Consolidate and advance the GPU infrastructure in Clad

Automatic Differentiation(AD) is a set of techniques to evaluate the derivative of functions specified by a computer program. Clad is a Clang-based automatic differentiation tool that transforms C++ source code to compute derivatives. Clad have demonstrated promising support for GPU-based differentiation through prior efforts involving CUDA, Thrust, and integrations with applications such as XSBench and LULESH. However, all this works remains fragmented and inconsistently tested. This project aims to consolidate the fragmented work and advance Clad’s GPU infrastructure into a robust and consistent system.