Add constraints and runtime API to transpose #2322
Open
+192
−2
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
arminaleTT
requested review from
odjuricicTT,
tt-mpantic,
sdjordjevicTT,
svuckovicTT,
mtopalovicTT,
jserbedzijaTT,
jnie-TT and
azecevicTT
as code owners
odjuricicTT
approved these changes
Feb 28, 2025
| CreateTiledLayout(tensorShape, mlir::tt::ttnn::BufferType::L1, | ||
| mlir::tt::ttnn::TensorMemoryLayout::Interleaved); | ||
| auto legalExp = Device::getDeviceConstraints(workerGrid); | ||
| EXPECT_TRUE(static_cast<bool>(legalExp)); |
There was a problem hiding this comment.
Can you add one testcase where the provided layout is invalid?
azecevicTT
approved these changes
Feb 28, 2025
| assert(inputs.size() == 1); | ||
|
|
||
| const auto inputShape = | ||
| mlir::cast<RankedTensorType>(getOperand().getType()).getShape(); |
There was a problem hiding this comment.
You can use getInput().getType() (you can check the name of the operands/attributes in TTNNOps.td, for every operand you have an appropriately generated getter) and you will directly get the RankedTensorType, getOperand() is reserved for more generic uses where you don't know exactly the operation you are working on.
| assert(inputs.size() == 1); | ||
|
|
||
| const auto inputShape = | ||
| mlir::cast<RankedTensorType>(getOperand().getType()).getShape(); |
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Outdated suggestions cannot be applied.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
#2314
Problem description
The optimizer needs more ops with constraints and runtime support to be able to ingest real models. Transpose is useful for both rennet (#2277) and llama (#2084)
What's changed
Added constraints and runtime APIs to the
transposeOp. Added unit tests to exercise the new APICloses #2314
Checklist