commit | c62c8464d5758797d6ca0e2a55535b0cbd28e575 | [log] [tgz] |
---|---|---|
author | Thomas <thomasraoux@google.com> | Mon Apr 03 15:58:24 2023 -0700 |
committer | GitHub <noreply@github.com> | Mon Apr 03 22:58:24 2023 +0000 |
tree | a504af8c8e76717312ee1622d1fc416a8aca4bae | |
parent | 92cc535aebc48dbd238ad03fdd0449196ba4f27f [diff] |
[CUDA] Remove call to nvvm-intr-range and add a pass setting ranges (#12904) With the new pass manager nvvm-intr-range is disabled by default and the new pass manager doesn't allow passing the shader model when adding this pass. Therefore adding a new pass that allows to control the ranges attached to blockid and grid size intrinsics. This allows llvm to do arithmetic simplification.
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.