| commit | acb25c46cdb0ffacd20c4392511a6e22bf15ca04 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <benvanik@google.com> | Mon Nov 15 11:45:23 2021 -0800 |
| committer | GitHub <noreply@github.com> | Mon Nov 15 11:45:23 2021 -0800 |
| tree | ccc23ee383b73eb139cf9d7e54ea9b8c0409dcd0 | |
| parent | 02cfcd1e5561c0db0470d09644a1f527c259c208 [diff] | |
| parent | 16747ff62d46b99f092915ad45136e6e4cd497d3 [diff] |
Merge pull request #7601 from google/benvanik-hal-streams Adding Stream -> HAL conversion. This is being added in parallel with the existing Flow -> HAL conversion so that we can still guard streams behind a flag. Once the flag is flipped the existing HAL/Conversion/ code will be deleted as well as most of the HAL passes that now are handled in the Stream dialect. MaterializeInterfaces was the only pass that required reworking insofar as much of the current one could be deleted (all the constant pool handling and binding simplification). Much of the code in here is transitory pending the large HAL dialect cleanup (removing awareness of tensors/etc). One of the larger changes here during conversion is that tensors that survive to the HAL dialect are converted directly to buffer views - prior to this they were buffers which then required a bunch of shady stuff to recalculate the tensor parameters. The TensorRewriteAdaptor will no longer be needed, and tensor->buffer_view is just a type change 🥳 This adds the `-iree-experimental-streams` flag to iree-translate which can be used to enable the new codepath. For this PR it defaults to disabled.
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 |  |
| BuildKite | CMake | Linux | x86-64 | Tracing + Standalone Runtime |  |
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.