commit | 5783b51d60b62b8312d2eed76052c169cd7137e1 | [log] [tgz] |
---|---|---|
author | Scott Todd <scotttodd@google.com> | Mon Mar 14 14:51:59 2022 -0700 |
committer | GitHub <noreply@github.com> | Mon Mar 14 14:51:59 2022 -0700 |
tree | a9086872e507ebffc924ae1bdea6f64eedefd2bc | |
parent | ff82e4227c938236aa8302269e02a838ed6aa3fe [diff] |
Update test/e2e/xla_ops/round.mlir test status. (#8524) Progress on https://github.com/google/iree/issues/7618 https://github.com/google/iree/blob/c96372348654eea8548509d38df5c8e8b179aef3/iree/test/e2e/xla_ops/round.mlir#L1-L6 `mhlo.round_nearest_afz` lowers to `math.copysign`, which has this support in IREE today: backend | result -- | -- LLVM CPU | ✔️ success LLVM WebAssembly | ❌ same error as on https://github.com/google/iree/issues/8514 CUDA | ✔️ success, `ConvertToNVVM` lowers to `llvm.intr.copysign` SPIR-V | ❌ missing lowering in `ConvertToSPIRV` VMVX | ❌ missing lowering in `IREE::VM::ConversionPass` This test was disabled on all backends/drivers, so this PR enables it where it passes and updates the comments where it is marked as failing.
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.