Skip to content

[mlir][tensor] Add tests to invalid.mlir (nfc) #112759

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 18, 2024
Merged

[mlir][tensor] Add tests to invalid.mlir (nfc) #112759

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4fc2c29
[mlir][tensor] Add tests to invalid.mlir
banach-space Oct 17, 2024
ff2ce65
fixup! [mlir][tensor] Add tests to invalid.mlir
banach-space Oct 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 29 additions & 8 deletions mlir/test/Dialect/Tensor/invalid.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,6 +213,27 @@ func.func @extract_slice_wrong_result_rank(%t: tensor<?xf32>, %idx : index) {
return
}


// -----

func.func @extract_slice_size_and_output_dim_mismatch_static_size(%t: tensor<16xf32>) {
// expected-error @+1 {{expected type to be 'tensor<4xf32>' or a rank-reduced version. (size mismatch)}}
%0 = tensor.extract_slice %t[0][4][1]
: tensor<16xf32> to tensor<6xf32>

Copy link
Contributor

@javedabsar1 javedabsar1 Oct 17, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why the empty line above return? I see pre-existing above had same. But these are not needed i suppose.

Copy link
Contributor Author

@banach-space banach-space Oct 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That's now fixed, thanks!

return
}

// -----

func.func @extract_slice_size_and_output_dim_mismatch_dynamic_size(%t: tensor<?xf32>, %idx : index) {
// expected-error @+2 {{expected type to be 'tensor<?xf32>' or a rank-reduced version. (size mismatch)}}
%c4 = arith.constant 4 : index
%0 = tensor.extract_slice %t[0][%c4][1] : tensor<?xf32> to tensor<4xi8>
Copy link
Contributor

@javedabsar1 javedabsar1 Oct 17, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ok I think i am missing something here which maybe you need to explain just for my sake. Above is not rank-reduced case.%c4 is 4. Is it that the result type is still expected to be tensor<?x4> because value of '4' is not rolled into the extract_slice type deduction so to say.

Copy link
Contributor Author

@banach-space banach-space Oct 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hopefully this will clarify things a little bit:

Importantly, this PR merely documents the current behaviour. And, I might be sending more following the Discourse post :)

Please let me know if this is still unclear 😅

Copy link
Contributor

@javedabsar1 javedabsar1 Oct 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Had to ask, am kind of glad I asked actually because now is understand the problem. Thanks - "PR merely documents the current behaviour."


return
}

// -----

func.func @extract_slice_wrong_static_type(%t: tensor<8x16x4xf32>, %idx : index) {
Expand All @@ -235,6 +256,14 @@ func.func @extract_slice_wrong_dynamic_type(%t: tensor<8x16x4xf32>, %idx : index

// -----

func.func @illegal_num_offsets(%arg0 : tensor<?x?x?xf32>, %arg1 : index, %arg2 : index) {
// expected-error@+1 {{expected 3 offset values}}
%0 = tensor.extract_slice %arg0[0, 0] [%arg1, %arg2] [1, 1] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
return
}

// -----

func.func @insert_slice_wrong_result_rank(%t1: tensor<?xf32>, %t2: tensor<?x?xf32>, %idx : index) {
// expected-error @+1 {{expected rank to be smaller or equal to the other rank.}}
%0 = tensor.insert_slice %t2 into %t1[0][4][1] : tensor<?x?xf32> into tensor<?xf32>
Expand Down Expand Up @@ -349,14 +378,6 @@ func.func @rank(%0: f32) {

// -----

func.func @illegal_num_offsets(%arg0 : tensor<?x?x?xf32>, %arg1 : index, %arg2 : index) {
// expected-error@+1 {{expected 3 offset values}}
%0 = tensor.extract_slice %arg0[0, 0] [%arg1, %arg2] [1, 1] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
return
}

// -----

func.func @illegal_num_offsets(%arg0 : tensor<?x?xf32>, %arg1 : tensor<?x?x?xf32>,
%arg2 : index, %arg3 : index) {
// expected-error@+1 {{expected 3 offset values}}
Expand Down
Loading