hpc-ch Forum on GPU – Video on Multi-resolution flow simulations on multi/many-core architectures
While the peak performance and energy efficiency of computing hardware are constantly growing, the development of fast scientific software is experiencing an important paradigm shift. Efficient algorithm implementations face rigid constraints about memory layouts, access patterns and FLOP/Byte ratios.
Diego Rossinelli (ETH Zurich) discusses the design of wavelet-based adaptive solvers for compressible flow simulations that run effectively on multi- and many-core architectures.