Requirements

The list of required software to use the library includes:

• CUDA Toolkit 12.6.3 or newer, which includes nvJitLink library

• Supported CUDA compiler (C++17 required)

• Supported host compiler (C++17 required)

• (Optionally) CMake (version 3.18 or greater)

Dependencies:

• commonDx (shipped with MathDx package)

• CUTLASS (shipped with MathDx package)

Supported Compilers

CUDA Compilers:

• NVCC 12.6.77+ (CUDA Toolkit 12.6.3 or newer)

• (Experimental support) NVRTC 12.6.77+ (CUDA Toolkit 12.6.3 or newer)

Host / C++ Compilers:

• GCC 7+

• Clang 9+ (only on Linux/WSL2)

Note

We recommend always using the latest CUDA Toolkit and NVCC compiler, and GCC 9+.

Note

HPC SDK nvc++ is not yet a supported host compiler in cuSolverDx.

Note

cuSolverDx emits errors for unsupported versions of C++ standard. These errors could be silenced by defining CUSOLVERDX_IGNORE_DEPRECATED_DIALECT during compilation, but cuSolverDx is not guaranteed to compile and work correctly in such configurations.

Supported System Architecture

• x86_64

• AArch64

Warning

Compiling cuSolverDx on Windows with MSVC or on certain ARM AArch64 architectures is experimental, ONLY supported when using NVRTC and nvJitLink as presented in the NVRTC Example.