1f4200e88a | ||
---|---|---|
include | ||
lib | ||
samples | ||
test | ||
tools | ||
.clang-format | ||
.gitignore | ||
CMakeLists.txt | ||
README.md |
README.md
ScaleHLS Project (SCALEHLS)
This project aims to create a framework that ultimately converts an algorithm written in a high level language into an efficient hardware implementation. With multiple levels of intermediate representations (IRs), MLIR appears to be the ideal tool for exploring ways to optimize the eventual design at various levels of abstraction (e.g. various levels of parallelism). Our framework will be based on MLIR, it will incorporate a backend for high level synthesis (HLS) C/C++ code. However, the key contribution will be our parametrization and optimization of a tremendously large design space.
Quick Start
This setup assumes that you have built LLVM and MLIR in $LLVM_BUILD_DIR
. To build and launch the tests, run
mkdir build && cd build
cmake -G Ninja .. -DMLIR_DIR=$LLVM_BUILD_DIR/lib/cmake/mlir -DLLVM_EXTERNAL_LIT=$LLVM_BUILD_DIR/bin/llvm-lit
cmake --build . --target check-scalehls
After the installation and test successfully completed, you should be able to run
bin/scalehls-translate -emit-hlscpp ../test/EmitHLSCpp/test_*.mlir
TODO List
scalehls-translate EmitHLSCpp
- Test HLS C++ emitter with some real benchmarks;
- TODOs in EmitHLSCpp.cpp;
- Create testcase for each important operation;
- Support memref/tensor cast/view/subview operations;
- Support atomic/complex/extend -related operations.
scalehls-opt
- Initial implementation.
HLSCpp Dialect
- Think about the dialect design.
- Initial implementation.