At the Extreme Scaling Workshop at Leibniz Supercomputing Centre a team consisting of Martin Kronbichler, Benjamin Krank, Niklas Fehn, Katharina Kormann and Wolfgang A. Wall scaled their code INDEXA (A high-order discontinuous Galerkin solver for turbulent incompressible flow towards the EXA scale) to the complete phase 1 of SuperMUC on 147,456 compute cores. Our code is a newly developed discontinuous Galerkin solver within the project ExaDG that targets the next generation of supercomputers with arithmetic performance up to an Exaflop/s (10^18 operations per second),  supported by the DFG priority program for exascale software. These developments are part of our effort to develop new high-order methods for coupled problems in computational mechanics. The scaling tests compared the run time of the same program on 8,192 cores with the run time on the whole machine. Our code obtained a speedup of a factor 9 to 12 when increasing the computational resources by a factor of 18, which is remarkable because our code solves a linear systems including multigrid solvers that have extensive phases of global communication. In addition, the speedup is measured against a well-optimized code on 8,192 cores where the main solver components reach about 50% of the arithmetic peak performance. This is an extremely high rate for discretization methods with support for complex geometries and arbitrary meshes. Part of the success was due to the re-design of core multigrid algorithms with improved communication patterns during the workshop. The focus has been on fast turnaround times of the solvers which are necessary for turbulent flow simulations that perform up to a few millions of time steps.