Extending LLVM for lightweight SPMD vectorization: using SIMD and vector instructions easily from any language

Popular parallel programming environments such as CUDA or OpenMP require considerable compiler support and runtime libraries and are therefore only available for a few programming languages and/or targets. We present an approach to vectorizing kernels written in an existing general-purpose language that requires minimal changes to compiler front-ends. Programmers annotate parallel (SPMD) code regions with a few intrinsic functions, which then guide an ordinary automatic vectorization algorithm. This mechanism allows programming SIMD and vector processors without many of the complexities of more powerful parallel programming environments. Our prototype implementation, based on a custom LLVM pass, is integrated into C, C++ and Rust compilers using only 29--37 lines of frontend-specific code each.