Skip to content

Use temp allocator for kernel registry #13012

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JakeStevens merged 1 commit into from
Aug 6, 2025
Merged

Use temp allocator for kernel registry #13012

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions runtime/executor/method.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -670,7 +670,7 @@ Error Method::resolve_operator(
size_t kernel_index,
InstructionArgs args,
size_t n_args) {
// TODO(T153505381, T153506819) Investigate optimizing this function for both
// TODO(T153506819) Investigate optimizing this function for both
// space and time.

// resolve name
Expand All @@ -691,8 +691,16 @@ Error Method::resolve_operator(
}

// resolve tensor meta
auto method_allocator = memory_manager_->method_allocator();
TensorMeta* meta = method_allocator->allocateList<TensorMeta>(n_args);
// Since temp allocator can be freed, we optimistically
// try to use that allocator first.
auto allocator = memory_manager_->temp_allocator();
// However, it does not have to be provided, so if it
// is not provided (or an empty one is provided), we
// fall back to the method allocator.
if (allocator == nullptr || allocator->size() == 0) {
allocator = memory_manager_->method_allocator();
}
TensorMeta* meta = allocator->allocateList<TensorMeta>(n_args);
if (meta == nullptr) {
return Error::MemoryAllocationFailed;
}
Expand All @@ -705,8 +713,7 @@ Error Method::resolve_operator(
auto tensor = eval->toTensor();
meta[count].dtype_ = tensor.scalar_type();
executorch::aten::DimOrderType* dim_order_ptr =
method_allocator->allocateList<executorch::aten::DimOrderType>(
tensor.dim());
allocator->allocateList<executorch::aten::DimOrderType>(tensor.dim());
if (dim_order_ptr == nullptr) {
return Error::MemoryAllocationFailed;
}
Expand Down
Loading