Filters








37 Hits in 2.3 sec

QPACE -- a QCD parallel computer based on Cell processors [article]

H. Baier, H. Boettiger, M. Drochner, N. Eicker, U. Fischer, Z. Fodor, A. Frommer, C. Gomez, G. Goldrian, S. Heybrock, D. Hierl, M. Hüsken, T. Huth (+21 others)
2009 arXiv   pre-print
QPACE is a novel parallel computer which has been developed to be primarily used for lattice QCD simulations.  ...  The compute power is provided by the IBM PowerXCell 8i processor, an enhanced version of the Cell processor that is used in the Playstation 3.  ...  Acknowledgements We acknowledge the funding of the QPACE project provided by the Deutsche Forschungsgemeinschaft (DFG) in the framework of SFB/TR-55 and by IBM.  ... 
arXiv:0911.2174v3 fatcat:pj4wlzlsr5ec5lvlvdaua4gifi

QPACE -- a QCD parallel computer based on cell processors

Dirk Pleiter, Thilo Maurer
2010 Proceedings of The XXVII International Symposium on Lattice Field Theory — PoS(LAT2009)   unpublished
QPACE is a novel parallel computer which has been developed to be primarily used for lattice QCD simulations.  ...  The compute power is provided by the IBM PowerXCell 8i processor, an enhanced version of the Cell processor that is used in the Playstation 3.  ...  Acknowledgements We acknowledge the funding of the QPACE project provided by the Deutsche Forschungsgemeinschaft (DFG) in the framework of SFB/TR-55 and by IBM.  ... 
doi:10.22323/1.091.0001 fatcat:tclpstcokbbrfgxvcln3ktvx2i

Status of the QPACE Project [article]

H. Baier, H. Boettiger, M. Drochner, N. Eicker, U. Fischer, Z. Fodor, G. Goldrian, S. Heybrock, D. Hierl, T. Huth, B. Krill, J. Lauritsen, T. Lippert (+17 others)
2008 arXiv   pre-print
We present a performance analysis of lattice QCD codes on QPACE and corresponding hardware benchmarks.  ...  The machine is a three-dimensional torus of identical processing nodes, based on the PowerXCell 8i processor.  ...  Acknowledgments QPACE is funded by the Deutsche Forschungsgemeinschaft (DFG) in the framework of SFB/ TR-55 and by IBM.  ... 
arXiv:0810.1559v1 fatcat:hk6ephtqdrcxbm5td4c7kvu4xm

Lattice QCD Applications on QPACE [article]

Y. Nakamura, A. Nobile, D. Pleiter, H. Simma, T. Streuer, T. Wettig, F. Winter
2011 arXiv   pre-print
QPACE is a novel massively parallel architecture optimized for lattice QCD simulations. A single QPACE node is based on the IBM PowerXCell 8i processor.  ...  The nodes are interconnected by a custom 3-dimensional torus network implemented on an FPGA. The compute power of the processor is provided by 8 Synergistic Processing Units.  ...  Acknowledgments We thank all members of the QPACE team for their hard and creative work that laid the groundwork for the studies reported on in this paper.  ... 
arXiv:1103.1363v1 fatcat:7aw6glmrq5hylhinsaeyt7mcb4

Solving the Dirac equation on QPACE [article]

Andrea Nobile
2011 arXiv   pre-print
We discuss the implementation and optimization challenges for a Wilson-Dirac solver with Clover term on QPACE, a parallel machine based on Cell processors and a torus network.  ...  We present benchmarks on up to 256 QPACE nodes showing an aggregate sustained performance of about 10 TFlops for the complete solver and very good scaling.  ...  Wettig, A. Frommer, Y. Nakamura, T.Streuer, S. Solbrig, B.Mendl and the whole QPACE team. This work has been supported by the DFG (SFB/TR55, Hadron Physics from Lattice QCD).  ... 
arXiv:1109.4279v1 fatcat:glrwidsnkjavrd5nq22hytarga

Lattice QCD Applications on QPACE

Y. Nakamura, A. Nobile, D. Pleiter, H. Simma, T. Streuer, T. Wettig, F. Winter
2011 Procedia Computer Science  
QPACE is a novel massively parallel architecture optimized for lattice QCD simulations. A single QPACE node is based on the IBM PowerXCell 8i processor.  ...  The nodes are interconnected by a custom 3-dimensional torus network implemented on an FPGA. The compute power of the processor is provided by 8 Synergistic Processing Units.  ...  Acknowledgments We thank all members of the QPACE team for their hard and creative work that laid the groundwork for the studies reported on in this paper.  ... 
doi:10.1016/j.procs.2011.04.089 fatcat:3swjjkhh7bcgxnomtjcwid5ili

QPACE: Quantum Chromodynamics Parallel Computing on the Cell Broadband Engine

Gottfried Goldrian, Thomas Huth, Benjamin Krill, Jack Lauritsen, Heiko Schick, Ibrahim Ouda, Simon Heybrock, Dieter Hierl, Thilo Maurer, Nils Meyer, Andreas Schäfer, Stefan Solbrig (+8 others)
2008 Computing in science & engineering (Print)  
An alternative approach uses compute nodes based on a commercial processor tightly coupled to a custom-designed network processor.  ...  Application-driven computers for Lattice Gauge Theory simulations have often been based on system-on-chip designs, but the development costs can be prohibitive for academic project budgets.  ...  We gratefully acknowledge important contributions to QPACE by Eurotech (Italy) and Knürr (Germany).  ... 
doi:10.1109/mcse.2008.153 fatcat:2payrontpfhuhgyywk3b2ozbga

QPACE 2 and Domain Decomposition on the Intel Xeon Phi [article]

Paul Arts, Jacques Bloch, Peter Georg, Benjamin Glaessle, Simon Heybrock, Yu Komatsubara, Robert Lohmayer, Simon Mages, Bernhard Mendl, Nils Meyer, Alessio Parcianello, Dirk Pleiter (+6 others)
2015 arXiv   pre-print
We give an overview of QPACE 2, which is a custom-designed supercomputer based on Intel Xeon Phi processors, developed in a collaboration of Regensburg University and Eurotech.  ...  We give some general recommendations for how to write high-performance code for the Xeon Phi and then discuss our implementation of a domain-decomposition-based solver and present a number of benchmarks  ...  Overview of QPACE 2 Between QPACE 1 and QPACE 2, the acronym QPACE changed its meaning from "QCD Parallel Computing on the Cell Processor" to "QCD Parallel Computing Engine".  ... 
arXiv:1502.04025v1 fatcat:s24tkzmwivhynfqu3x3cbohlpy

Lattice Boltzmann fluid-dynamics on the QPACE supercomputer

L. Biferale, F. Mantovani, M. Pivanti, M. Sbragaglia, A. Scagliarini, S.F. Schifano, F. Toschi, R. Tripiccione
2010 Procedia Computer Science  
QPACE is a massively parallel application-driven system powered by the Cell processor.  ...  In this paper we present an implementation for the QPACE supercomputer of a Lattice Boltzmann model of a fluid-dynamics flow in 2 dimensions.  ...  We furthermore acknowledge access to QPACE and eQPACE during the bring-up phase of these systems.  ... 
doi:10.1016/j.procs.2010.04.119 fatcat:quubncme3vgxxcrot2aefkcuzu

High-Performance Computing Applications on Novel Architectures

Volodymyr Kindratenko, George K. Thiruvathukal, Steven Gottlieb
2008 Computing in science & engineering (Print)  
The IBM PowerXCell 8i-based Roadrunner supercomputer recently acquired by Los Alamos National Laboratory (LANL) is the first to achieve a petaflop per second on the Linpack benchmark; it's based on a new  ...  G u e s t E d i t o r s ' I n t r o d u c t i o n Computing in SCienCe & engineering 13 T his is an exciting time for highperformance computing (HPC) on novel architectures.  ...  massively parallel computer called QPACE that's optimized for applications in lattice quantum chromodynamics (QCD).  ... 
doi:10.1109/mcse.2008.149 fatcat:pdoldufmsfepheujc66z6hj4ma

An FPGA-based Torus Communication Network [article]

Marcello Pivanti, Sebastiano Fabio Schifano, Hubert Simma
2011 arXiv   pre-print
The design includes the VHDL code to implement on latest FPGA devices a network processor, which can be accessed by the CPU through a PCIe interface and which controls the external PHYs of the physical  ...  Moreover, a Linux driver and a library implementing custom communication APIs are provided. The TNW has been successfully integrated in two recent parallel machine projects, QPACE and AuroraScience.  ...  Acknowledgements: We like to thank the members of the QPACE project, in particular T. Mauer, A. Nobile, D. Pleiter, and T.  ... 
arXiv:1102.2346v1 fatcat:egguuv7sqzcglip6ln366bsr7i

Status of the QPACE Project

Andrea Nobile
2009 Proceedings of The XXVI International Symposium on Lattice Field Theory — PoS(LATTICE 2008)   unpublished
Acknowledgments QPACE is funded by the Deutsche Forschungsgemeinschaft (DFG) in the framework of SFB/ TR-55 and by IBM.  ...  Unlike in other existing Cell-based parallel machines, in QPACE we can move data directly from the local store (LS) of any SPE on one node to the LS of any SPE of one of the 6 neighboring nodes.  ...  Conclusion QPACE is a next-generation massively parallel computer optimized for LQCD applications.  ... 
doi:10.22323/1.066.0039 fatcat:2ez57eyr3vbxtmynrqmlrwvgpm

Solving the Dirac equation on QPACE

Andrea Nobile
2011 Proceedings of The XXVIII International Symposium on Lattice Field Theory — PoS(Lattice 2010)   unpublished
We discuss the implementation and optimization challenges for a Wilson-Dirac solver with Clover term on QPACE, a parallel machine based on Cell processors and a torus network.  ...  We present benchmarks on up to 256 QPACE nodes showing an aggregate sustained performance of about 10 TFlops for the complete solver and very good scaling.  ...  Wettig, A. Frommer, Y. Nakamura, T.Streuer, S. Solbrig, B.Mendl and the whole QPACE team. This work has been supported by the DFG (SFB/TR55, Hadron Physics from Lattice QCD).  ... 
doi:10.22323/1.105.0034 fatcat:6i4rnmas35f7lb5w64iy6doxyu

Editorial

M. Weigel, A. Arnold, P. Virnau
2012 The European Physical Journal Special Topics  
A rather long history of such machines exists in particular in lattice field theory, most recently featuring the QPACE machine based on the Cell processor, and in astrophysical particle simulations, where  ...  a series GRAPE of special-purpose computers based on field-programmable gate arrays (FPGAs) has played a significant a  ...  A rather long history of such machines exists in particular in lattice field theory, most recently featuring the QPACE machine based on the Cell processor, and in astrophysical particle simulations, where  ... 
doi:10.1140/epjst/e2012-01633-0 fatcat:kutoljli3fa5vhwylf2fszofsq

QPACE 2 and Domain Decomposition on the KNC

Tilo Wettig, Paul Arts, Jacques Bloch, Peter Georg, Benjamin Glaessle, Simon Heybrock, Yu Komatsubara, Robert Lohmayer, Simon Mages, Bernhard Mendl, Nils Meyer, Alessio Parcianello (+6 others)
2015 Proceedings of The 32nd International Symposium on Lattice Field Theory — PoS(LATTICE2014)   unpublished
We give an overview of QPACE 2, which is a custom-designed supercomputer based on Intel Xeon Phi processors, developed in a collaboration of Regensburg University and Eurotech.  ...  We give some general recommendations for how to write high-performance code for the Xeon Phi and then discuss our implementation of a domain-decomposition-based solver and present a number of benchmarks  ...  A follow-up project, QPACE 3, will use the KNL processor and have a target peak performance of about 4 Pflop/s in double precision.  ... 
doi:10.22323/1.214.0021 fatcat:7qo36u3e7fewjmirhiucc35jg4
« Previous Showing results 1 — 15 out of 37 results