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

GPUs are gaining popularity due to their massive computational parallelism (Jia et al., 2021) and usage in interactive graphics (Nguyen, 2007) or machine learning applications (Mittal & Vaishay, 2019).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) (Hu et al., 2016) 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.