The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

Go to file

Sean Silva eaeb4011e6 Lower !shape.shape to SSA values. This uses an approach inspired by what is done in IREE. See comments on LowerRankedShapes.cpp for how it works. The basic gist is that we have an op that creates a !shape.shape from a set of SSA values representing the extents, and then iteratively replace any op producing a !shape.shape with instances of that op.		2020-05-13 17:20:23 -07:00
include/npcomp	Lower !shape.shape to SSA values.	2020-05-13 17:20:23 -07:00
lib	Lower !shape.shape to SSA values.	2020-05-13 17:20:23 -07:00
python	Add implicit constant capture.	2020-05-08 17:55:02 -07:00
python_native	Add implicit constant capture.	2020-05-08 17:55:02 -07:00
test	Lower !shape.shape to SSA values.	2020-05-13 17:20:23 -07:00
tools	Add -DCMAKE_EXPORT_COMPILE_COMMANDS=TRUE	2020-05-11 12:58:42 -07:00
.clang-format	Add stub numpy dialect.	2020-04-26 17:20:58 -07:00
.gitignore	Add MLIRContext.dense_elements_attr to create an attribute from a python buffer/array.	2020-05-08 17:36:07 -07:00
CMakeLists.txt	Move python native library to python_native/_npcomp...so.	2020-05-06 22:44:12 -07:00
LICENSE	Add license	2020-04-26 20:10:24 -07:00
README.md	Update llvm-project to 310d32cb80a611e6384a921e85607fea05841f26	2020-05-11 15:12:47 -07:00
contributing.md	Add contributing.md	2020-04-26 20:17:16 -07:00

README.md

npcomp - An aspirational MLIR based numpy compiler

This is a research prototype of MLIR dialects for representing numpy programs, and a set of reference tracing/compiler tools. The primary purpose at this point is to establish a solid modeling of restricted Python programs and Numpy based computations in MLIR. While this project will provide some reference implementations to prove the design, the intention is to align this with the broader set of tools that exist at this level of abstraction.

Design Notes

As I work through things, I've been jotting down some design notes:

Quick start

LLVM_VERSION=10
export CC=clang-$LLVM_VERSION
export CXX=clang++-$LLVM_VERSION
export LDFLAGS=-fuse-ld=$(which ld.lld-$LLVM_VERSION)
export LLVM_SRC_DIR=/path/to/llvm-project

# Check out last known good commit.
(cd $LLVM_SRC_DIR && git checkout 310d32cb80a611e6384a921e85607fea05841f26)

./tools/install_mlir.sh
./tools/cmake_configure.sh


# ./tools/test_all.sh runs all of these commands.
cd build
ninja
ninja check-npcomp-opt
# Note: currently, python tests run separately
./python/run_tests.py

Interactive Use

The cmake configuration populates symlinks in the build/python directory mirroring the source layout. This allows edit-run without rebuilding (unless if files are added/removed).

Configuring the PYTHONPATH should be sufficient to run any interactive tooling (python3, Jupyter/Colab, etc).

export PYTHONPATH="$(realpath build/python):$(realpath build/python_native)"

The run_tests.py script is special in that it sets up the PYTHONPATH correctly when run.

Note that running the cmake_configure.sh script will also output a .env file in the workspace folder with the correct PYTHONPATH set. This allows tools like VSCode to work by default for debugging.

Things to look at:

python/npcomp/tracing/mlir_trace_test.py : Simple test case of tracing a function to an MLIR module.

Notes:

Python sources are symlinked to the output directory at configure time. Adding sources will require a reconfigure. Editing should not.
It is a very common issue to have both python 2.7 (aka. "python") and python 3.x (aka. "python3") on a system at a time (and we can only hope that one day this ends). Since the native library at development time binds to a specific version, if you try to run with a different python, you will get an error about the "native" module not being found.