TilerHelper and 2D Tiling Visualizations

[hunhoffe]

Description

This PR introduces some classes to help with data transformations/tiling and data visualization. The main classes introduced are:

• TensorTile: A class representing information for specifying a 'chunk' of data, suitable for use in describing a npu_dma_memcpy_nd operation; also includes code for visualizing the TensorTile.
• TensorTileSequence: A wrapper class for a list of TensorTiles; also includes code for visualization (including animations).
• TensorTiler2D: A class that helps with data tiling. Provides simple_tiler(), group_tiler(), and step_tiler() methods to aid in generating iterative patterns of tiling over the tensor.

I also include:

• A (non-exhaustive, but also not completely trivial) set of tests in test/python/tensortiler
• A minor edit of a few programming examples (dma_transpose, matrix_scalar_add, row_wise_bias_add matrxi_multiplication/whole_array) to show how to use the TensorTiler2D
• Two new programming examples (in programming_examples/basic/tiling_exploration) and an introductory notebook that use the device to create an access order map that can be compared to the map provided by the TensorTiler2D. These examples are meant to verify the TensorTiler2D can produce valid access patterns but also illustrate how to use the tensor tiling code.
• A change to npu_dma_memcpy_nd to support taking a TensorTile directly instead of sizes/strides/offset

Some incidental things that got included in this PR:

• First programming example with no inputs, only an output, which required some minor changes to support

Note for future contributions

• Visualization of transformation chaining (e.g., toStream AND fromStream w/ ObjectFIFOLink)
• Helper class for transformation chaining?
• Support for overlapping data patterns (e.g., image transforms)
• Integration of visualization into runtime sequence and/or memtile data movement.

Notes

Credit to Andre for his really excellent tool here: https://andreroesti.com/data-layout-viz/data_layout.html
This is my attempt at making something similar that can be integrated into a development tool directly, with the additional step of generating sizes/strides for you.

[github-actions]

Coverage Report

Created: 2024-10-25 14:52

Click here for information about interpreting this report.

Filename	Function Coverage	Line Coverage	Region Coverage	Branch Coverage
IR/AIEXDialect.cpp	100.00%	86.12%	88.69%	79.79%
Transforms/AIEDmaToNpu.cpp	100.00%	91.00%	85.61%	73.26%
Totals	100.00%	88.47%	87.68%	77.74%

Generated by llvm-cov -- llvm version 14.0.0

[fifield]

How hard is it to generalize from 2d?

[hunhoffe]

@fifield Great question but I'm not sure... This needs some work before it's ready for merge due to some complexities with translating between the sizes/strides generated by the TensorTiler2D and the limitations in sizes/sizes allowed by the hardware.

My plan right now is to get a bit more confident about the problem space in 2D (which is also easier to visualize) before moving on to something more complex.

[hunhoffe]

CI is currently failing because lit test for notebooks assumes dependencies which are only added in #1909

[jgmelber]

One nitpick would be to add an overall README to the tiling_exploration programming example directory.

[hunhoffe]

Notes:

• Will have follow-on PR for better Python documentation (Add python documentation to TensorTiler source code #1923)
• Started follow-on PR for checking/benchmarking mat mul whole array implementation using tiler to generate sizes/strides (Mat mul whole array implementation using tiler helper tools #1924)