# TBC

**Repository Path**: lordrebel/TBC

## Basic Information

- **Project Name**: TBC
- **Description**: a compiler based on mlir
- **Primary Language**: C++
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-08-28
- **Last Updated**: 2026-03-23

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# TODO
## for ubuntu version> 24.04
### 1. create venv
```bash
python3 -m venv ./pyenv
source ./pyenv/bin/activate

```

## pepare env
```bash
source env.source
```
## how to build

### llvm prepare

#### 1. pull code

```bash
cd ..
git clone --branch llvmorg-19.1.7 --depth 1  https://gitee.com/mirrors/LLVM.git
```

#### 2. compile llvm

```bash

cd LLVM&&mkdir -p build && cd build
cmake -G Ninja ../llvm     -DLLVM_ENABLE_PROJECTS="mlir"     -DLLVM_INSTALL_UTILS=ON     -DLLVM_TARGETS_TO_BUILD=""     -DLLVM_ENABLE_ASSERTIONS=ON     -DMLIR_INCLUDE_TESTS=OFF     -DLLVM_INSTALL_GTEST=ON     -DMLIR_ENABLE_BINDINGS_PYTHON=ON     -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=../../llvm_release -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DLLVM_ENABLE_BINDINGS=ON   -DLLVM_ENABLE_LLD=ON -DLLVM_ENABLE_PIC=ON  -DMLIR_INCLUDE_INTEGRATION_TESTS=ON -DPython3_EXECUTABLE=$(which python3)

cmake --build . --target install

```

### 3. install omp

```bash
#for gcc
sudo apt-get install libomp-dev
#for clang-20
sudo apt install libomp-20-dev
```
### 4 ortools prepare
#### 1. pull code
```bash
git clone --branch v9.14 --depth 1 https://github.com/google/or-tools.git
```
#### compile ortools
```bash
mkdir build &&cd build
make -G Ninja -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_EXE_LINKER_FLAGS="-fuse-ld=lld" -DCMAKE_SHARED_LINKER_FLAGS="-fuse-ld=lld" -DCMAKE_MODULE_LINKER_FLAGS="-fuse-ld=lld"  -S ../ -DBUILD_DEPS=ON -DCMAKE_BUILD_TYPE=Release   -DCMAKE_INSTALL_PREFIX=../ortools_release
cmake --build .  --config Release --target install
```

### 5. build
```bash
bash build.sh
```
## how to use
### simple test
1. download lenet.onnx from [here](https://github.com/ONNC/onnc-tutorial/blob/master/models/lenet/lenet.onnx)
2. run
```bash
source env.source
model_transform.py --model_name lenet --model_path ./your/path/to/onnx --platform onnx - --mlir ./lenet.mlir
```
3. for more details see `model_transform.py --help`

## TODO List
- [X] test fp8/fp16 onnx model import
- [X] update cast/quantize/dequantize op type infer and converter
- [X] add torch converter
- [X] add svjson converter
- [X] add platform dependent pass for optmize imported model
- [X] test operator to kernel lowering
- [ ] opreorder pass
- [X] simple layergroup pass
- [ ] kernel dialect design
- [ ] kernel pass design
- [ ] kernel op fuse pass
- [ ] kernel active to lut op
- [X] lenet from kernel dialect lowering to hal dialect
- [X] finish packWeight Pass (pack all weight into weight group and address assgin)
- [ ] prototype of layergroupPass
- [ ] hal pass design
- [X] add pass for hal to assign tensorKind
- [ ] hal dialect design
- [ ] infernece pass design
- [ ] toTOSA conversion
- [X] import `pdll` rewrite the canonical patterns
- [X] import `transform` dialect to do transform dynamically
- [ ] consider using safetensor instead of cnpy