From f31482892dbb273f60603022bdd1de015e233658 Mon Sep 17 00:00:00 2001 From: Simon Camphausen Date: Wed, 11 Dec 2024 16:08:15 +0000 Subject: [PATCH] Add maintenance note Co-authored-by: Marius Brehler --- README.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/README.md b/README.md index e728f917..d9590bc0 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,15 @@ SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception ![Build and test](https://github.com/iml130/mlir-emitc/workflows/Build%20and%20test/badge.svg) +> [!WARNING] +> The code provided in this repository is no longer maintained and superseded by code available in upstream MLIR. + +> [!NOTE] +> We encourage to use upstream MLIR lowering passes instead of the TOSA and StableHLO to EmitC conversions provided here. +> Lowering via multiple dialects and hence using different abstraction levels, allows to reuse different optimization passes. +> Furthermore, the generated C and C++ code depends on the standard libraries without requiring additional header files, whereas code generated with the the conversions in this repositories requires a header-only reference implementation. +> For missing features, we highly encourage to consider extending the upstream dialect and conversions. + MLIR-EmitC provides a way to translate ML models into C++ code. The repository contains scripts and tools to translate Keras and TensorFlow models into the [TOSA](https://mlir.llvm.org/docs/Dialects/TOSA/) and