Raptor

Raptor is an MLIR compiler for ONNX neural networks targeting processing-in-memory (PIM) architectures. It extends ONNX-MLIR and emits per-core .pim binaries, memory.bin, config.json, and weights for the simulators under backend-simulators/pim/. Optional JSON instructions use --pim-emit-json.

The target has shared host memory, PIM cores with ReRAM crossbars, explicit inter-core communication, and no hardware branches or loops. Lowering, scheduling, and memory planning keep repeated work compact until codegen.

Build

Initialize submodules:

git submodule update --init --recursive

Follow ONNX-MLIR's LLVM/MLIR build instructions. The CI workflow records dependency versions and setup, including CMake and Protobuf. Rust stable is required for the functional simulator. Python requirements include the Graph Explorer and need Python 3.13+; create the repository environment if absent, then install:

python3.13 -m venv .venv
.venv/bin/python -m pip install -r requirements.txt

If compatible Protobuf libraries are unavailable locally:

git clone --depth 1 --branch v34.0 https://github.com/protocolbuffers/protobuf
cmake -S protobuf -B protobuf/build -G Ninja \
  -DCMAKE_BUILD_TYPE=Release -Dprotobuf_BUILD_TESTS=OFF
cmake --build protobuf/build
sudo cmake --install protobuf/build

Configure and build Raptor, adjusting MLIR_DIR to your LLVM build:

cmake -S . -B build_release -G Ninja \
  -DCMAKE_BUILD_TYPE=Release \
  -DONNX_MLIR_ACCELERATORS=PIM \
  -DLLVM_ENABLE_ASSERTIONS=ON \
  -DMLIR_DIR="$PWD/onnx-mlir/llvm-project/build_release/lib/cmake/mlir"
cmake --build ./build_release

Use release builds first. For debugging, configure build_debug with -DCMAKE_BUILD_TYPE=Debug and the matching MLIR package, then run cmake --build ./build_debug. Use debug only for small cases requiring symbols. Optional mold linking uses -fuse-ld=mold in CMAKE_{EXE,SHARED,MODULE}_LINKER_FLAGS.

Always build through cmake --build; invoking ninja directly bypasses CMake configuration and generated shim updates.

Compile a model

./build_release/Release/bin/onnx-mlir model.onnx -o /tmp/raptor/model \
  --maccel=PIM --EmitPimCodegen \
  --crossbar-count=64 --crossbar-size=128 --core-count=144

This writes artifacts under /tmp/raptor/pim/. All three hardware flags are mandatory positive values. The example uses the development/YOLO profile; Pimcomp comparison profiles differ, and validation defaults to Arch-A.

Documentation

Start with the documentation index. It links the compiler architecture, compiler options, and evaluation methodology.

Validation commands, the operation inventory, and the Graph Explorer remain beside their components.