| commit | ac9d6d56ab1d5776b9e83fcc17dfef9eaf3f5b49 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Sun Dec 03 20:20:31 2023 -0800 |
| committer | GitHub <noreply@github.com> | Sun Dec 03 20:20:31 2023 -0800 |
| tree | 09eb6bdac299ce4f896ad185ecd8a70d104fd734 | |
| parent | 62d756131296de8a95b9d10b9e8a3f9ec92e85e1 [diff] |
Adding optional exported function declaration string to bytecode modules. (#15782)
This allows iree-dump-module (and in the future other things) to report
the original source declaration for an exported function. This is only
intended to aid debugging and not machine interpretation.
Example from iree-dump-module:
```
Exported Functions:
[ 0] predict(!vm.ref<?>) -> (!vm.ref<?>)
iree.abi.declaration: sync func @predict(%input0: tensor<1x28x28x1xf32>) -> (%output0: tensor<1x10xf32>)
```
Example from iree-run-module with invalid args:
```
D:\Dev\iree\runtime\src\iree\vm\invocation.c:95: INVALID_ARGUMENT; input list and function mismatch; expected 1 arguments but passed 0; invoking function 'predict'; `sync func @predict(%input0: tensor<1x28x28x1xf32>) -> (%output0: tensor<1x10xf32>)`
```
Frontends can attach an `iree.abi.declaration` attribute to public
functions to override the automatically generated string or add
`iree.abi.name` attributes to args/results to have them used instead of
the defaults.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.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.