commit | 2884f2769ed501524e7e034031bafae8052d6cfe | [log] [tgz] |
---|---|---|
author | Lei Zhang <antiagainst@google.com> | Tue Sep 07 14:36:51 2021 -0400 |
committer | GitHub <noreply@github.com> | Tue Sep 07 14:36:51 2021 -0400 |
tree | 1c7f11ab258b16cd51033a8f0098321c07a2b096 | |
parent | 9294b24c6b066a1e7f522ed58b7d6eed6ead2dfb [diff] |
Add support to capture Tracy traces when benchmarking (#6971) This commit adds logic to perform Tracy captures after running each benchmark. It allows us to have more details regarding the benchmark to investigate performance regressions, etc. Also decreased the benchmark repetition count for VMVX. VMVX is very unoptimized for now and can take a long time to run, e.g., one inference of MobileNetV2 takes almost 1min. Decrease the repetition for it until it's reasonably fast.
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!
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.