Variable size transpose ukernels are treated as 1d ukernels. They are inherently 2d ukernels, element size contains one dimensions. When the input or output dimension is strided, then adding element size to input pointer in the outer loop will no longer point to the next element.

[copybara-service[bot]]

Variable size transpose ukernels are treated as 1d ukernels. They are inherently 2d ukernels, element size contains one dimensions. When the input or output dimension is strided, then adding element size to input pointer in the outer loop will no longer point to the next element.