| commit | ccd576caa0a2f0633e0d4ac52273f71c5c585482 | [log] [tgz] |
|---|---|---|
| author | Quinn Dawkins <quinn.dawkins@gmail.com> | Mon Jan 08 11:24:22 2024 -0500 |
| committer | GitHub <noreply@github.com> | Mon Jan 08 11:24:22 2024 -0500 |
| tree | afb1ab3550227e39a37e9a40ee2972e2da0adbc0 | |
| parent | f0c83805e71bdce6650bbc5ef0a92faf58767346 [diff] |
[LLVMGPU] Add AMDGPUToArith conversion patterns to ROCDL lowering (#16067) The details of the patterns are already tested upstream, this just adds a pipeline check to make sure a simple elementwise arith.extf fp8 -> fp32 example connects all the way. Currently this is only supported for gfx940. For other targets we will need to add emulation patterns. Additionally adds some debug logging to ConvertToROCDL.
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.