[iree-benchmark-module] Unify sync, async and dispatch execution (#24986) `iree-benchmark-module` had separate synchronous, asynchronous, and generated-dispatch execution paths that applied output processing, replay capture, and profiling flushes inconsistently. Run them through one batch lifecycle so discovery resolves each function's ABI and iteration accounting once and every execution model shares the measured loop. The shared lifecycle fixes several inconsistencies: - Retain asynchronous outputs for `--enable_output_processing`. - Supply fence arguments for discovered asynchronous functions. - Use the generated repeat count for dispatch benchmarks selected with `--function`. - Handle non-power-of-two `--batch_concurrency` without reading past the invocation list. - Return recording devices from context setup so asynchronous fences participate in replay capture. Errors go to stderr with `EXIT_FAILURE`, matching `iree-run-module`. Output processing requires a single benchmarked function, and nonpositive batch size or concurrency is rejected. Device profiling ends before output processing. Assisted by AI. Co-authored-by: Claude Opus 5.5 <noreply@anthropic.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.
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 |
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.