This application concerns using the HPC resources for evaluation of novel algorithms of resource efficient classification. In this evaluation we need only CPU cluster. The research is partially funded by Swedish Foundation for Strategic Research (SSF, grant nos. UKR22-0024, UKR24-0014), the Swedish Research Council (VR) Scholars at Risk (SAR) Sweden (VR SAR grant no. GU 2022/1963), the Swedish Research Council (VR grant no. 2022-04657). The overarching goal of the research projects is to solve the grand challenge of fast and power-efficient Artificial Intelligence (AI) . Solving this challenge is important for more rapid emergence of such intelligent technologies as self-driving cars, autonomous robots, large scale information retrieval systems, which in turn are essential for the sustainable development of cities and industries as well as building resilient infrastructures. The emerging computing technology, i.e. in-memory computing (Karunaratne, G., et al. (2020a). In-Memory Hyper-dimensional Computing. Nature Electronics, pages 1–14), delivers great promises for orders of magnitude improvements in power efficiency of computations. It is prospected to be a game-changing technology for fast and energy efficient AI. The theoretical core of the project is Vector Symbolic Architectures also known as hyperdimensional computing, i.e., VSA/HDC (Kanerva, P.: Hyperdimensional computing: An introduction to computing in distributed representation with high-dimensional random vectors. In: Cognitive Computation (2009), vol. 1 p. 139–159). For the execution of the project it is essential to perform large scale experiments involving massive computations on vectors of extremely high dimensionality up to a million.