#0: Port all Misc ops to use TensorSpec #15509
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
sminakov-tt
changed the title
sminakov-tt
changed the title
sminakov-tt
requested review from
ayerofieiev-tt,
dmakoviichuk-tt,
rfurko-tt,
cfjchu,
TT-BrianLiu,
razorback3,
dongjin-na,
yugaoTT,
tt-aho,
bbradelTT,
asandhupatlaTT,
sjameelTT,
mywoodstock,
shwetankTT,
sankarmanoj-tt and
pavlejosipovic
as code owners
bbradelTT
approved these changes
Nov 27, 2024
ayerofieiev-tt
approved these changes
Nov 27, 2024
tt-aho
approved these changes
Nov 28, 2024
yugaoTT
approved these changes
Nov 28, 2024
bbradelTT
approved these changes
Dec 2, 2024
| ceil((double)img_width / (double)img_stride_w); | ||
| uint32_t output_height = tt::round_up(output_height_unpadded, TILE_HEIGHT); | ||
| uint32_t output_width = input_tensor_a.get_legacy_shape()[3]; | ||
| auto output_padding = |
There was a problem hiding this comment.
Seems like this op was trying to encode padding info in it's output tensor, how is handled now?
There was a problem hiding this comment.
This computation is not needed anymore. It is now properly handled by tensor layout.
There was a problem hiding this comment.
Ok I'll trust you on that
pavlejosipovic
approved these changes
Dec 4, 2024
yieldthought
pushed a commit
that referenced
this pull request
Dec 13, 2024
### Ticket ### Problem description We need to migrate all ops to use `compute_output_specs` with TensorSpec, instead of older `compute_output_shapes` ### What's changed Migrated all misc ops to TensorSpec Minor infra upgrades to support the migration. ### Checklist - [x] [Post commit CI passes](https://github.com/tenstorrent/tt-metal/actions/runs/12057375995) - [x] [(Single-card) Demo tests](https://github.com/tenstorrent/tt-metal/actions/runs/12133160610) - [x] [(Single-card) Model perf tests](https://github.com/tenstorrent/tt-metal/actions/runs/12133156506) - [x] [(Single-card) Device perf regressions](https://github.com/tenstorrent/tt-metal/actions/runs/12146782009) - [x] New/Existing tests provide coverage for changes
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.
Ticket
Problem description
We need to migrate all ops to use
compute_output_specswithTensorSpec, instead of older
compute_output_shapesWhat's changed
Migrated all misc ops to TensorSpec
Minor infra upgrades to support the migration.
Checklist