-
Notifications
You must be signed in to change notification settings - Fork 608
Qualcomm AI Engine Direct - gpu support part1 #12165
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.
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
Open
haowhsu-quic
wants to merge
1
commit into
pytorch:main
Choose a base branch
from
CodeLinaro:dev_gpu_infra
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+901
−90
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,62 @@ | ||
| /* | ||
| * Copyright (c) Qualcomm Innovation Center, Inc. | ||
| * All rights reserved. | ||
| * | ||
| * This source code is licensed under the BSD-style license found in the | ||
| * LICENSE file in the root directory of this source tree. | ||
| */ | ||
|
|
||
| #include <executorch/backends/qualcomm/runtime/backends/gpu/GpuBackend.h> | ||
|
|
||
| #include "GPU/QnnGpuCommon.h" | ||
|
|
||
| namespace executorch { | ||
| namespace backends { | ||
| namespace qnn { | ||
|
|
||
| using executorch::runtime::Error; | ||
|
|
||
| GpuBackend::GpuBackend( | ||
| const QnnImplementation& implementation, | ||
| QnnLogger* logger, | ||
| const QnnExecuTorchGpuBackendOptions* gpu_options) | ||
| : QnnBackend(implementation, logger) { | ||
| gpu_backend_custom_config_ = | ||
| std::make_unique<GpuBackendCustomConfig>(gpu_options); | ||
| } | ||
|
|
||
| Qnn_Version_t GpuBackend::GetExpectedBackendVersion() const { | ||
| Qnn_Version_t backend_version; | ||
| backend_version.major = QNN_GPU_API_VERSION_MAJOR; | ||
| backend_version.minor = QNN_GPU_API_VERSION_MINOR; | ||
| backend_version.patch = QNN_GPU_API_VERSION_PATCH; | ||
| return backend_version; | ||
| } | ||
|
|
||
| bool GpuBackend::IsProfileEventTypeParentOfNodeTime( | ||
| QnnProfile_EventType_t event_type) { | ||
| return (event_type == QNN_PROFILE_EVENTTYPE_EXECUTE); | ||
| } | ||
|
|
||
| Error GpuBackend::MakeConfig(std::vector<const QnnBackend_Config_t*>& config) { | ||
| const std::vector<QnnBackend_CustomConfig_t>& backend_custom_config = | ||
| gpu_backend_custom_config_->CreateBackendCustomConfig(); | ||
|
|
||
| uint32_t num_custom_configs = backend_custom_config.size(); | ||
| backend_config_.resize(num_custom_configs); | ||
| // +1 for null terminated | ||
| config.reserve(num_custom_configs + 1); | ||
|
|
||
| for (std::size_t i = 0; i < num_custom_configs; ++i) { | ||
| backend_config_[i].option = QNN_BACKEND_CONFIG_OPTION_CUSTOM; | ||
| backend_config_[i].customConfig = backend_custom_config[i]; | ||
| config.push_back(&backend_config_[i]); | ||
| } | ||
|
|
||
| config.push_back(nullptr); | ||
| return Error::Ok; | ||
| } | ||
|
|
||
| } // namespace qnn | ||
| } // namespace backends | ||
| } // namespace executorch |
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,40 @@ | ||
| /* | ||
| * Copyright (c) Qualcomm Innovation Center, Inc. | ||
| * All rights reserved. | ||
| * | ||
| * This source code is licensed under the BSD-style license found in the | ||
| * LICENSE file in the root directory of this source tree. | ||
| */ | ||
|
|
||
| #pragma once | ||
|
|
||
| #include <executorch/backends/qualcomm/runtime/backends/gpu/GpuBackendCustomConfig.h> | ||
|
|
||
| namespace executorch { | ||
| namespace backends { | ||
| namespace qnn { | ||
|
|
||
| class GpuBackend : public QnnBackend { | ||
| public: | ||
| GpuBackend( | ||
| const QnnImplementation& implementation, | ||
| QnnLogger* logger, | ||
| const QnnExecuTorchGpuBackendOptions* gpu_options); | ||
|
|
||
| Qnn_Version_t GetExpectedBackendVersion() const override; | ||
|
|
||
| bool IsProfileEventTypeParentOfNodeTime( | ||
| QnnProfile_EventType_t event_type) override; | ||
|
|
||
| protected: | ||
| executorch::runtime::Error MakeConfig( | ||
| std::vector<const QnnBackend_Config_t*>& config) override; | ||
|
|
||
| private: | ||
| std::vector<QnnBackend_Config_t> backend_config_; | ||
| std::unique_ptr<GpuBackendCustomConfig> gpu_backend_custom_config_; | ||
| }; | ||
|
|
||
| } // namespace qnn | ||
| } // namespace backends | ||
| } // namespace executorch |
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm slightly worried about the runtime size increase, that usually is a requirement for production. Do we know how much size increase with this PR? If I have a model runs on HTP only, can the runtime include HTP only?