| commit | bf8588e0efbfe0de12099cac8042fd7dd69ccc19 | [log] [tgz] |
|---|---|---|
| author | bjacob <benoitjacob@google.com> | Thu Jun 01 06:37:13 2023 -0400 |
| committer | GitHub <noreply@github.com> | Thu Jun 01 10:37:13 2023 +0000 |
| tree | 46a3a3f263ce29332a941e191a75002a98e84cbb | |
| parent | 446a5422a2a922e0be5bb06352bd94b6450b5758 [diff] |
Microkernels: add arm64 bitcode. Test everywhere. (#13846) This adds arm64 to the ukernels bitcode build, and, following #13825 , that is automatically picked up by `iree-compile` when the target is arm64. This generalizes the e2e matmul tests BUILD with data-tiling + microkernels to cover relevant cases on both x86-64 and arm64. This drops tags on that e2e matmul test, so it's now enabled everywhere. It just uses generic (not fast) bitcode if we don't have dedicated fast code for some architecture, but it runs everywhere. Fixes #13804 .
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.