Skip to content
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

Add QNN Op package #1 #2840

Closed
wants to merge 1 commit into from
Closed

Conversation

jijoongmoon
Copy link
Collaborator

This PR adds the source code and directories for qualcomm npu op
support.
. nntrainer / npu / qnn

Self evaluation:

  1. Build test: [X]Passed [ ]Failed [ ]Skipped
  2. Run test: [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon [email protected]

This PR adds the source code and directories for qualcomm npu op
support.
 . nntrainer / npu / qnn

**Self evaluation:**
1. Build test:	 [X]Passed [ ]Failed [ ]Skipped
2. Run test:	 [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <[email protected]>
return assigned_int_key;
}

void ClContext::initBlasClKernels() {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this a temporary change due to excessive amount of code in all commits for QNN(including later PRs)?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This will be chaged in later PR.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I just check this comment.
I will skip to review the qnn_context for this PR.

@@ -45,6 +45,7 @@ option('enable-avx', type: 'boolean', value: true)
option('enable-opencl', type: 'boolean', value: false)
option('enable-biqgemm', type: 'boolean', value: false)
option('enable-benchmarks', type: 'boolean', value : false)
option('enable-qnn', type: 'boolean', value: true)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about setting the default value of enable-qnn as false?

Comment on lines +3 to +8
* Copyright (C) 2024 Debadri Samaddar <[email protected]>
*
* @file cl_context.h
* @date 23 Feb 2024
* @see https://github.com/nnstreamer/nntrainer
* @author Debadri Samaddar <[email protected]>
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It seems that you need to update the Copyright for this qnn_context.h


namespace nntrainer {

extern std::mutex cl_factory_mutex;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
extern std::mutex cl_factory_mutex;
extern std::mutex qnn_factory_mutex;


namespace nntrainer {

std::mutex cl_factory_mutex;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ditto.

Suggested change
std::mutex cl_factory_mutex;
std::mutex qnn_factory_mutex;

Comment on lines +15 to +16
#ifndef __CL_CONTEXT_H__
#define __CL_CONTEXT_H__
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It should be updated for qnn_context.h.

Suggested change
#ifndef __CL_CONTEXT_H__
#define __CL_CONTEXT_H__
#ifndef __QNN_CONTEXT_H__
#define __QNN_CONTEXT_H__

@jijoongmoon jijoongmoon deleted the qnn_package branch December 26, 2024 00:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants