| commit | e31b5a2e0476f0b7d0cf1b32869509554044c2c7 | [log] [tgz] |
|---|---|---|
| author | Quinn Dawkins <quinn.dawkins@gmail.com> | Tue Jan 23 16:29:07 2024 -0500 |
| committer | GitHub <noreply@github.com> | Tue Jan 23 16:29:07 2024 -0500 |
| tree | 95be0025ba00c0436d24d178bf70fddf562afe4e | |
| parent | 3a375593aa56035619444640fdb5988e60eb1157 [diff] |
Add a pass for parameterizing large constants (#15955) This adds a pass for constructing a parameter archive out of the globals present in IR. The expected flow for this pass is to hoist all constants above a specified size (probably the default inlining size for a constant in a kernel) into globals + initializers and then replacing them with parameters. This can happen any time before, after, or in-between const-eval and const-expr-hoisting.
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.