Reception

Welcome Speech

PTF, DeepSky & The Era of Synoptic Surveys . Peter Nugent (Lawrence Berkeley National Laboratory)

Astrophysics is transforming from a data-starved to a data-swamped discipline, fundamentally changing the nature of scientific inquiry and discovery. New technologies are enabling the detection, transmission, and storage of data of hitherto unimaginable quantity and quality across the electromagnetic, gravity and particle spectra. The observational data obtained in the next decade alone will supesede everything accumulated over the preceding four thousand years of astronomy. Within the next year there will be no fewer than 4 large-scale photometric and spectroscopic surveys underway, each generating and/or utilizing tens of terabytes of data per year. some will focus on the static universe while others will greatly expand our knowledge of transient phenomena. Maximizing the science from these programs requires integrating the processing pipeline with high-performance computing resources coupled to large astrophysics databases with near real-time turnaround. Here I will present an overview of the first of these programs, DeepSky and the Palomar Transient Factory (PTF), the processing and discovery pipeline we have developed at LBNL and NERSC for them and several of the great discoveries made ruing the first 120 nights of observations with PTF. In particular I will highlight how these efforts have enabled a much more robust nearby supernova program, allowing us to carry out next generation cosmology programs with both Type Ia and II-P supernovae while at the same time discovering events which previously exploded only in the minds of theorists. I will aslo discuss the synergy between these programs and future spectroscopic surverys like BigBOSS - particularly their power to be a source for LRG and QSO target selection. Finally I will comment on how the lessons learned from PTF will be esential for the preparation of future large synoptic sky surveys like LSST and SASIR.

GPU-Clusters, Green Grid, Virtual Research Environments . Harry Enke (Astrophysikalisches Institut Potsdam)

Special purpose hardware like GPU-Clusters, FPGA and GRAPE boards as well as e.g robotic telescopes are precious resources. Integrating such resources into a Grid infrastructure provides efficient access and usage of these resources for collaborators from all over the world. The road of building suitable research environments for small groups of collaborators, embedded in a larger grid-structure will be explored.

Coffee Break

Service Infrastructures for Science: HPC, Grids, and Clouds. The DEISA Example . Wolfgang Gentzsch (DEISA-2)

Scientists' dream of accessing the best suited and least loaded HPC system in the world which best suits their application, independently from time and space, is currently coming true. High-speed networks transport data at the speed of light, middleware manages distributed computing resources in an intelligent manner, portal technology enable secure, seamless, and remote access to resources, applications, and data, and sophisticated numerical methods approximate the underlying mathematical equations in a highly accurate way. With the convergence of these core technologies into complex service oriented architecture, we see the rise of large compute and data grids and clouds, currently being built and deployed by grid e-Infrastructure initiatives suchs as DEISA, and cloud service providers suchs as Amazon.

In our talk, with the aid of the DEISA project, the Distributed European Infrastructure for Supercomputing Applications, we will elaborate on the different research e-Infrastructures, HPC systems, Grids, and Clouds. we will describe the evolution of DEISA from a set of independent HPC centers towards a European HPC ecosystem with Cloud-like HPC services. Finally, we present the DEISA Extreme Computing Initiative DECI attracting scientists all over Europe to use the DEISA resources, and we will highlight a few success stories from scientists who achieved breakthrough results so far which would not have been possible without such and infrastructure.

A brief history of gLite - Past, present and future , Maria Alandes Pradillo (CERN)

The world largest multi science grid infrastructure, EGEE, is based on the gLite middleware. The infrastructure links more than 250 computer centers providing 1500000 cores to 13000 researchers located in over 30 countries around the globe. The user communities are active in such diverse areas as Biomedical research, Astronomy and High Energy Physics. The gLite software integrates components developed and maintained by globally dispersed teams. This presentation describes the five years of gLite evolution and summarizes its origin and history. The development of its software lifecycle models, the evolution of its architecture and the deployment experience will illustrate the adaptive changes necessary to follow the progression of EGEE from and experimental infrastructure to the current mature service. In addition gLite's plans to contribute to future european grid infrastructures will be outlined.

Lunch

Gaia and Data Processing , William O'Mullane (ESA)

Gaia is ESA's ambitious space astrometry mission the main objective of which is to astrometrically and spectro-photometrically map 1000 Million celestial objects (mostly in our galaxy) with unprecedented accuracy. The Gaia Data Processing and Analysis Consortium (DPAC), formed in 2006, preparing the siftware to process this data. The satellite will downlink close to 100 TB of raw telemetry data over 5 years. To achieve its required accuracy of a few 10s of Microarcsecond astrometry, a highly involved processing of this data is required.

In addition to the main astrometric instrument Gaia will host a Radial Velocity instrument, two low-resolution dispersers for multi-color photometry and two Star Mappers. Gaia is flying Giga Pixel camera. The various instruments each require relatively complex processing while at the same time being interdependent. We describe the overall composition of the DPAC and the overall architecture of the Gaia data processing system. We shall delve further into the core processing - one of the nine, so-called, coordination units comprising the Gaia processing system.

 15:15 - 15:45

Coffee Break

Clouds and Science: Opportunities and Obstacles , Daniel S. Katz (University of Chicago)

Clouds offer a number of opportunities for science, but current applications will need to change to take advantage of these opportunities. This talk with use the author's experiences in graduate school, where parallel programming was starting to become mainstream in HPC, and at JPL, where grids were starting to become mainstream for some HPC science, to look at the issues in today's context where clouds are becoming popular, but are not currently used for a high fraction of large-scale science.

• Intel Compilers: most common flags and run-time environment variables: OpenMP support and examples
• Intel Threading Tools: overview

Coffee Break

Intel Tutorial

• Intel VTune performance analysis tool: overview
• Cluster Tools: Intel MPI: overview, benefits and switches