Merge main -> google

* 8fc4cc005 Add tosa's MakeBroadcastPass to the tosa compilation (#6199)
* 6565ff40c Integrate MLIR-EmitC at iml130/mlir-emitc@65088b00 (#6205)
* be6d0b636 Removing the SIP signature parser from the runtime. (#6203)
* f980bf686 Removing iree.module.export. (#6202)
* 5490defa6 Use the result buffer's length when converting flow.tensor.clone (#6201)
* 0bb39fc27 Delete old SIP ABI. (#6200)
* 187aa7f13 Flip flags to enable IREE native ABI. (#6155)
* 7c611b95c Refresh some of our Colab notebooks. (#6162)
* 89dd503c6 Properly support categories when benchmarking on Android (#6187)
* 845b8bc70 [CUDA/ROCM] Add byte offset to the base when lowering binding (#6193)
* d18d794ac Clear the whole temporary directory before/after benchmarking (#6192)
* b65b09fee Disabling tying of stream operands until #6185 can be fixed. (#6188)
* a8eb740eb Convert `elf_module_test` to an executable with C API (#6176)
* 58d2c0e79 Add test case for dynamic-update-slice into constant (#6189)
* 948aa9b43 Clone loaded constants if they are used for inplace update (#6174)
* 1e4435d52 Bump googletest to the most recent commit (#6186)
* 6c2d8e6e0 Fix some small typos in docs. (#6172)
* bd3dd6856 Merge google -> main (#6167)
* 28052c5c7 Fix rocm_device_pointer and adding bitcode (#6184)
* 77732f15d Check fread error in tflite bindings. (#6147)
* 9295f2330 Hoist static allocation at the funcOp top (#6153)
* c869c9e32 Merge pull request #6169 from google/benvanik-inproc-cmdbuf
* 0e6bb8038 [CUDA] Enable dynamic pipeline (#6168)
* 111be2e14 Add IREE variant of mlir-lsp-server. (#6178)
* 86cc1ed5a Fix the initial value in `iree/samples/variables_and_state` (#6177)
* 2c2a21be7 Add a pass to tile, pad and vectorize linalg ops on tensors (#6151)
* 91800f5fb Add TranslationInfo Attribute. (#6175)
* 9debd78b5 Fix missing no-ops under IREE_SYNCHRONIZATION_DISABLE_UNSAFE (#6113)
* db2a17fc8 Fix passing input options (#6173)
* 01ef5db34 Add back passes for legalizing shape->standard. (#6171)
* 972fa79e7 Add VM->Python mapping for i1 buffer views. (#6170)
* a0284145f Add support for the rodata op in the VM to EmitC conversion (#5953)

Includes local patches to:
- bindings/python/iree/runtime/function.py: Handles duck-typed arrays (for compatibility with JAX DeviceArray, et al)
- integrations/tensorflow/iree_tf_compiler/TF/test/saved_model_to_iree_abi.mlir: Updates lit test for upstream change that was inadvertently not being tested.

PiperOrigin-RevId: 379371908
tree: bab104d11c04b90a1c9303494b7f9a89951af689
  1. .github/
  2. bindings/
  3. build_tools/
  4. colab/
  5. docs/
  6. experimental/
  7. integrations/
  8. iree/
  9. scripts/
  10. third_party/
  11. .bazelignore
  12. .bazelrc
  13. .bazelversion
  14. .clang-format
  15. .gitignore
  16. .gitmodules
  17. .style.yapf
  18. .yamllint.yml
  19. AUTHORS
  20. BUILD.bazel
  21. CMakeLists.txt
  22. configure_bazel.py
  23. CONTRIBUTING.md
  24. LICENSE
  25. README.md
  26. SUBMODULE_VERSIONS.txt
  27. WORKSPACE
README.md

IREE: Intermediate Representation Execution Environment

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.

Project Status

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!

Communication Channels

Related Project Channels

  • MLIR topic within LLVM Discourse: IREE is enabled by and heavily relies on MLIR. IREE sometimes is referred to in certain MLIR discussions. Useful if you are also interested in MLIR evolution.

Build Status

CI SystemBuild SystemPlatformArchitectureComponentStatus
KokoroBazelLinuxx86Corekokoro_status_bazel_linux_x86_core
KokoroCMake & BazelLinuxx86-swiftshaderIntegrationskokoro_status_cmake-bazel_linux_x86-swiftshader_integrations
KokoroCMake & BazelLinuxx86-turingIntegrationskokoro_status_cmake-bazel_linux_x86-turing_integrations
KokoroCMakeLinuxx86-swiftshaderCore + Bindingskokoro_status_cmake_linux_x86-swiftshader
KokoroCMakeLinuxx86-swiftshader-asanCore + Bindingskokoro_status_cmake_linux_x86-swiftshader-asan
KokoroCMakeLinuxx86-turingCore + Bindingskokoro_status_cmake_linux_x86-turing
KokoroCMakeAndroidarm64-v8aRuntime (build only)kokoro_status_cmake_android_arm64-v8a
BuildKiteCMakeAndroidarm64-v8aRuntimebuildkite-status-cmake-android-arm

Presentations and Talks

  • 2020-08-20: IREE CodeGen: MLIR Open Design Meeting Presentation (recording and slides)
  • 2020-03-18: Interactive HAL IR Walkthrough (recording)
  • 2020-01-31: End-to-end MLIR Workflow in IREE: MLIR Open Design Meeting Presentation (recording and slides)

License

IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.