| commit | 91e73d39692f8079add68b4307edb0e63e61b347 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Fri Feb 24 22:55:37 2023 -0800 |
| committer | Ben Vanik <ben.vanik@gmail.com> | Fri Mar 03 19:36:06 2023 -0800 |
| tree | 00487a526e6e8275ca0f581c5a5f6c7ba65d53eb | |
| parent | 8883247a1e2004fd7ae6d91c8e3bcee03de1f797 [diff] |
Adding requirement bits to bytecode modules and bumping version. The compiler now emits per-module and per-function requirement bitfields that indicate extensions needed to execute the bytecode they contain. This allows for nice error messages on loading when the runtime has certain extensions omitted: ``` D:\Dev\iree\runtime\src\iree\vm\bytecode\module.c:309: INVALID_ARGUMENT; required module features [EXT_F32] are not available in this runtime configuration; have [] while module requires [EXT_F32]; while invoking native function hal.executable.create; while calling import; [ 1] native hal.executable.create:0 - [ 0] bytecode module.__init:446 D:\Dev\iree/tests/e2e/models/unidirectional_lstm.mlir:0:0 ``` While making the breaking change I'm also adding a block_count field to each function descriptor and a special block opcode that can be used for verification and disassembly. All functions now have their signatures embedded (not just exports) to allow for internal function call verification.
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.