vkCompViz: Universal C++ Library for GPU-Based Experiments

GPUs are gaining popularity due to their massive computational parallelism and usage in interactive graphics or machine learning applications. Prototyping GPU-executed experiments is often time-consuming due to the complexity of GPU-related APIs. Multiplatform and multi-vendor support is also not guaranteed with all existing APIs. The vkCompViz C++ library offers a simple way to write a GPGPU (general-purpose computing on graphics processing units) program. Only the paths to files with GPU code (shader/kernel), paths to input images, or a buffer of arbitrary input data need to be provided by the host application. The library is capable of running a sequence of compute shaders, processing the input data, and storing the result or presenting it in a window. Memory usage and computational time can also be automatically measured.