TY - GEN A1 - Stüben, Hinnerk T1 - Hadron masses from dynamical, non-perturbatively O(a) improved Wilson fermions N2 - We present results on light hadron masses from simulations of full QCD and report on experiences in running such simulations on a Hitachi SR8000-F1 supercomputer. T3 - ZIB-Report - 00-52 KW - QCD KW - Hadron masses Y1 - 2000 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-6205 ER - TY - GEN A1 - Ilgenfritz, Ernst-Michael A1 - Kerler, Werner A1 - Müller-Preussker, Michael A1 - Stüben, Hinnerk T1 - Parallel tempering in full QCD with Wilson fermions N2 - We study the performance of QCD simulations with dynamical Wilson fermions by combining the Hybrid Monte Carlo algorithm with parallel tempering on $10^4$ and $12^4$ lattices. In order to compare tempered with standard simulations, covariance matrices between sub-ensembles have to be formulated and evaluated using the general properties of autocorrelations of the parallel tempering algorithm. We find that rendering the hopping parameter $\kappa$ dynamical does not lead to an essential improvement. We point out possible reasons for this observation and discuss more suitable ways of applying parallel tempering to QCD. T3 - ZIB-Report - 01-33 KW - QCD KW - parallel tempering KW - correlation analysis Y1 - 2001 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-6593 ER - TY - GEN A1 - Baumann, Wolfgang A1 - Busch, Hubert A1 - Gottschewski, Jürgen A1 - Steinke, Thomas A1 - Stüben, Hinnerk T1 - Berliner Landeshöchstleistungsrechner Parallelrechner Cray T3D/T3E: Betrieb, Nutzung, Projekte, Perspektiven für den Ausbau N2 - Seit fast drei Jahren betreibt das Konrad-Zuse-Zentrum für Informationstechnik Berlin (ZIB) Parallelrechner der höchsten Leistungsklasse im normalen Rechenzentrumsbetrieb. Bereits im Mai 1995 hat das ZIB über seine Erfahrungen mit dem damals leistungsstärksten Parallelrechner Deutschlands berichtet. Das Gesamtkonzept des ZIB sieht weiterhin einen Höchstleistungsrechner als unabdingbaren Bestandteil des High Performance Scientific Computing (HPSC) im ZIB vor. Der vorliegende Bericht beschreibt die aktuelle Konfiguration, Betriebserfahrungen und die Rechnernutzung sowie typische Rechenleistungen, die für einzelne Anwendungsprogramme erzielt wurden. Beschreibungen der Forschungsgebiete mit den Forschungsgruppen, die den Rechner nutzen und die Anforderungen an den Rechnerausbau, die sich aus deren Arbeiten herleiten, beschließen den Bericht. T3 - ZIB-Report - TR-97-08 Y1 - 1997 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-5504 ER - TY - GEN A1 - Ilgenfritz, Ernst-Michael A1 - Kerler, Werner A1 - Müller-Preussker, Michael A1 - Stüben, Hinnerk T1 - Parallel tempering and decorrelation of topological charge in full QCD N2 - The improvement of simulations of QCD with dynamical Wilson fermions by combining the Hybrid Monte Carlo algorithm with parallel tempering is studied on $10^4$ and $12^4$ lattices. As an indicator for decorrelation the topological charge is used. T3 - ZIB-Report - 00-25 KW - QCD KW - parallel tempering KW - topological charge Y1 - 2000 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-5930 ER - TY - GEN A1 - Khan, Arifa Ali A1 - Bakeyev, Timur A1 - Göckeler, Meinulf A1 - Horsley, Roger A1 - Pleiter, Dirk A1 - Rakow, Paul A1 - Schäfer, Andreas A1 - Schierholz, Gerrit A1 - Stüben, Hinnerk T1 - Accelerating Hasenbusch's Acceleration of Hybrid Monte Carlo N2 - Hasenbusch has proposed splitting the pseudo-fermionic action into two parts, in order to speed-up Hybrid Monte Carlo simulations of QCD. We have tested a different splitting, also using clover-improved Wilson fermions. An additional speed-up between 5 and 20\% over the original proposal was achieved in production runs. T3 - ZIB-Report - 03-30 Y1 - 2003 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-7520 ER - TY - GEN A1 - Fleuren, Maria A1 - Stüben, Hinnerk A1 - Zegwaard, Gideon T1 - MoDySim - A parallel dynamical UMTS simulator N2 - UMTS is a 3rd generation mobile telecommunication system which enables multi-service and multi-bit rate communication going beyond the possibilities of previous systems. The simulator MoDySim models UMTS in great detail. Characteristics of UMTS such as soft hand-over and the interdependency of load and capacity among neighbouring cells are challenges for the parallelisation of such a system. In this paper we explain how the software was parallelised and present performance results of a UMTS simulation for the city of Berlin. T3 - ZIB-Report - 03-26 Y1 - 2003 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-7489 ER - TY - GEN A1 - Ilgenfritz, Ernst-Michael A1 - Kerler, Werner A1 - Müller-Preussker, Michael A1 - Sternbeck, André A1 - Stüben, Hinnerk T1 - A numerical reinvestigation of the Aoki phase with $N_f=2$ Wilson fermions at zero temperature N2 - We report on a numerical reinvestigation of the Aoki phase in lattice QCD with two flavors of Wilson fermions where the parity-flavor symmetry is spontaneously broken. For this purpose the Hybrid Monte Carlo algorithm was used and an explicit symmetry-breaking source term $h\bar{\psi} i \gamma_{5} \tau^{3}\psi$ was added to the Wilson fermion action. The order parameter $\langle\bar{\psi}i\gamma_{5}\tau^{3}\psi\rangle$ was studied at several values of $(\beta,\kappa,h)$ on lattices of sizes $4^4$ to $12^4$. Our largest lattices can be considered as infintely large allowing to extrapolate to $h=0$. The existence of a parity-flavor-breaking phase can be confirmed at $\beta=4.0$ and $\beta=4.3$ while we find no sign of parity-flavor-breaking at $\beta=4.6$ and $\beta=5.0$. T3 - ZIB-Report - 03-27 KW - Wilson fermions KW - phase diagram KW - parity-flavor symmetry KW - Aoki phase Y1 - 2003 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-7492 ER - TY - GEN A1 - Streuer, Thomas A1 - Stüben, Hinnerk T1 - Simulations of QCD in the Era of Sustained Tflop/s Computing N2 - 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. T3 - ZIB-Report - 07-48 Y1 - 2008 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-10623 SN - 1438-0064 ER - TY - GEN A1 - Ilgenfritz, Ernst-Michael A1 - Kerler, Werner A1 - Müller-Preussker, Michael A1 - Sternbeck, Andre A1 - Stüben, Hinnerk T1 - Probing the Aoki phase with N_f=2 Wilson fermions at finite temperature N2 - In this letter we report on a numerical investigation of the Aoki phase in the case of finite temperature which continues our former study at zero temperature. We have performed simulations with Wilson fermions at $\beta=4.6$ using lattices with temporal extension $N_{\tau}=4$. In contrast to the zero temperature case, the existence of an Aoki phase can be confirmed for a small range in $\kappa$ at $\beta=4.6$, however, shifted slightly to lower $\kappa$. Despite fine-tuning $\kappa$ we could not separate the thermal transition line from the Aoki phase. T3 - ZIB-Report - 05-48 KW - Wilson fermions KW - phase diagram KW - parity-flavor symmetry KW - Aoki phase KW - finite temperature Y1 - 2005 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-8812 ER - TY - GEN A1 - Hege, Hans-Christian A1 - Stüben, Hinnerk T1 - Vectorization and Parallelization of Irregular Problems via Graph coloring. N2 - Efficient implementations of irregular problems on vector and parallel architectures are generally hard to realize. An important class of problems are Gauß-Seidel iteration schemes applied to irregular data sets. The unstructured data dependences arising there prevent restructuring compilers from generating efficient code for vector or parallel machines. It is shown, how to structure the data dependences by decomposing the underlying data set using graph coloring techniques and by specifying a particular execution order already on the algorithm level. Methods to master the irregularities originating from different types of tasks are proposed. An application is given and some open issues and future developments are discussed. T3 - ZIB-Report - SC-90-16 Y1 - 1990 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-443 ER -