Handle compiler warnings for TRT EP #9956
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jywu-msft
reviewed
Dec 8, 2021
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
Outdated
Show resolved
Hide resolved
jywu-msft
reviewed
Dec 8, 2021
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
Outdated
Show resolved
Hide resolved
jywu-msft
reviewed
Dec 8, 2021
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
Outdated
Show resolved
Hide resolved
chilo-ms
commented
Dec 8, 2021
| @@ -1104,7 +1105,7 @@ TensorrtExecutionProvider::GetCapability(const GraphViewer& graph, | |||
|
|
|||
| // Remove subgraphs if its size is less than the predefined minimal size | |||
| for (auto it = supported_nodes_vector.begin(); it != supported_nodes_vector.end(); ++it) { | |||
| const int subgraph_size = it->first.size(); | |||
| const int subgraph_size = static_cast<int>(it->first.size()); | |||
There was a problem hiding this comment.
Thought about changing from "const int subgraph_size" to "const size_t subgraph_size". Which means the type of min_subgraph_size_ should be changed to size_t as well. However, min_subgraph_size_ is one of C APIs, it's better not to modify it.
chilo-ms
commented
Dec 9, 2021
| @@ -1432,8 +1433,8 @@ common::Status TensorrtExecutionProvider::Compile(const std::vector<Node*>& fuse | |||
| auto trt_context = trt_state->context->get(); | |||
| auto trt_profile = &(trt_state->trt_profile); | |||
| auto alloc = trt_state->scratch_allocator; | |||
| int num_inputs = input_indexes.size(); | |||
| int num_outputs = output_indexes.size(); | |||
| int num_inputs = static_cast<int>(input_indexes.size()); | |||
There was a problem hiding this comment.
If we change to "size_t num_inputs", we will need to add "static_cast<int32_t>(i)" to "auto input = trt_state->network->get()->getInput(i);" at line 1510.
So don't change this part and also it's not highly possible number of inputs is large enough to overflow 'int' type.
jywu-msft
reviewed
Dec 9, 2021
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
Outdated
Show resolved
Hide resolved
jywu-msft
reviewed
Dec 9, 2021
jywu-msft
approved these changes
Dec 9, 2021
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Modify code for removing compiler warning of C4244, C4267 and C4996 of TRT EP in order to comply with Service 360 security rules.
Here is the issue from BinSkim: https://msdata.visualstudio.com/DefaultCollection/Vienna/_workitems/edit/1523090/