Skip to content

[ETHOSN] Fix for the mock inference after NPU driver update #13650

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
merged 1 commit into from
Dec 21, 2022
Merged

[ETHOSN] Fix for the mock inference after NPU driver update #13650

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion src/runtime/contrib/ethosn/ethosn_device.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,7 +272,7 @@ TVM_REGISTER_GLOBAL("relay.ethos-n.test.infra.inference_result")
// Allow the ethos-n support code to be tested without a device
bool Inference(tvm::runtime::TVMArgs args,
#ifdef _ETHOSN_API_VERSION_3_2_0
dl::ProcMemAllocator* proc_mem_alloc,
dl::ProcMemAllocator* /*proc_mem_alloc*/,
#endif
dl::Network* /* npu */, const std::vector<uint32_t>& input_order,
const std::vector<uint32_t>& output_order, const std::vector<uint32_t>& input_sizes,
Expand Down
4 changes: 1 addition & 3 deletions src/runtime/contrib/ethosn/ethosn_runtime.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,9 +114,6 @@ Module EthosnModule::LoadFromBinary(void* strm) {
cmms.resize(func_count);
for (unsigned int i = 0; i < func_count; i++) {
OrderedCompiledNetwork& compiled = cmms[i];
#ifdef _ETHOSN_API_VERSION_3_2_0
compiled.proc_mem_alloc = std::make_unique<dl::ProcMemAllocator>();
#endif
std::string ext_symbol;
std::string cmm;
uint64_t input_size;
Expand All @@ -130,6 +127,7 @@ Module EthosnModule::LoadFromBinary(void* strm) {
// If hardware unavaiable use the mock inference functionality. If hardware is
// avaiable, deserialize the compiled graph.
#ifdef _ETHOSN_API_VERSION_3_2_0
compiled.proc_mem_alloc = std::make_unique<dl::ProcMemAllocator>();
compiled.runtime_cmm = std::make_unique<dl::Network>(
compiled.proc_mem_alloc->CreateNetwork(cmm.c_str(), cmm.size()));
#else
Expand Down