BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CERN//INDICO//EN BEGIN:VEVENT SUMMARY:Large Synoptic Survey Telescope (LSST): New Algorithms and Archite ctures DTSTART;VALUE=DATE-TIME:20120503T120000Z DTEND;VALUE=DATE-TIME:20120503T124500Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-24@cern.ch DESCRIPTION:Speakers: Dr. JIM\, Bosch ()\nWhen it enters operation\, the L arge Synoptic Survey Telescope will produce 15TB of image data each night\ , more than any other optical survey. In many respects\, applying existin g algorithms at this scale is a significant technical challenge on its own . However\, the improved statistical errors and the fact that LSST is "de ep\, wide\, and fast" will demand algorithms that are qualitatively differ ent from those sufficient for surveys that are smaller in any one of these dimensions. In many cases\, the computational demands for these more com plex algorithms are considerably greater. In this talk\, I will touch on several of these computational problems and the LSST collaboration's plans to address them\, with a focus on difference imaging\, image coaddition\, and galaxy shape measurement for weak lensing. A particular challenge fo r LSST is that the state-of-the-art in both algorithm development and hard ware architecture may change significantly before the survey begins\, and our approach must be flexible enough to take advantage of both.\n\nhttp:// indico.cern.ch/contributionDisplay.py?contribId=24&confId=159120 LOCATION:Department of Astrophysical Sciences\, University of Princeton\, USA URL:http://indico.cern.ch/contributionDisplay.py?contribId=24&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:White Paper plan and writing assignments DTSTART;VALUE=DATE-TIME:20120504T094500Z DTEND;VALUE=DATE-TIME:20120504T110000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-25@cern.ch DESCRIPTION:Speakers: Prof. KATSANEVAS\, Stavros (CNRS/IN2P3)\nhttp://indi co.cern.ch/contributionDisplay.py?contribId=25&confId=159120 LOCATION:IN2P3/CNRS\, France URL:http://indico.cern.ch/contributionDisplay.py?contribId=25&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:Technology and Market Trend in Computing DTSTART;VALUE=DATE-TIME:20120504T074500Z DTEND;VALUE=DATE-TIME:20120504T083000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-13@cern.ch DESCRIPTION:Speakers: Dr. PANZER-STEINDEL\, Bernd ()\nFor the past 15 year s the CERN IT department has launched regular (every\n~2-3 years) technolo gy+market evaluations which are\nused as input for the computer center arc hitecture and cost/budget\nplanning activities.\nThe talk will try to give an overview of the various market and technology\ndevelopments in the are a of data processing and data storage. This will cover\nprocessors\, memor y\, HDDs\, SSDs and some future technologies.\nCost and technology trends for the next 3-5 years will be discussed.\n\nhttp://indico.cern.ch/contrib utionDisplay.py?contribId=13&confId=159120 LOCATION:CERN\, Switzerland URL:http://indico.cern.ch/contributionDisplay.py?contribId=13&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:Frontiers of Volunteer Computing DTSTART;VALUE=DATE-TIME:20120504T070000Z DTEND;VALUE=DATE-TIME:20120504T074500Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-12@cern.ch DESCRIPTION:Speakers: Prof. ANDERSON\, David (UC Berkeley)\nTen years from now\, as today\, the majority of the world's computing and storage resour ces will reside not in machine rooms but in the hands of consumers. Throug h volunteer computing much of these resources will be available to science . The first PetaFLOPS computation was done using volunteered computers\, a nd the same is likely to be true for the ExaFLOPS milestone. Volunteer com puting has existed for a decade and is being used to do breakthrough scien ce in areas ranging from molecular biology to radio astronomy\; however\, it is an emerging technology and has potential applications in many new ar eas\, including those involving storage and processing of large data. The landscape of volunteer computing is shaped by many factors. Some of these involve hardware technology\; mobile devices\, Graphics Processing Units ( GPUs)\, wired and wireless communication networks\, memory\, and storage. I will discuss trends in these areas. Other factors involve software: tech nologies like virtualization are making it easier for scientists to use vo lunteer computing\, while the rise of proprietary software environments an d vendor-controlled application markets is making it more difficult. Final ly\, I will discuss the organizational\, economic\, and marketing issues t hat must be addressed for volunteer computing to achieve its potential.\n\ nhttp://indico.cern.ch/contributionDisplay.py?contribId=12&confId=159120 LOCATION:UC Berkeley\, USA URL:http://indico.cern.ch/contributionDisplay.py?contribId=12&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:Welcome to the AEI\, and introduction to ASPERA DTSTART;VALUE=DATE-TIME:20120503T073000Z DTEND;VALUE=DATE-TIME:20120503T074500Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-23@cern.ch DESCRIPTION:Speakers: Prof. ALLEN\, Bruce ()\nI'll first give you a lightn ing overview of the AEI. The Max-Planck Institute for Gravitational Physic s\, also known as the Albert Einstein Institute or AEI\, is the world's la rgest institute devoted to the study of gravitation. The main focus in Ha nnover is the detection of gravitational waves. These were first predicte d by Einstein about a century ago\; we hope to make the first direct detec tions with the LIGO/VIRGO and GEO instruments in the coming five years. S earching for weak gravitational-wave signals in detector noise is a large- scale computing and data analysis problem\, hence the relevance of this AS PERA workshop.\n\nI'll then give you a lightning overview to ASPERA. ASPER A is a network of European national government agencies responsible for co ordinating and funding national research efforts in Astroparticle Physics. Within the ERA-NET scheme of the European Commission\, ASPERA started in July 2006. After a first successful three-year period\, ASPERA\, as ASPERA 2\, is now continuing for another three-year programme towards the devel opment of a sustainable body for astroparticle physics in Europe. ASPERA 2 is funded by the European Commission through the 7th Framework Programme. \n\nhttp://indico.cern.ch/contributionDisplay.py?contribId=23&confId=15912 0 LOCATION:AEI Hannover\, Germany URL:http://indico.cern.ch/contributionDisplay.py?contribId=23&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:Computing in the context of Cherenkov Telescope Array (CTA) DTSTART;VALUE=DATE-TIME:20120503T124500Z DTEND;VALUE=DATE-TIME:20120503T133000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-19@cern.ch DESCRIPTION:Speakers: Dr. LAMANNA\, Giovanni (LAPP)\nThe Cherenkov Telesco pe Array (CTA) – an array of tens of Cherenkov telescopes deployed on a n unprecedented scale – will allow the European scientific community to remain at the forefront of research in the field of very high energy gamma -ray astronomy.\n\nOne of the challenges to design the CTA observatory is to handle the large amounts of data generated by the instrument and to pro vide simple and efficient user access at any level and according to astrop hysical standards in order to serve the data and the software for data ana lysis to the physics community. The high data rate of CTA together with th e large computing power requirements for Monte Carlo simulations\, fundame ntal tool for data selection and calibration\, demand dedicated computer r esources which can be well handled through a DCI approach. Preliminary wor ks and ideas about the organization of a coherent Data Management system f or CTA will be presented.\n\nhttp://indico.cern.ch/contributionDisplay.py? contribId=19&confId=159120 LOCATION:IN2P3/CNRS\, France URL:http://indico.cern.ch/contributionDisplay.py?contribId=19&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:Energy Efficient Computing with GPUs DTSTART;VALUE=DATE-TIME:20120503T074500Z DTEND;VALUE=DATE-TIME:20120503T083000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-18@cern.ch DESCRIPTION:Speakers: Dr. LANFEAR\, Timothy ()\nThe past five years have s een the use of graphical processing units (GPUs) for computation grow from being of interest to a handful of early adopters to a mainstream technolo gy used in the world's largest supercomputers. One of the attractions of t he GPU architecture is the efficiency with which it can perform computatio ns. Energy efficiency is a key concern in the design of all modern computi ng systems\, from the lowest power mobile devices to the largest supercomp uters\; it will be paramount in the push to exascale computing. We discuss the Echelon project\, and how the NVIDIA GPU architecture will evolve ove r the coming 5-10 years. Echelon is a DARPA-funded project investigating e fficient parallel computer architectures for the Exascale era.\n\nhttp://i ndico.cern.ch/contributionDisplay.py?contribId=18&confId=159120 LOCATION:NVIDIA\, UK URL:http://indico.cern.ch/contributionDisplay.py?contribId=18&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:GPUs in real-time discovery of millisecond radio transients with L OFAR DTSTART;VALUE=DATE-TIME:20120503T152000Z DTEND;VALUE=DATE-TIME:20120503T160000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-16@cern.ch DESCRIPTION:Speakers: Dr. KARASTERGIOU\, Aris ()\nI will present a project that uses GPU technology with the next-generation LOFAR radio telescope\, to search for bright millisecond bursts of radio emission from astrophysi cal sources. GPUs provide the computing power necessary to remove in real time the effects of propagation of the radio emission through the ionised interstellar medium. I will present details of the specific problem\, our current approach for optimisation of the relevant GPU code\, and why GPUs are currently the most appropriate solution compared to other multicore te chnologies. Finally\, I will describe how our current work fits in the con text of the Square Kilometer Array and its pathfinders for the science of astrophysical radio transients.\n\nhttp://indico.cern.ch/contributionDispl ay.py?contribId=16&confId=159120 LOCATION:University of Oxford\, UK URL:http://indico.cern.ch/contributionDisplay.py?contribId=16&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:Computing Challenges at the Pierre Auger Observatory DTSTART;VALUE=DATE-TIME:20120504T090000Z DTEND;VALUE=DATE-TIME:20120504T094500Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-28@cern.ch DESCRIPTION:Speakers: CHUDOBA\, Jiri (Acad. of Sciences of the Czech Rep. (CZ))\nPierre Auger Observatory needs a lot of computing resources for sim ulation of cosmic ray showers with ultra-high energies up to 10^21 eV. We are able to use simultaneously several thousand cores and generate more th an 1 TB of data daily in the current EGI grid environment. We are limited by available resources and a long duration of a single job for very high e nergies\, which is already simplified by thinning parameter in the Corsika simulation program. Details of the time traces which would be useful for mass composition analyses and hadronic interaction physics get lost by th inning. Thousand times more computing power and correspondingly increased storage is needed for simulations without thinning. Significant speedup co uld be obtained by using many CPUs or even GPUs for generation of a single shower. We discuss the current trends in the middleware heading to a prov ision of a whole worker node with many cores to a single parallel job. The expected development in the Corsika and Geant4 towards parallelization an d usage of GPU is needed for an efficient usage of the new infrastructure. Possibilities of computing in clouds are also discussed.\n\nhttp://indico .cern.ch/contributionDisplay.py?contribId=28&confId=159120 LOCATION:Institute of Physics Academy of Sciences of the Czech Republic\, Czech Republic URL:http://indico.cern.ch/contributionDisplay.py?contribId=28&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:the ASPERA process DTSTART;VALUE=DATE-TIME:20120503T114500Z DTEND;VALUE=DATE-TIME:20120503T120000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-29@cern.ch DESCRIPTION:Speakers: KATSANEVAS\, Stavros (CNRS/IN2P3)\nhttp://indico.cer n.ch/contributionDisplay.py?contribId=29&confId=159120 LOCATION: URL:http://indico.cern.ch/contributionDisplay.py?contribId=29&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:AMD Accelerator technologies - CPU\, GPU and APU architectures to enable scientific computing in the future. Making accelerators accessable through the Heterogenous System Architecture and Open standards. DTSTART;VALUE=DATE-TIME:20120503T094500Z DTEND;VALUE=DATE-TIME:20120503T103000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-1@cern.ch DESCRIPTION:Speakers: NORDLUND\, Leif ()\nAMD is developing processor tech nology in three formats - CPU\, GPU\, and more recently\, APU. And across these areas\, AMD is leading a drive toward Heterogeneous Systems Architec ture (HSA)\, an open platform standard that takes advantage of CPU/GPU pro cessor cores as a unified processing engine\, which we are making into an open platform standard. This architecture enables many benefits for HPC\, including greatly enhanced application performance and significantly low p ower consumption.\n\nhttp://indico.cern.ch/contributionDisplay.py?contribI d=1&confId=159120 LOCATION:AMD\, Sweden URL:http://indico.cern.ch/contributionDisplay.py?contribId=1&confId=159120 END:VEVENT BEGIN:VEVENT SUMMARY:General purpose\, high-performance and energy-efficient x86 based computing with Many-Core Technologies (TFLOPS on a chip) DTSTART;VALUE=DATE-TIME:20120503T090000Z DTEND;VALUE=DATE-TIME:20120503T094500Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-27@cern.ch DESCRIPTION:Speakers: CORNELIUS\, Herbert ()\nAs we see Moore's Law alive and well\, more and more parallelism is introduced to all computing platfo rms on all levels of integration and programming to achieve higher perform ance and energy efficiency. We will discuss the new Intel(r) Many Integrat ed Core (MIC) architecture for highly-parallel workloads with general purp ose\, energy efficient TFLOPS performance on a single chip. We will also d iscuss the journey to ExaScale including technology trends for high-perfor mance and look at some of the R&D areas for HPC at Intel.\n\nhttp://indico .cern.ch/contributionDisplay.py?contribId=27&confId=159120 LOCATION:Intel\, Germany URL:http://indico.cern.ch/contributionDisplay.py?contribId=27&confId=15912 0 END:VEVENT BEGIN:VEVENT SUMMARY:GPUs in Fermi satellite data analysis DTSTART;VALUE=DATE-TIME:20120503T140000Z DTEND;VALUE=DATE-TIME:20120503T144000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-9@cern.ch DESCRIPTION:Speakers: Dr. BASTIERI\, Denis (Università di Padova)\nThe st andard analysis of the Fermi LAT collaboration could be sped up by two ord ers of magnitude porting the most time-consuming Science Tools toward a GP U architecture. Using an NVIDIA S2050\, with its Fermi architecture\, we w ere able to accelerate the computation of the satellite "livetime cube"\, reducing the execution time from 70 minutes (CPU) to 30 seconds (GPU). Oth er analysis tools could benefit from GPUs: in particular\, the likelihood analysis and the upper limit computation. In this talk\, we will present U riel\, the Ultrafast Robotic Interface for Extended Likelihood\, and many different applications where GPUs can have an impact in gamma-ray astrophy sics.\n\nhttp://indico.cern.ch/contributionDisplay.py?contribId=9&confId=1 59120 LOCATION:INFN/University of Padova\, Italy URL:http://indico.cern.ch/contributionDisplay.py?contribId=9&confId=159120 END:VEVENT BEGIN:VEVENT SUMMARY:GPUs in gravitational wave data analysis DTSTART;VALUE=DATE-TIME:20120503T144000Z DTEND;VALUE=DATE-TIME:20120503T152000Z DTSTAMP;VALUE=DATE-TIME:20130525T120208Z UID:indico-contribution-159120-8@cern.ch DESCRIPTION:Speakers: KEPPEL\, Drew ()\nSearches for gravitational-wave si gnals from inspiraling black hole or neutron star binaries push the limits of currently available computing resources with conventional CPU-based co mputer clusters. Previous efforts have used the advantages associated with GPU-hardware to accelerate computationally-intensive portions of the sear ches by porting those computations to run on the GPUs. Additionally\, futu re computational savings could be obtained through further code optimizati on and novel analysis techniques\, which will of course be impacted by the technologies available in the coming years. In this presentation\, I will summarize the LIGO Scientific Collaboration and the Virgo Collaborations' efforts to accelerate inspiral searches using GPUs and will discuss how t hese efforts will be focused in the coming years.\n\nhttp://indico.cern.ch /contributionDisplay.py?contribId=8&confId=159120 LOCATION:AEI Hannover\, Germany URL:http://indico.cern.ch/contributionDisplay.py?contribId=8&confId=159120 END:VEVENT END:VCALENDAR