1062 eng reportzib 0 2008-02-26 2008-02-26 -- The latest machine generation installed at supercomputer centres in Germany offers a peak performance in the tens of Tflop/s range. We study performance and scaling of our quantum chromodynamics simulation programme BQCD that we obtained on two of these machines, an IBM Blue Gene/L and an SGI Altix 4700. We compare the performance of Fortran/MPI code with assembler code. The latter allows to exploit concurrency at more levels, in particular in overlapping communication and computation as well as prefetching data from main memory. 07-48 1438-0064 1091 urn:nbn:de:0297-zib-10623 Appeared in C. Bischof, M. Brückner, P. Gibbon, G. Goubert, T. Lippert, B. Mohr, F. Peters (Eds.), Parallel Computing: Architectures, Algorithms and Applications, NIC Series, Vol. 38 (2007), 535--542. Thomas Streuer unknown unknown Hinnerk Stüben 07-48 Informatik, Informationswissenschaft, allgemeine Werke Distributed Algorithms and Supercomputing https://opus4.kobv.de/opus4-zib/files/1062/ZR_07_48.pdf https://opus4.kobv.de/opus4-zib/files/1062/ZR_07_48.ps