Alternative approach to handling memory offset shift #9406
Merged
Conversation
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
JakeStevens
requested review from
JacobSzwejbka,
lucylq and
swolchok
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9406
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 7cdc42b with merge base 7159650 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D71488571 |
Contributor
|
this looks fine, but I'll be surprised if it continues to get rid of the warning |
swolchok
approved these changes
Mar 19, 2025
Contributor
Author
|
@pytorchbot label "topic: not user facing" |
JakeStevens
force-pushed
the
export-D71488571
branch
from
0583a8b to
65e5b87
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 21, 2025
Summary:
To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to:
```
memory_offset |= static_cast<size_t>(memory_offset_high)
<< (sizeof(size_t) - sizeof(uint32_t));
```
This fails for build of OSS qwen example however.
Instead, we modify to add a check for
```
sizeof(size_t) > sizeof(uint32_t)
```
in the conditional instead of changing the computation.
In our builds of interest, this compiles away the if branch
Reviewed By: digantdesai, swolchok, dpalmasan
Differential Revision: D71488571
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D71488571 |
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 21, 2025
Summary: Pull Request resolved: pytorch#9406 To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to: ``` memory_offset |= static_cast<size_t>(memory_offset_high) << (sizeof(size_t) - sizeof(uint32_t)); ``` This fails for build of OSS qwen example however. Instead, we modify to add a check for ``` sizeof(size_t) > sizeof(uint32_t) ``` in the conditional instead of changing the computation. In our builds of interest, this compiles away the if branch Reviewed By: digantdesai, swolchok, dpalmasan Differential Revision: D71488571
JakeStevens
force-pushed
the
export-D71488571
branch
2 times, most recently
from
c6c43b5 to
da6c3e3
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 24, 2025
Summary:
To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to:
```
memory_offset |= static_cast<size_t>(memory_offset_high)
<< (sizeof(size_t) - sizeof(uint32_t));
```
This fails for build of OSS qwen example however.
Instead, we modify to add a check for
```
sizeof(size_t) > sizeof(uint32_t)
```
in the conditional instead of changing the computation.
In our builds of interest, this compiles away the if branch
Reviewed By: digantdesai, swolchok, dpalmasan
Differential Revision: D71488571
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D71488571 |
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 24, 2025
Summary: Pull Request resolved: pytorch#9406 To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to: ``` memory_offset |= static_cast<size_t>(memory_offset_high) << (sizeof(size_t) - sizeof(uint32_t)); ``` This fails for build of OSS qwen example however. Instead, we modify to add a check for ``` sizeof(size_t) > sizeof(uint32_t) ``` in the conditional instead of changing the computation. In our builds of interest, this compiles away the if branch Reviewed By: digantdesai, swolchok, dpalmasan Differential Revision: D71488571
JakeStevens
force-pushed
the
export-D71488571
branch
from
da6c3e3 to
8dbe71f
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 24, 2025
Summary:
To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to:
```
memory_offset |= static_cast<size_t>(memory_offset_high)
<< (sizeof(size_t) - sizeof(uint32_t));
```
This fails for build of OSS qwen example however.
Instead, we modify to add a check for
```
sizeof(size_t) > sizeof(uint32_t)
```
in the conditional instead of changing the computation.
In our builds of interest, this compiles away the if branch
Reviewed By: digantdesai, swolchok, dpalmasan
Differential Revision: D71488571
JakeStevens
force-pushed
the
export-D71488571
branch
from
8dbe71f to
d6c9092
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D71488571 |
JakeStevens
force-pushed
the
export-D71488571
branch
from
d6c9092 to
9f274c3
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 25, 2025
Summary:
To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to:
```
memory_offset |= static_cast<size_t>(memory_offset_high)
<< (sizeof(size_t) - sizeof(uint32_t));
```
This fails for build of OSS qwen example however.
Instead, we modify to add a check for
```
sizeof(size_t) > sizeof(uint32_t)
```
in the conditional instead of changing the computation.
In our builds of interest, this compiles away the if branch
Reviewed By: digantdesai, swolchok, dpalmasan
Differential Revision: D71488571
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D71488571 |
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 25, 2025
Summary: Pull Request resolved: pytorch#9406 To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to: ``` memory_offset |= static_cast<size_t>(memory_offset_high) << (sizeof(size_t) - sizeof(uint32_t)); ``` This fails for build of OSS qwen example however. Instead, we modify to add a check for ``` sizeof(size_t) > sizeof(uint32_t) ``` in the conditional instead of changing the computation. In our builds of interest, this compiles away the if branch Reviewed By: digantdesai, swolchok, dpalmasan Differential Revision: D71488571
JakeStevens
force-pushed
the
export-D71488571
branch
2 times, most recently
from
53db757 to
fc27c40
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Mar 26, 2025
Summary:
To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to:
```
memory_offset |= static_cast<size_t>(memory_offset_high)
<< (sizeof(size_t) - sizeof(uint32_t));
```
This fails for build of OSS qwen example however.
Instead, we modify to add a check for
```
sizeof(size_t) > sizeof(uint32_t)
```
in the conditional instead of changing the computation.
In our builds of interest, this compiles away the if branch
Reviewed By: digantdesai, swolchok, dpalmasan
Differential Revision: D71488571
Summary: Pull Request resolved: pytorch#9406 To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to: ``` memory_offset |= static_cast<size_t>(memory_offset_high) << (sizeof(size_t) - sizeof(uint32_t)); ``` This fails for build of OSS qwen example however. Instead, we modify to add a check for ``` sizeof(size_t) > sizeof(uint32_t) ``` in the conditional instead of changing the computation. In our builds of interest, this compiles away the if branch Reviewed By: digantdesai, swolchok, dpalmasan Differential Revision: D71488571
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D71488571 |
JakeStevens
force-pushed
the
export-D71488571
branch
from
fc27c40 to
7cdc42b
Compare
kirklandsign
pushed a commit
that referenced
this pull request
Apr 11, 2025
Summary:
To support embedded system builds which threw an error on the warning
for left shift by 32 on a 32 bit dtype, the code was modified to:
```
memory_offset |= static_cast<size_t>(memory_offset_high)
<< (sizeof(size_t) - sizeof(uint32_t));
```
This fails for build of OSS qwen example however.
Instead, we modify to add a check for
```
sizeof(size_t) > sizeof(uint32_t)
```
in the conditional instead of changing the computation.
In our builds of interest, this compiles away the if branch
Reviewed By: digantdesai, dpalmasan
Differential Revision: D71488571
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Summary:
To support embedded system builds which threw an error on the warning for left shift by 32 on a 32 bit dtype, the code was modified to:
This fails for build of OSS qwen example however.
Instead, we modify to add a check for
in the conditional instead of changing the computation.
In our builds of interest, this compiles away the if branch
Reviewed By: digantdesai, dpalmasan
Differential Revision: D71488571