[HAL] Refactor HAL executable exports to function IDs (#24507) Refactor the durable HAL runtime API from export ordinals to executable-local function ids while leaving compiler dialect churn minimal. Function ids are carried as 64-bit C and VM tokens so future backends can use executable-local encodings; current dense-table implementations validate and decode them as indexes. Public rename map: - iree_hal_executable_export_count -> iree_hal_executable_function_count - iree_hal_executable_export_info -> iree_hal_executable_function_info - iree_hal_executable_export_parameters -> iree_hal_executable_function_parameters - iree_hal_executable_lookup_export_by_name -> iree_hal_executable_lookup_function_by_name - iree_hal_executable_export_info_t -> iree_hal_executable_function_info_t - iree_hal_executable_export_parameter_t -> iree_hal_executable_function_parameter_t - iree_hal_executable_export_flags_t -> iree_hal_executable_function_flags_t - IREE_HAL_EXECUTABLE_EXPORT_FLAG_* -> IREE_HAL_EXECUTABLE_FUNCTION_FLAG_* - IREE_HAL_EXECUTABLE_EXPORT_PARAMETER_* -> IREE_HAL_EXECUTABLE_FUNCTION_PARAMETER_* - iree_hal_executable_vtable_t export_count/export_info/export_parameters -> function_count/function_info/function_parameters - iree_hal_executable_vtable_t lookup_export_by_name -> lookup_function_by_name - HAL dispatch export_ordinal/entry_point arguments -> function/function_id Compiler HAL ops and attributes intentionally keep their existing export names in this change. Runtime VM imports now use function_id, and executable.lookup.function is exposed from the HAL and hal_loader modules so callers can resolve stable function names to runtime ids before dispatch.
IREE (Intermediate Representation Execution Eenvironment, 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.
Releases notes are published on GitHub releases.
| Package | Release status |
|---|---|
| GitHub release (stable) | |
| GitHub release (nightly) | |
iree-base-compiler | |
iree-base-runtime |
For more details on the release process, see https://iree.dev/developers/general/release-management/.
| Operating system | Build status |
|---|---|
| Linux | |
| macOS | |
| macOS |
For the full list of workflows see https://iree.dev/developers/general/github-actions/.
See our website for more information.
Community meeting recordings: IREE YouTube channel
| Date | Title | Recording | Slides |
|---|---|---|---|
| 2025-06-10 | Data-Tiling in IREE: Achieving High Performance Through Compiler Design (AsiaLLVM) | recording | slides |
| 2025-05-17 | Introduction to GPU architecture and IREE's GPU CodeGen Pipeline | recording | slides |
| 2025-02-12 | The Long Tail of AI: SPIR-V in IREE and MLIR (Vulkanised) | recording | slides |
| 2024-10-01 | Unveiling the Inner Workings of IREE: An MLIR-Based Compiler for Diverse Hardware | recording | |
| 2021-06-09 | IREE Runtime Design Tech Talk | recording | slides |
| 2020-08-20 | IREE CodeGen (MLIR Open Design Meeting) | recording | slides |
| 2020-03-18 | Interactive HAL IR Walkthrough | recording | |
| 2020-01-31 | End-to-end MLIR Workflow in IREE (MLIR Open Design Meeting) | recording | slides |
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.