commit | f4f6c8342b43699a52284634ce52344e4190f03b | [log] [tgz] |
---|---|---|
author | Lei Zhang <antiagainst@google.com> | Wed Aug 04 17:16:04 2021 -0400 |
committer | GitHub <noreply@github.com> | Wed Aug 04 14:16:04 2021 -0700 |
tree | b3f86599bf516a04207b3b3206345ae5e3e2e7cd | |
parent | ff88056e5a1520785541ad5ebdfecb46eb1950e1 [diff] |
[spirv] Add support for linking SPIR-V modules (#6557) Actually, Vulkan flavored SPIR-V does not have linking in the conventional sense. For example, there is no cross-module symbol reference and symbol resolution and such. It's more just combining all SPIR-V modules into the one, with multiple entry points. This commit enables combining multiple SPIR-V modules into one and serialize it. Right now we only combine SPIR-V modules using the same interface (i.e., binding layout). This avoids handling different descriptor set layouts and it also is forward looking, as we would like to have two level of linking/combining eventually. Fixes https://github.com/google/iree/issues/3604
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!
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.