| commit | cbd835d64612c031e093bc6e9f92d2a89bb76e28 | [log] [tgz] |
|---|---|---|
| author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | Mon Jul 26 13:31:30 2021 -0700 |
| committer | GitHub <noreply@github.com> | Mon Jul 26 13:31:30 2021 -0700 |
| tree | e1ff9243d0b9a564d15d05e157161409a312cd75 | |
| parent | f300aee8c9d0da48179737b77abe690ab58e12f2 [diff] |
Make Dispatch region formation handle `LinalgExtOp`s that implement `TiledOpInterface`. (#6540) Using the pattern to tile + distribute operations that implement the TiledOpInterface, this change extends dispatch region creation logic to handle LinalgExpOp that implement the tiled op interface. Also a few clean ups Add utility functions to interpret the root and fusion attributes to make the intent clearer. Modify the logic that decides the loops to be partitioned to be more configurable Make the analysis to find tied operands of the dispatch region run after destructive updates are resolved to use flow.dispatch.tensor.load/store. This seems to be a bug, that would disallow having any LinalgOp not have tied operands either. Remove the use of AffineMinSCFCanonicalizationPattern. It seems to hit an assertion (see Issue Segfault during application of AffineMinSCFCanonicalizationPattern #6520), also since all loop bounds are dynamic, there is no reason to apply this canonicalization.
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!
| CI System | Build System | Platform | Architecture | Configuration / Component | Status |
|---|---|---|---|---|---|
| Kokoro | Bazel | Linux | x86-64 |  | |
| Kokoro | CMake & Bazel | Linux | x86-64 (swiftshader) | Integrations |  |
| Kokoro | CMake & Bazel | Linux | x86-64 (turing) | Integrations |  |
| Kokoro | CMake | Linux | x86-64 (swiftshader) |  | |
| Kokoro | CMake | Linux | x86-64 (swiftshader) | asan |  |
| Kokoro | CMake | Linux | x86-64 (turing) |  | |
| Kokoro | CMake | Android | arm64-v8a | Runtime (build only) |  |
| Kokoro | CMake | Bare Metal | risc-v-32 | Runtime |  |
| Kokoro | CMake | Linux | risc-v-64 | Runtime |  |
| Buildkite | CMake | Android | arm64-v8a | Runtime |  |
| BuildKite | CMake | Android | arm64-v8a | Runtime Benchmarks (Mako) |  |
| BuildKite | CMake | Android | arm64-v8a | Runtime Benchmarks |  |
| BuildKite | CMake | Linux | x86-64 | Tracing + Standalone Runtime |  |
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.