| commit | e32a5026ab6e06d58ee7a90074239ea2a8074fe9 | [log] [tgz] |
|---|---|---|
| author | Han-Chung Wang <hanhan0912@gmail.com> | Thu Jan 11 10:07:41 2024 -0800 |
| committer | GitHub <noreply@github.com> | Thu Jan 11 10:07:41 2024 -0800 |
| tree | 030867cfda471c9be22bd97eee87a19de5fd8f77 | |
| parent | 869e505e761eb830630425411a2b22c9c2ef5bc0 [diff] |
Bump LLVM to llvm/llvm-project@f5145f4dc819 (#16073) This includes a revert for https://github.com/llvm/llvm-project/commit/11ac97c67a9315dce48fd938d68ae991e3559f10 Other fixes: - Implement https://github.com/openxla/iree/pull/16073/commits/77b777c0c7b7365fc6f676c1fb582b16f99f6d72 which avoids inlining big constants into dispatch. - Add fixes for https://github.com/llvm/llvm-project/commit/b3037ae1fc6d26459e37f813757ad30872eb2eee, see https://github.com/openxla/iree/pull/16073/commits/7ed5f2976e63170707363ed66a208c9fa712cfab - Add fixes for https://github.com/llvm/llvm-project/commit/bae1fdea712fcd0b0ea525b115e661f92263f2e7, see https://github.com/openxla/iree/pull/16073/commits/c83cefbd1c78be6b37fe3623c50bd3c9fe8a930b It updates `HALDispatchABI::buildScopeAttr` to take `LLVM::LLVMFuncOp` as inputs, so it can handle if the `DistinctAttr` is needed or not for `DISubprogramAttr`. - Add fixes for https://github.com/llvm/llvm-project/commit/bb6d5c220004a5d7e466a669324001285a688918 - Add `--split-input-file` to `lower_to_ukernel_ops.mlir`. - Move few `CHECK-DAG` to beginning for fixing lit tests. - Replace some `CHECK[-NEXT]` with `CHECK-DAG` - Add `--canonicalize` to `affinemin_canonicalization.mlir` which hoists constants out of region.
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.