commit | 446a5422a2a922e0be5bb06352bd94b6450b5758 | [log] [tgz] |
---|---|---|
author | bjacob <benoitjacob@google.com> | Thu Jun 01 06:10:27 2023 -0400 |
committer | GitHub <noreply@github.com> | Thu Jun 01 06:10:27 2023 -0400 |
tree | d382f32d9474e4aff6415d9e7f9fdc5aae5bf889 | |
parent | 295ded212c73c102926967c8870d2ee3f2fcaf4b [diff] |
Correct 32bit/64bit separation in ukernel code. (#13878) * Rename `iree_uk_ssize_t` to `iree_uk_index_t` to make it clear that the primary requirement on this type is to match the compiler's `index` type. * Build non-arch/ ukernel code twice, for 32bit and 64bit architectures. As in libdevice, wasm_32 / wasm_64 is chosen as a sane 32bit/64bit architecture to pick when the only thing that matters is the bitness (which only matters for choosing the right definition of `iree_uk_index_t`). * Drop `strip_target_info.py`, instead adopt `Device.cpp`'s code dropping function attributes inside of the compiler after loading the bitcode.
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.