[BYOC] [ACL] 20.05 memory corruption temporarely fix #6724
Merged
Conversation
This file contains 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
d-smirnov
force-pushed
the
acl_memory_corruption_fix
branch
from
a123536
to
d29e765
Compare
|
@merrymercy Please advise on failed Integration Test / docs: GPU. I cannot reproduce failure of tutorials/auto_scheduler/tune_matmul_x86.py locally |
|
See #6723 |
ZihengJiang
added
status: need review
status: need update
d-smirnov
force-pushed
the
acl_memory_corruption_fix
branch
from
d29e765
to
701b42b
Compare
lhutton1
reviewed
Oct 22, 2020
|
@lhutton Some operations of ACL up to 20.11 requires data to be vector-friendly. In squeezenet there is an avg_pool2d operator with specific tensor layout ((1, 13, 13, 1001), float32). |
Makes sense, thanks for the clarification :) |
d-smirnov
force-pushed
the
acl_memory_corruption_fix
branch
from
701b42b
to
ad7d495
Compare
comaniac
approved these changes
Nov 5, 2020
This workaround prevents execution of operations via ACL runtime in case if arguments or output tensor require memory padding. Workaround is applicable to all ACL versions prior forecoming ACL 20.11 (which will not use data padding).
d-smirnov
force-pushed
the
acl_memory_corruption_fix
branch
from
34530e7
to
d99e6d5
Compare
|
Thanks @d-smirnov @lhutton1 |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 2, 2020
This workaround prevents execution of operations via ACL runtime in case if arguments or output tensor require memory padding. Workaround is applicable to all ACL versions prior forecoming ACL 20.11 (which will not use data padding).
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 4, 2020
This workaround prevents execution of operations via ACL runtime in case if arguments or output tensor require memory padding. Workaround is applicable to all ACL versions prior forecoming ACL 20.11 (which will not use data padding).
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Dec 4, 2020
This workaround prevents execution of operations via ACL runtime in case if arguments or output tensor require memory padding. Workaround is applicable to all ACL versions prior forecoming ACL 20.11 (which will not use data padding).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This fix intended to prevent execution of operations via ACL runtime
in case if its arguments require memory padding. This fix is tempоrary
and intended for ACL 20.05 and should be removed after migration
to ACL 20.11