commit | b922a7012978b149e87fd828b893eb3a1a05485a | [log] [tgz] |
---|---|---|
author | Benoit Jacob <jacob.benoit.1@gmail.com> | Tue Oct 22 10:24:05 2024 -0400 |
committer | GitHub <noreply@github.com> | Tue Oct 22 14:24:05 2024 +0000 |
tree | 7fcd40f192d7957e7e352d53f451b7521bd0c7c0 | |
parent | bb71f7d4e56051c9b60de50c8c5a343027dbe645 [diff] |
GPU data tiling: query the target's list of MMA intrinsics. Add FP8 test. (#18862) The current code had its own list of MFMA intrinsics that we can use, then checked that against the target. Flipping this around, we can simply query the list from the target. The only subtlety is that the target may support multiple intrinsics for a given combination of element types, in which case we have to choose one. This PR also changes `std::optional<Attr>` to just `Attr` since a default-constructed `Attr` is null-ish, there is no need for a second null-value. The heuristic added in this PR is designed to match the existing choices so that the tests don't need to change; these existing choices are also what maximizes some microbenchmark performance, but we have known that they may be counterproductive in real scenarios where the bottleneck is power. The test gains a FP8 testcase, and some renaming to simplify function names (which had become a lie in some testcases). --------- Signed-off-by: Benoit Jacob <jacob.benoit.1@gmail.com> Co-authored-by: Quinn Dawkins <quinn.dawkins@gmail.com>
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
Package | Release status |
---|---|
GitHub release (stable) | |
GitHub release (nightly) | |
Python iree-compiler | |
Python iree-runtime |
Host platform | Build status |
---|---|
Linux | |
macOS | |
Windows |
For the full list of workflows see https://iree.dev/developers/general/github-actions/.
See our website for more information.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.