#0: Fix failing test case for width sharded non-32 multiple output width #16224
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
sankarmanoj-tt
requested review from
mywoodstock,
shwetankTT and
pavlejosipovic
as code owners
sankarmanoj-tt
force-pushed
the
smanoj/fix_test_case_7
branch
from
8db5c45 to
41070e7
Compare
ttnn/cpp/ttnn/operations/conv/conv2d/prepare_conv2d_weights.cpp
Outdated
Show resolved
Hide resolved
|
It would be nice to remove this test case from |
sankarmanoj-tt
force-pushed
the
smanoj/fix_test_case_7
branch
from
41070e7 to
1007506
Compare
|
@pavlejosipovic I've added a UT. It exposed some more bugs, which I have also fixed. I removed the test from the sweep. |
sankarmanoj-tt
force-pushed
the
smanoj/fix_test_case_7
branch
from
83628b8 to
3f80dad
Compare
| @@ -191,6 +192,7 @@ Result conv2d( | |||
|
|
|||
| if (bypass_halo) { | |||
| if (input_tensor_post_tm.layout() == Layout::TILE) { | |||
| input_tensor_post_tm = ttnn::reshape(input_tensor_post_tm, input_tensor_post_tm.get_padded_shape()); | |||
There was a problem hiding this comment.
why do we need this reshape here?
There was a problem hiding this comment.
to_layout was not using the padded shape, and was instead using the logical shape. This was causing an error.
There was a problem hiding this comment.
at least we should log an issue with unit tests and reference it here.
Would be better if we can just fix to layout.
Halo with untialize is doing this properly?
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Outdated suggestions cannot be applied.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.
Problem description
tests/sweep_framework/sweeps/conv2d/short/conv2d_short_sweep.py::test_conv2d_localrun_fail_only[device_params0-input_spec7]test case fails.What's changed
Fixed width sharded weights preparation, where out_channels % 32 != 0
Checklist