commit | 59e67a704d17280959a991319a7ff1ae8c5a74fe | [log] [tgz] |
---|---|---|
author | Lei Zhang <antiagainst@google.com> | Fri Mar 17 16:39:36 2023 -0700 |
committer | Lei Zhang <antiagainst@google.com> | Tue Jun 13 21:17:32 2023 -0700 |
tree | f63b98c0d8a2b8ca3456771d10bcdb08fe79827f | |
parent | 6e93f001137d4b4860d0343ca7fc414aa45cc642 [diff] |
[metal] Enable compiling to Metal library when possible This commit extends Metal compilation to additionally invoke Metal shader compilers on macOS to further compile MSL into Metal library, so we don't need to JIT compile during runtime. This reduces runtime overhead. For other platforms where we don't have access to offline Metal compilers, we still embed MSL source code in IREE flatbuffer.
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.