Inverting matrices is a crucial part in many algorithms in linear algebra, computer graphics and data analysis. There are many libraries providing algorithms to achieve this but none that allow for calling from the GPU context. GPUs and accelerators become more and more prevalent in high performance computers. Having no ready-to-use implementation scientists need to write their own algorithms. In this thesis the Gauß-Elimination algorithm is implemented using OpenMP, OpenACC, CUDA, HIP and OpenCL. These implementations are then compared to the already existing libraries Eigen and cuBLAS in terms of speed, precision and implementation effort.

@misc{PSOGOTUTGM22,
	author	 = {Yannik Koenneker},
	title	 = {{Performance study on GPU offloading techniques using the Gauß matrix inverse algorithm}},
	advisors	 = {Georgiana Mania},
	year	 = {2022},
	month	 = {03},
	school	 = {Universität Hamburg},
	howpublished	 = {{Online \url{https://wr.informatik.uni-hamburg.de/_media/research:theses:yannik_koenneker_performance_study_on_gpu_offloading_techniques_using_the_gauss_matrix_inverse_algorithm.pdf}}},
	type	 = {Bachelor's Thesis},
	abstract	 = {Inverting matrices is a crucial part in many algorithms in linear algebra, computer graphics and data analysis. There are many libraries providing algorithms to achieve this but none that allow for calling from the GPU context. GPUs and accelerators become more and more prevalent in high performance computers. Having no ready-to-use implementation scientists need to write their own algorithms. In this thesis the Gauß-Elimination algorithm is implemented using OpenMP, OpenACC, CUDA, HIP and OpenCL. These implementations are then compared to the already existing libraries Eigen and cuBLAS in terms of speed, precision and implementation effort.},
}