LinearSolve.jl: High-Performance Unified Interface for Linear Solvers in Julia. Easily switch between factorization and Krylov methods, add preconditioners, and all in one interface.
The benchmarks have pretty conclusively shown that MKL's LU factorization is just so much better than OpenBLAS that we should effectively always use it. What this does is make MKL_jll into a dependency of LinearSolve.jl and then uses the direct calls to the binary as part of the default algorithm when it's available (it won't be available on systems where MKL does not exist, like M2 macbooks). This uses the direct calls instead of LibBLASTrampoline and thus does not effect the user's global state, thus only being a local change that simply accelerates packages using LinearSolve (i.e. all of SciML).
The benchmarks have pretty conclusively shown that MKL's LU factorization is just so much better than OpenBLAS that we should effectively always use it. What this does is make MKL_jll into a dependency of LinearSolve.jl and then uses the direct calls to the binary as part of the default algorithm when it's available (it won't be available on systems where MKL does not exist, like M2 macbooks). This uses the direct calls instead of LibBLASTrampoline and thus does not effect the user's global state, thus only being a local change that simply accelerates packages using LinearSolve (i.e. all of SciML).