mirror of
https://github.com/zama-ai/concrete.git
synced 2026-02-09 20:25:34 -05:00
d9363ffb27
The bufferization of the BConcrete dialect emits calls to Concrete wrapper functions and casts all memrefs to ranked memrefs with dynamic strides and an implicit identity layout map. The implicit identity map does not allow for casts of memrefs with non-zero offsets, e.g., resulting from folding of memrefs related to intermediate results passed as operands to the operation implemented by a wrapper. Casting to memrefs symbolic offsets in the layout map (e.g., `[d0, d1, ...](s0, s1, ...) -> (d0 + s0, d1 + s1, ...)`) allows for more flexibility, in particular this adds support for memrefs with non-zero, constant offsets returned by operations generating intermediate results.
Building the compiler
Install MLIR following https://mlir.llvm.org/getting_started/ Use commit c2415d67a564
Install pybind11:
pip install pybind11
Build concrete library:
git clone https://github.com/zama-ai/concrete_internal
cd concrete_internal
git checkout engine_c_api
cd concrete-ffi
RUSTFLAGS="-C target-cpu=native" cargo build --release
Generate the compiler build system, in the build directory
export LLVM_PROJECT="PATH_TO_LLVM_PROJECT"
export CONCRETE_PROJECT="PATH_TO_CONCRETE_INTERNAL_PROJECT"
make build-initialized
Build the compiler
make concretecompiler
Test the compiler
#TODO: let cmake set this PATH
export LD_LIBRARY_PATH="path_to_concrete-compiler/compiler/build/lib/Runtime/"
make test
Run the compiler
./build/src/concretecompiler