commit | a1defb45237709760e27dc28a89cac44c0ae5363 | [log] [tgz] |
---|---|---|
author | Lei Zhang <antiagainst@google.com> | Sat Feb 11 17:24:59 2023 -0800 |
committer | Lei Zhang <antiagainst@google.com> | Tue Jun 13 21:17:31 2023 -0700 |
tree | 15bcafa31de62317bcb5ff9bd08f37c02ca6d1b9 | |
parent | 9b474922485989cd34a893ff94acbee3b75cf945 [diff] |
[metal] Support loading executables and compiling kernels This commit implements IREE executable APIs and adds a no-op executable cache. This reuses the already in-tree SPIR-V CodeGen and MSL cross compilation path to generate kernels and embed them into IREE deployable flatbuffer as MSL source strings. Then at runtime we compile those source strings into Metal kernel functions and get pipeline state object out fo them. A future commit will wire up .mtllib or binary archive offline compilation.
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.