commit | 0ba4d9e8721d3937e3f0d62504a37e0bd5fc99c3 | [log] [tgz] |
---|---|---|
author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | Thu Jan 27 20:19:18 2022 -0800 |
committer | GitHub <noreply@github.com> | Thu Jan 27 20:19:18 2022 -0800 |
tree | e017f7a3893ad4b51eaf5c185dad4a1e7454c5d1 | |
parent | e3ded855a4d6e15df14b7463c5a6314fcfcb6c94 [diff] |
Add a pass to propagate unsupported element type conversion. (#8173) With PR #8155, the buffer for tensor with unsupported element types (like i1, i2, etc.) are converted to use a supported element type through widening (and truncation if needed in future). This introduces arith.trunci and arith.extui operations to convert back and forth from the program representation in its original form. Propagate the use of supported element type for all tensor operations to ensure that the no load/stores of unsupported element types are used.
IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler and runtime that lowers Machine Learning (ML) models to a unified IR that scales up to meet the needs of the datacenter and down to satisfy the constraints and special considerations of mobile and edge deployments.
See our website for project details, user guides, and instructions on building from source.
IREE is still in its early phase. We have settled down on the overarching infrastructure and are actively improving various software components as well as project logistics. It is still quite far from ready for everyday use and is made available without any support at the moment. With that said, we welcome any kind of feedback on any communication channels!
See our website for more information.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.