saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-04 23:59:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Minor optimization: if a node has already been placed, there's no need to find a kernel for it. (#2417)

Browse source
This commit is contained in:
Pranav Sharma 2019-11-17 20:08:33 -08:00 committed by GitHub
parent 5ab7041fa7
commit f268e69c79
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
onnxruntime/core/providers/cuda/cuda_execution_provider.cc
View file

@ -1204,8 +1204,9 @@ CUDAExecutionProvider::GetCapability(const onnxruntime::GraphViewer& graph,
continue;
const auto& node = *p_node;
const auto* cuda_kernel_def = GetKernelRegistry()->TryFindKernel(node, Type());
if (cuda_kernel_def == nullptr || !node.GetExecutionProviderType().empty()) {
const KernelCreateInfo* cuda_kernel_def = nullptr;
if (!node.GetExecutionProviderType().empty() ||
!(cuda_kernel_def = GetKernelRegistry()->TryFindKernel(node, Type()))) {
// node is not in cuda exeuction provider if no kernel def found,
// or if other execution provider already assigned to it
defs_outside_cuda.insert(node.OutputDefs().cbegin(), node.OutputDefs().cend());