| commit | 77e7cacb8d7eadf0350a54b66511683239e38edc | [log] [tgz] |
|---|---|---|
| author | bjacob <benoitjacob@google.com> | Sat Sep 17 22:06:32 2022 -0400 |
| committer | GitHub <noreply@github.com> | Sun Sep 18 02:06:32 2022 +0000 |
| tree | eb9fcc527249f65085c89b6ee9175e68b9290288 | |
| parent | 6c98ebb821dee4bbbf85f476991e0638b1a15de2 [diff] |
mmt4d builtin ukernels: baseline ARM64 kernels for f32 and i8 (#10440)
Also some renaming: the absence of a suffix like "i8mm" on the new
baseline asm file `mmt4d_tile_arm_64.S` caused a clash with the existing
`mmt4d_tile_arm_64.{h,c}` . Since the latter have a single entry point
named `mmt4d_select_tile_arm_64`, renamed them accordingly. Then did the
same with the `_generic` files in the parent dir. This usefully
highlights that the actual kernels are an "implementation detail" and
the _select_ function, returning a function pointer to one of them, is
the entry point.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.