commit | 0fb618ccecff6559165609bab4f5b0a934a09edb | [log] [tgz] |
---|---|---|
author | Han-Chung Wang <hanchung@google.com> | Mon Mar 14 23:04:25 2022 -0700 |
committer | GitHub <noreply@github.com> | Mon Mar 14 23:04:25 2022 -0700 |
tree | a506cc71d7168847c6380e1fe04e78c80a3538d5 | |
parent | 5783b51d60b62b8312d2eed76052c169cd7137e1 [diff] |
Switch all x86 and RISC-V matmul codegen to use DoubleTilingExpert. (#8539) The RISC-V targets were considered as ARM configuration. This PR makes it go through Sandbox based approach. The commit also moves quantized matmul to use DoubleTilingExpert. They used old pipeline because of long compilation time. Many instructions were generated during the lowering. This is addressed in https://github.com/llvm/llvm-project/commit/1538bd518cd236f4321695e9c5f0dd24601db366 It is a step toward https://github.com/google/iree/issues/8431
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.