| commit | 9d6b425c81254d6fc8e18057188c26609320fab4 | [log] [tgz] |
|---|---|---|
| author | Lei Zhang <antiagainst@gmail.com> | Sat Jul 13 09:54:33 2024 -0700 |
| committer | GitHub <noreply@github.com> | Sat Jul 13 09:54:33 2024 -0700 |
| tree | a80faf0cd87407b27fbea00e8ecef0d22c6e2ab5 | |
| parent | 2ed3f92c6a451b0f17f94f1391c2ec7f3c1defe4 [diff] |
[spirv] Push GPU target conversion to before SPIR-V conversion (#17816) This commit moves the `SPIRVConvertGPUTargetPass` to right before the `ConvertToSPIRVPass` in the pipeline. This makes sure we use the same `#iree_gpu.target` in the majority of the configuration and lowering passes in the CodeGen flow, and scopes the SPIR-V target environment to only the final SPIR-V conversion. With this, we are able to unify and simplify lots of SPIR-V tests. Progress towards https://github.com/iree-org/iree/issues/16341 ci-extra: test_nvidia_gpu,test_nvidia_a100,test_amd_mi250,test_amd_w7900,build_test_all_macos_arm64,build_and_test_android --------- Signed-off-by: Lei Zhang <antiagainst@gmail.com>
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.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.