[Metal] Carry export name separately from MSL entry point for name lookup (#24642) spirv-cross rewrites SPIR-V entry point names to be legal MSL/C identifiers when serializing Metal executables: '.' characters (codegen dispatch names like _dot_general_matmul_i32.i32.i32_...) become '_', and reserved '__' prefixes (stream builtins like __builtin_splat_i64) are dropped. The MetalSPIRV target stored only the rewritten MSL function name in PipelineDef.entry_point, and the runtime loaded pipeline->name from that same field -- so hal.executable.lookup.function, which references the original un-rewritten hal.executable.export symbol name, could never match for any export whose name spirv-cross rewrites. This broke every metal-spirv e2e test using such exports (dot/dot_general/convolution matmul kernels and compare/dynamic_slice/gather stream builtins). Add a dedicated always-present name field to PipelineDef carrying the canonical hal.executable.export symbol name (populated from exportOp.getName() in the compiler), appended at the end of the table for backward-compatible vtable layout. The runtime now sources pipeline->name (used by lookup_function_by_name) from this field, keeping entry_point as the MTLFunction name for -[MTLLibrary newFunctionWithName:]. The loader falls back to entry_point when name is absent for compatibility. Verified: dot_general (8/8), compare (15/15), and the full Metal CTS suite (command_buffer_tests/queue_tests/dispatch_tests/queue_dispatch_tests, 4/4) pass. Signed-off-by: Alex Vasile <48962821+Alex-Vasile@users.noreply.github.com> Signed-off-by: Alex Vasile <48962821+Alex-Vasile@users.noreply.github.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 | |
| 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.