:00 |
|
execution_provider.cc
|
Replace GSL with GSL-LITE submodule and fix up refs (#1920)
|
2019-10-01 12:43:29 -07:00 |
|
execution_providers.h
|
Ignore allocator type in ExecutionProviders allocator map. Make default initialization of OrtMemoryInfo more clearly invalid. (#2768)
|
2020-01-14 18:14:55 +10:00 |
|
feeds_fetches_manager.cc
|
Replace GSL with GSL-LITE submodule and fix up refs (#1920)
|
2019-10-01 12:43:29 -07:00 |
|
feeds_fetches_manager.h
|
Rework the feed/fetch copy setup so that it can be calculated prior to subgraph execution (#1761)
|
2019-09-10 15:46:00 +10:00 |
|
func_kernel.cc
|
|
|
|
func_kernel.h
|
Ryanunderhill/customop dll (#2002)
|
2019-10-11 11:12:51 -07:00 |
|
fuse_nodes_funcs.cc
|
Ryanunderhill/api interface (#1855)
|
2019-09-20 13:39:11 -07:00 |
|
fuse_nodes_funcs.h
|
Replace GSL with GSL-LITE submodule and fix up refs (#1920)
|
2019-10-01 12:43:29 -07:00 |
|
graph_partitioner.cc
|
Add CUDA Scan operator. (#2403)
|
2019-11-21 07:59:06 +10:00 |
|
graph_partitioner.h
|
|
|
|
iexecutor.h
|
Fix bug with delayed allocation of If and Scan outputs. (#2024)
|
2019-10-11 19:49:21 +10:00 |
|
kernel_def_builder.cc
|
Fix kernel registry validation to reenable DML kernels
|
2019-12-02 15:43:44 -08:00 |
|
kernel_registry.cc
|
Avoid printing a misleading message exposed by a previous commit + register float type for Slice cuda op. (#2219)
|
2019-10-22 07:23:05 -07:00 |
|
kernel_registry_manager.cc
|
Add details of which node was not able to be placed on an execution provider. (#1665)
|
2019-08-21 13:31:00 -07:00 |
|
kernel_registry_manager.h
|
|
|
|
mem_buffer.h
|
Rename OrtAllocatorInfo to OrtMemoryInfo to make it more obvious. (#1758)
|
2019-09-05 14:20:37 -07:00 |
|
mem_pattern.h
|
Rename OrtAllocatorInfo to OrtMemoryInfo to make it more obvious. (#1758)
|
2019-09-05 14:20:37 -07:00 |
|
mem_pattern_planner.h
|
Rename MLValue to OrtValue (#1154)
|
2019-06-03 17:29:55 -07:00 |
|
memcpy.cc
|
Move CopyTensor out of IExecutionProvider interface. (#1268)
|
2019-07-11 14:49:20 -07:00 |
|
memcpy.h
|
|
|
|
mimalloc_arena.cc
|
mimalloc allocator (#2071)
|
2019-10-23 22:34:00 -07:00 |
|
mimalloc_arena.h
|
mimalloc allocator (#2071)
|
2019-10-23 22:34:00 -07:00 |
|
mldata_type_utils.cc
|
|
|
|
mldata_type_utils.h
|
|
|
|
node_index_info.cc
|
Downgrade compiler to CentOS 4.8.5 (#1985)
|
2019-10-03 15:40:46 -07:00 |
|
node_index_info.h
|
Minor perf improvements. (#1580)
|
2019-08-13 09:05:48 +10:00 |
|
onnxruntime_typeinfo.cc
|
Introduce container type runtime checks and other improvements (#2522)
|
2019-12-04 16:04:17 -08:00 |
|
onnxruntime_typeinfo.h
|
Add ability to get symbolic dimension info for graph inputs and outputs. (#2051)
|
2019-10-12 15:46:28 -07:00 |
|
op_kernel.cc
|
Move access to intra-op threadpool into OpKernelContext. (#2091)
|
2019-10-11 10:36:20 -07:00 |
|
op_kernel_context_internal.h
|
Move access to intra-op threadpool into OpKernelContext. (#2091)
|
2019-10-11 10:36:20 -07:00 |
|
op_kernel_info.cc
|
Part 2 of renaming AllocatorInfo to MemoryInfo. (#1804)
|
2019-09-12 08:19:29 -07:00 |
|
op_node_proto_helper.cc
|
Replace GSL with GSL-LITE submodule and fix up refs (#1920)
|
2019-10-01 12:43:29 -07:00 |
|
ort_value_name_idx_map.h
|
Ignore allocator type in ExecutionProviders allocator map. Make default initialization of OrtMemoryInfo more clearly invalid. (#2768)
|
2020-01-14 18:14:55 +10:00 |
|
ort_value_pattern_planner.cc
|
Downgrade compiler to CentOS 4.8.5 (#1985)
|
2019-10-03 15:40:46 -07:00 |
|
ort_value_pattern_planner.h
|
Rename OrtAllocatorInfo to OrtMemoryInfo to make it more obvious. (#1758)
|
2019-09-05 14:20:37 -07:00 |
|
ort_value_tensor_slicer.cc
|
Add CUDA Scan operator. (#2403)
|
2019-11-21 07:59:06 +10:00 |
|
ort_value_tensor_slicer.h
|
Fix some warnings on Windows (#2560)
|
2020-01-22 15:59:11 -08:00 |
|
parallel_executor.cc
|
Downgrade compiler to CentOS 4.8.5 (#1985)
|
2019-10-03 15:40:46 -07:00 |
|
parallel_executor.h
|
Refine threading control options and move inter op thread pool to session state. (#1841)
|
2019-09-18 22:36:23 -07:00 |
|
path_lib.cc
|
Avoid using the default logger in the graph lib and optimizers (#2361)
|
2019-11-14 13:23:28 -08:00 |
|
path_lib.h
|
Update protobuf to 3.11.2 (#1928)
|
2019-12-27 18:28:18 -08:00 |
|
run_options.cc
|
Ryanunderhill/api interface (#1855)
|
2019-09-20 13:39:11 -07:00 |
|
sequential_execution_plan.h
|
Ignore allocator type in ExecutionProviders allocator map. Make default initialization of OrtMemoryInfo more clearly invalid. (#2768)
|
2020-01-14 18:14:55 +10:00 |
|
sequential_executor.cc
|
Add Tracelogging for profiling (#1639)
|
2019-11-11 21:34:10 -08:00 |
|
sequential_executor.h
|
|
|
|
session_options.h
|
update default optimization level + fix gemm_activation fusion (#2791)
|
2020-01-13 14:05:38 -08:00 |
|
session_state.cc
|
Add Tracelogging for profiling (#1639)
|
2019-11-11 21:34:10 -08:00 |
|
session_state.h
|
Add Tracelogging for profiling (#1639)
|
2019-11-11 21:34:10 -08:00 |
|
session_state_initializer.cc
|
Ignore allocator type in ExecutionProviders allocator map. Make default initialization of OrtMemoryInfo more clearly invalid. (#2768)
|
2020-01-14 18:14:55 +10:00 |
|
session_state_initializer.h
|
Introduce execution mode enum for clarity and extensibility; Change Python, C and C# APIs accordingly; Removed EnableSequentialExecution, DisableSequentialExecution in favor of the more general SetExecutionModeAPI. (#2098)
|
2019-10-14 09:48:19 -07:00 |
|
simple_tensor_allocator.cc
|
Replace GSL with GSL-LITE submodule and fix up refs (#1920)
|
2019-10-01 12:43:29 -07:00 |
|
simple_tensor_allocator.h
|
Rename MLValue to OrtValue (#1154)
|
2019-06-03 17:29:55 -07:00 |
|
sparse_tensor.cc
|
Part 2 of renaming AllocatorInfo to MemoryInfo. (#1804)
|
2019-09-12 08:19:29 -07:00 |
|
tensor.cc
|
Fix some warnings on Windows (#2560)
|
2020-01-22 15:59:11 -08:00 |
|
tensor_allocator.cc
|
Replace GSL with GSL-LITE submodule and fix up refs (#1920)
|
2019-10-01 12:43:29 -07:00 |
|
tensor_allocator.h
|
Part 2 of renaming AllocatorInfo to MemoryInfo. (#1804)
|
2019-09-12 08:19:29 -07:00 |
|
tensor_allocator_with_mem_pattern.h
|
Revert "Use IArenaAllocator::Reserve for initializers and mem pattern planner blocks (#2835)" (#2904)
|
2020-01-24 14:02:30 +10:00 |
|
tensor_external_data_info.cc
|
Replace GSL with GSL-LITE submodule and fix up refs (#1920)
|
2019-10-01 12:43:29 -07:00 |
|
tensor_external_data_info.h
|
|
|
|
tensor_shape.cc
|
Filter out info from non-const initializers during shape inferencing (#1806)
|
2019-09-26 13:44:33 +10:00 |
|
tensor_type_and_shape.cc
|
Introduce PrimitiveType into a Type System along with an integer constant (#2307)
|
2019-11-08 17:47:06 -08:00 |
|
tensor_type_and_shape.h
|
Add ability to get symbolic dimension info for graph inputs and outputs. (#2051)
|
2019-10-12 15:46:28 -07:00 |
|
tensorprotoutils.cc
|
Fix some warnings on Windows (#2560)
|
2020-01-22 15:59:11 -08:00 |
|
tensorprotoutils.h
|
Fix some warnings on Windows (#2560)
|
2020-01-22 15:59:11 -08:00 |
|
TensorSeq.h
|
Introduce container type runtime checks and other improvements (#2522)
|
2019-12-04 16:04:17 -08:00 |
|
utils.cc
|
Revert "Use IArenaAllocator::Reserve for initializers and mem pattern planner blocks (#2835)" (#2904)
|
2020-01-24 14:02:30 +10:00 |
|
utils.h
|
Revert "Use IArenaAllocator::Reserve for initializers and mem pattern planner blocks (#2835)" (#2904)
|
2020-01-24 14:02:30 +10:00 |
