Skip to content

Add SoC SXR2250P #8148

New issue

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

#

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

Already on GitHub? # to your account

Jump to bottom
Merged
merged 1 commit into from
Feb 11, 2025
Merged

Add SoC SXR2250P #8148

merged 1 commit into from
Feb 11, 2025

Conversation

cccclai
Copy link
Contributor

@cccclai cccclai commented Feb 3, 2025

Differential Revision: D69063201

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Feb 3, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8148

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 5fea01d with merge base 70143a2 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Feb 3, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Feb 3, 2025
@cccclai @facebook-github-bot
Add SoC SXR2250P (pytorch#8148)
e0c023a 
Summary:


As title, need to support SoC SXR2250P

Differential Revision: D69063201
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

@cccclai cccclai added the release notes: qualcomm Changes to the Qualcomm backend delegate label Feb 3, 2025
@cccclai
Copy link
Contributor Author

cccclai commented Feb 3, 2025

I may need some help to figure out the exact config for the SoC SXR2250P..

winskuo-quic
winskuo-quic reviewed Feb 4, 2025
View reviewed changes
backends/qualcomm/serialization/qc_schema.py Outdated
@@ -60,6 +61,7 @@ class SocInfo:
QcomChipset.SM8750: SocInfo(QcomChipset.SM8750, HtpInfo(HtpArch.V79, 8)),
QcomChipset.SSG2115P: SocInfo(QcomChipset.SSG2115P, HtpInfo(HtpArch.V73, 2)),
QcomChipset.SA8295: SocInfo(QcomChipset.SA8295, HtpInfo(HtpArch.V68, 8)),
QcomChipset.SXR2250P: SocInfo(QcomChipset.SXR2250P, HtpInfo(HtpArch.V68, 8)),
Copy link
Collaborator

Choose a reason for hiding this comment

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

This should be v69

backends/qualcomm/serialization/qc_compiler_spec.fbs Outdated
@@ -39,6 +39,7 @@ enum QcomChipset: int {
SM8650 = 57,
SA8295 = 39,
SM8750 = 69
SXR2250P = 36,
Copy link
Collaborator

Choose a reason for hiding this comment

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

Could you try 53? Thanks

backends/qualcomm/serialization/qc_schema.py Outdated
@@ -44,6 +44,7 @@ class QcomChipset(IntEnum):
SM8650 = 57 # v75
SA8295 = 39 # v68
SM8750 = 69 # v79
SXR2250P = 42 # v69
Copy link
Collaborator

Choose a reason for hiding this comment

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

Also 53 for this.

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Feb 4, 2025
@cccclai @facebook-github-bot
Add SoC SXR2250P (pytorch#8148)
7dd2967 
Summary:


As title, need to support SoC SXR2250P

Differential Revision: D69063201
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Feb 4, 2025
@cccclai @facebook-github-bot
Add SoC SXR2250P (pytorch#8148)
611cdb7 
Summary:


As title, need to support SoC SXR2250P

Differential Revision: D69063201
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Feb 7, 2025
@cccclai @facebook-github-bot
Add SoC SXR2250P (pytorch#8148)
13b0e76 
Summary:


As title, need to support SoC SXR2250P

Differential Revision: D69063201
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

@cccclai
Copy link
Contributor Author

cccclai commented Feb 7, 2025

@winskuo-quic I added a few more SoCs to support, but not sure some of the specs. Can I get some help with this?

winskuo-quic
winskuo-quic reviewed Feb 7, 2025
View reviewed changes
Copy link
Collaborator

@winskuo-quic winskuo-quic left a comment •
edited
Loading

Choose a reason for hiding this comment

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

Hi @cccclai,
I think SXR2250P is a variant of SXR2230P, and their DspArch and VTCM size should be the same. Could you try it on your side and see if compiling SXR2250P using -m SXR2230P works?
Thanks.

backends/qualcomm/serialization/qc_compiler_spec.fbs Outdated
SXR1230P = x,
SXR2230P = x,
SXR2250P = 53
SSG2125P = x
Copy link
Collaborator

Choose a reason for hiding this comment

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

SXR1230P = 45,
SXR2230P = 53,
SSG2125P = 58,

SXR2230P and SXR2250P are both 53. I think we could keep SXR2230P = 53 here and remove SXR2550P since SXR2550P is a variant of SXR2230P

backends/qualcomm/serialization/qc_schema.py Outdated
SXR2230P = 1 # place holder
SSG2115P = 1 # place holder
SSG2125P = 1 # place holder
SXR2250P = 53 # v69
Copy link
Collaborator

Choose a reason for hiding this comment

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

SXR1230P = 45,
SXR2230P = 53,
SSG2125P = 58,

SSG2115P is duplicate
Also consider remove SXR2250P and keep SXR2230P = 53 due to the same reason above

backends/qualcomm/serialization/qc_schema.py
QcomChipset.SXR1230P: SocInfo(QcomChipset.SXR1230P, HtpInfo(HtpArch.V69, 8)),
QcomChipset.SXR2230P: SocInfo(QcomChipset.SXR2230P, HtpInfo(HtpArch.V69, 8)),
QcomChipset.SSG2125P: SocInfo(QcomChipset.SSG2125P, HtpInfo(HtpArch.V69, 8)),
QcomChipset.SXR2250P: SocInfo(QcomChipset.SXR2250P, HtpInfo(HtpArch.V69, 8)),
}
Copy link
Collaborator

Choose a reason for hiding this comment

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

QcomChipset.SXR2250P: SocInfo(QcomChipset.SXR2250P, HtpInfo(HtpArch.V69, 8)),
QcomChipset.SXR1230P: SocInfo(QcomChipset.SXR1230P, HtpInfo(HtpArch.V73, 2)),
QcomChipset.SXR2230P: SocInfo(QcomChipset.SXR2230P, HtpInfo(HtpArch.V69, 8)),
QcomChipset.SSG2125P: SocInfo(QcomChipset.SSG2125P, HtpInfo(HtpArch.V73, 2)),

QcomChipset.SXR2250P is dupicate.
Also consider remove SXR2250P and keep SXR2230P due to the same reason above.

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Feb 7, 2025
@cccclai @facebook-github-bot
Add SoC SXR2250P (pytorch#8148)
0b7929f 
Summary:


As title, need to support SoC SXR2250P

Differential Revision: D69063201
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

@cccclai
Copy link
Contributor Author

cccclai commented Feb 7, 2025

@winskuo-quic yes it works! I use SXR2230P and model add.pte can be executed

I 00:00:00.000172 executorch:qnn_executor_runner.cpp:160] Model file add.pte is loaded.
I 00:00:00.000201 executorch:qnn_executor_runner.cpp:170] Using method forward
I 00:00:00.000210 executorch:qnn_executor_runner.cpp:217] Setting up planned buffer 0, size 48.
[INFO] [Qnn ExecuTorch]: Deserializing processed data using QnnContextCustomProtocol
[INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
[WARNING] [Qnn ExecuTorch]:  <W> Initializing HtpProvider

[WARNING] [Qnn ExecuTorch]:  <W> Function not called, PrepareLib isn't loaded!

[INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
[INFO] [Qnn ExecuTorch]: Caching: Caching is in RESTORE MODE.
[INFO] [Qnn ExecuTorch]: QnnContextCustomProtocol expected magic number: 0x5678abcd but get: 0x2000000
[WARNING] [Qnn ExecuTorch]:  <W> Specified config SOC, ignoring on real target

[WARNING] [Qnn ExecuTorch]:  <W> Function not called, PrepareLib isn't loaded!

[WARNING] [Qnn ExecuTorch]:  <W> Function not called, PrepareLib isn't loaded!

[INFO] [Qnn ExecuTorch]: Running level=3 optimization.
I 00:00:00.134639 executorch:qnn_executor_runner.cpp:241] Method loaded.
E 00:00:00.134655 executorch:method.cpp:1056] Output 0 is memory planned, or is a constant. Cannot override the existing data pointer.
I 00:00:00.134665 executorch:qnn_executor_runner.cpp:301] ignoring error from set_output_data_ptr(): 0x2
I 00:00:00.134669 executorch:qnn_executor_runner.cpp:304] Inputs prepared.
I 00:00:00.134709 executorch:qnn_executor_runner.cpp:447] Input list not provided. Inputs prepared with default values set.
I 00:00:00.135125 executorch:qnn_executor_runner.cpp:454] Model executed successfully.
[INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters
[INFO] [Qnn ExecuTorch]: Destroy Qnn context
[INFO] [Qnn ExecuTorch]: Destroy Qnn device

@cccclai
Copy link
Contributor Author

cccclai commented Feb 10, 2025

@winskuo-quic if this PR looks good to you, mind approving it?

winskuo-quic
winskuo-quic approved these changes Feb 11, 2025
View reviewed changes
Copy link
Collaborator

@winskuo-quic winskuo-quic left a comment

Choose a reason for hiding this comment

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

LGTM. Thanks

@winskuo-quic
Copy link
Collaborator

@winskuo-quic if this PR looks good to you, mind approving it?

Sorry. Forgot to press approve when leaving the comments.

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Feb 11, 2025
@cccclai @facebook-github-bot
Add SoC SXR1230P, SXR2230P, SSG2125P (pytorch#8148)
6ade125 
Summary:


As title, need to support SoC SXR2250P

Differential Revision: D69063201
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

@cccclai @facebook-github-bot
Add SoC SXR1230P, SXR2230P, SSG2125P (pytorch#8148)
5fea01d 
Summary:


As title, need to support SoC SXR2250P

Differential Revision: D69063201
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69063201

@facebook-github-bot facebook-github-bot merged commit 2f0a6c7 into pytorch:main Feb 11, 2025
46 of 47 checks passed
This was referenced Feb 11, 2025
Open
Open
This was referenced Feb 24, 2025
Open
Open
@nirvanagth nirvanagth mentioned this pull request Mar 5, 2025
Open
# for free to join this conversation on GitHub. Already have an account? # to comment
Reviewers

@billmguo billmguo billmguo approved these changes

@kirklandsign kirklandsign kirklandsign approved these changes

@winskuo-quic winskuo-quic winskuo-quic approved these changes

@chunit-quic chunit-quic Awaiting requested review from chunit-quic

@haowhsu-quic haowhsu-quic Awaiting requested review from haowhsu-quic

@shewu-quic shewu-quic Awaiting requested review from shewu-quic

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported release notes: qualcomm Changes to the Qualcomm backend delegate
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@cccclai @facebook-github-bot @winskuo-quic @billmguo @kirklandsign