commit | 61db4ca4085a13fbd866c5a19040a7b21f29b495 | [log] [tgz] |
---|---|---|
author | Nicolas Vasilache <nicolasvasilache@users.noreply.github.com> | Mon Mar 28 18:12:14 2022 +0200 |
committer | GitHub <noreply@github.com> | Mon Mar 28 09:12:14 2022 -0700 |
tree | 123a6a0c1c23b990898bbe9ef97530a6c4a0880c | |
parent | c783385ecf451a3c631578c9451465103c4c2977 [diff] |
Bump llvm to 5c116d50e42f93ef4fa9a9719121378ec6b99b69 (#8652) * Bump LLVM to [5c116d50e42f93ef4fa9a9719121378ec6b99b69](https://github.com/llvm/llvm-project/commit/5c116d50e42f93ef4fa9a9719121378ec6b99b69) * 217988819 iree-dialects fixes (createOperation -> create and OpAsmParser::OperandType -> OpAsmParser::UnresolvedOperand) * 5d06650d6 Assert on PDL native function call type mismatches. * 8b2abae7b Add missing include in iree-dialects * e6491bf94 Rename OpAsmParser::OperandType to OpAsmParser::UnresolvedOperand globally in IREE * c50542572 Rename createOperation -> create globally * 11614987b Bump MHLO to [e918d22b258375050a140b320eeb1d1167079e43](https://github.com/tensorflow/mlir-hlo/commit/e918d22b258375050a140b320eeb1d1167079e43) * 0762fbfe7 clang-format * cdf96f56c Update PDL usage in linalg_transforms tests * 1807fd24f Fix IREE tests for LLVM bump LLVM revision: [5c116d50e42f93ef4fa9a9719121378ec6b99b69](https://github.com/llvm/llvm-project/commit/5c116d50e42f93ef4fa9a9719121378ec6b99b69) MHLO revision: [e918d22b258375050a140b320eeb1d1167079e43](https://github.com/tensorflow/mlir-hlo/commit/e918d22b258375050a140b320eeb1d1167079e43) PiperOrigin-RevId: 437369768
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.