Google Git
Sign in
opensecura / 3p / openxla / iree / 9ca7563d903d8e6f04e9f456f0cf1cf70546d506
commit9ca7563d903d8e6f04e9f456f0cf1cf70546d506[log] [tgz]
authorScott Todd <scotttodd@google.com>Wed Apr 13 10:47:11 2022 -0700
committerGitHub <noreply@github.com>Wed Apr 13 10:47:11 2022 -0700
tree96ce003e60c7e83ccced9d4425d2ea9aae2e43ff
parent519815e4bcd51cf690ede07338d73d99241465b7 [diff]
Make benchmark artifact generation a bit more flexible. (#8846)

Here's my use case:

* I'm working on Windows, where we don't support building the TensorFlow integration tools (notably `iree-import-tflite`)
* I want to use the .mlir files that we feed into our benchmarking for local development (more specifically I want _some_ set of real programs, but the benchmark suite offers a set that we continuously build/test and have metrics for already)

---

Now, a sensible solution would be to extend
https://github.com/google/iree/blob/1ddd9170bd6cc2701e2d669754a8fff248739233/build_tools/buildkite/cmake/android/arm64-v8a/benchmark2.yml#L9-L14
to also zip up the imported .mlir files so anyone could download them from Buildkite.

---

I, however, had the more indirect idea to write a Colab notebook ([work in progress here](https://colab.research.google.com/gist/ScottTodd/4b27c6b44f90d239d4676dacddb87895/iree-benchmarks-import-demo.ipynb)) that installs the latest IREE release along with the project source and then builds `iree-benchmark-suites` using the installed tools. That _almost_ worked, except for the few issues that this PR patches over:

* `$<TARGET_FILE:iree::tools::iree-compile>` only works when building with `IREE_BUILD_COMPILER`, but it's also useful to point at already built tools using `IREE_HOST_BINARY_ROOT`. The `iree_get_executable_path` function handles switching between those modes easily
* Compiling imported files for the full list of benchmark configurations can be slow. If a developer just wants to import .mlir files then skipping those following steps would be useful. I added a new `iree-benchmark-import-models` target that does that.

(I also considered the _even more indirect_ idea to parse the artifact paths from [benchmarks/TFLite/CMakeLists.txt](https://github.com/google/iree/blob/main/benchmarks/TFLite/CMakeLists.txt) and run `iree-import-tflite` manually, but the `iree-benchmark-suites` target already does that natively :P)

---

I'm open to any workflow that solves my original use case, but these changes seem generally good to have anyways.
2 files changed
tree: 96ce003e60c7e83ccced9d4425d2ea9aae2e43ff
  1. .github/
  2. benchmarks/
  3. bindings/
  4. build_tools/
  5. colab/
  6. docs/
  7. experimental/
  8. integrations/
  9. iree/
  10. llvm-external-projects/
  11. scripts/
  12. third_party/
  13. .bazelignore
  14. .bazelrc
  15. .bazelversion
  16. .clang-format
  17. .gitignore
  18. .gitmodules
  19. .pylintrc
  20. .style.yapf
  21. .yamllint.yml
  22. AUTHORS
  23. BUILD.bazel
  24. CMakeLists.txt
  25. configure_bazel.py
  26. CONTRIBUTING.md
  27. LICENSE
  28. README.md
  29. 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 SystemPlatformArchitectureConfiguration / ComponentStatus
KokoroBazelLinuxx86-64kokoro status bazel/linux/x86-swiftshader/core
KokoroCMake & BazelLinuxx86-64 (swiftshader)Integrationskokoro status cmake-bazel/linux/x86-swiftshader
KokoroCMake & BazelLinuxx86-64 (turing)Integrationskokoro status cmake-bazel/linux/x86-turing
KokoroCMakeLinuxx86-64 (swiftshader)kokoro status cmake/linux/x86-swiftshader
KokoroCMakeLinuxx86-64 (swiftshader)asankokoro status cmake/linux/x86-swiftshader-asan
KokoroCMakeLinuxx86-64 (turing)kokoro status cmake/linux/x86-turing
KokoroCMakeAndroidarm64-v8aRuntime (build only)kokoro status cmake/android/arm64-v8a
KokoroCMakeBare Metalrisc-v-32Runtimekokoro status cmake/baremetal/riscv32
KokoroCMakeLinuxrisc-v-64Runtimekokoro status cmake/linux/riscv64
BuildkiteCMakeAndroidarm64-v8aRuntimebuildkite status iree-android-arm64-v8a
BuildKiteCMakeAndroidarm64-v8aRuntime Benchmarksbuildkite status iree-benchmark
BuildKiteCMakeLinuxx86-64Tracing + Standalone Runtimebuildkite status iree-build-configurations

Architecture Overview

IREE Architecture

See our website for more information.

Presentations and Talks

  • 2021-06-09: IREE Runtime Design Tech Talk (recording and slides)
  • 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.