commit | 915977bf50b388312d6ae4a70f8ee097d48d9b5b | [log] [tgz] |
---|---|---|
author | Lei Zhang <antiagainst@google.com> | Fri Sep 02 18:08:02 2022 -0400 |
committer | GitHub <noreply@github.com> | Fri Sep 02 22:08:02 2022 +0000 |
tree | 09e69471c41b26f4ab37bf85bb4069bf4da524e3 | |
parent | ea7fdabeed0de08a7a1e3141fde7dd52d27f5595 [diff] |
[vulkan] Update various targets to match current status (#10283) * Used Android API level (e.g., 30) instead of the Android version (e.g., 11). This makes it consistent with how we specify Android targets on CPU side (e.g., aarch64-none-linux-android30). (Android API level to version mapping: https://apilevels.com/) * Updated capabilties and extensions for mobile GPUs on Android 12. * Changed benchmarking to track Android 12 (which is what the devices have for a long time).
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.