Blog

Archive for the ‘hpc-ch’ Category

Video – Discussion Between SDSC and Argonne About the Challenges of Visualizing Large Data Sets

Friday, December 23rd, 2011

In the two previous posts we presented the simulation of the spatial structure of the light emitted in early galaxies. We asked Rick Wagner of SDSC to discuss with Venkartram Vishwanath of Argonne the challenges of creating visualizations of very large numerical scale.

The simulation of Rick produces for example 256 GB of data for a small set of the field and up to many TB of data for the entire one. Traditionally they write the snapshots to disk and analyze them later. According to Rick this approach is not sustainable in the future since larger and larger sets of data will be produced.

Venkartram agrees that one challenge of next generation simulations is that I/O will not keep up with the growth rate of computing capability. In his group at Argonne they are now working on efficient infrastructure and software to reduce the amount of data being written to storage to perform analysis, as well as in-situ visualization while the simulation is progress. This will facilitate the transformation of the data into insight.

Venkartram is developing methods that will allow a non-intrusive integration of the simulation with the visualization. Not a single line of the code has to be modified. The data is buffered, staged and written out, maintaining the integrity of the data formats that are produced. This method can also be used to increase the speed data is written to disk.

Interview with Joe Insley of Argonne on Visualizing the Spatial Structure of the Light Emitted in Early Galaxies

Thursday, December 22nd, 2011

Joe Insley (Argonne National Lab) has been working together with Rick Wagner of SDSC (see previous interview) on the visualization of the spatial structure of the light emitted in early galaxies. The visualization compares variables from two different simulations.

To compare of the two different simulations visually, Joe used vl3, a hardware-accelerated volume rendering library and application developed at the University of Chicago and Argonne.

The visualization for smaller data sets can be rendered in real time on a half-dozen nodes with 20 frames per second. The visualization can also be streamed from Argonne to SDSC over a dedicated network using a software developed at Argonne, and is controlled through a web-based client

Interview with Brian Sparks, of HPC Advisory Board about their collaboration with CSCS

Friday, December 16th, 2011

At the  hpc-ch booth at SC11 you could have read on a signboard that CSCS is a proud member of the HPC Advisory Board. Brian Sparks, a representative of the of the HPC Advisory Board at SC11, visited us at the booth. We asked Brian to present the board and some of his activities.

Brian tells us that the HPC Advisory Board is an open community that was started in 2008. Now, just three years later there are 270 members worldwide, a variety of ISV, OEM, independent Hardware vendors, as well as all the different end users both in academia and in research. All members come together for a common goal: being able to take advantage of HPC technologies and make them very easy to use.

According to Brian, CSCS is an important partner for the HPC Advisory Board for a number of reasons. CSCS has been the first center of excellence outside the USA, followed by China. These centers are basically providing tools and outbound activities to be able to promote HPC to users of all kinds. In the last two years the HPC Advisory Board together with CSCS have organized together three days hands-on workshops in Lugano.

The third annual workshop will be organized again with CSCS and will take place on March 13-15, 2012 in Lugano. The same place has been already booked  for the fourth workshop in 2013. This is a great workshop not only for people in Switzerland but also in the surrounding countries to get in and have nice three days of heavy information in terms of MPI, parallel programming languages, GPU, storage technology, network topologies, and some hand-on clustering. At the end there will also be a little competition and some great prizes.

Brian also recognizes the importance of hpc-ch as media partner for the HPC Advisory Council. hpc-ch covers not only the workshop in Lugano but also the workshop in the ISC time frame.

We look forward to meeting Brian and the HPC Advisory Board in March 2012 in Lugano.

Interview with Vittoria Rezzonico, Computational Sciences and Engineering Coordinator at EPFL

Monday, December 12th, 2011

Vittoria Rezzonico is the new Computational Sciences and Engineering Coordinator at EPFL. In this function Vittoria has become the reference person at EPFL for HPC issues and she is coordinating the deployment of shared HPC systems at the university.

In his function Vittoria meets on a regular basis the researchers of EPFL to learn their needs in supercomputing. Starting with this information she advises them about where they can best get the needed resources. These can be internal pooled HPC systems at EPFL but also external resources like CADMOS, CSCS or Vital-IT.

In the past research groups at EPFL were each running own suppurate clusters. This made very difficult to effectively use the building infrastructure. In addition some clusters were getting old, thus heaving high running costs (electricity, cooling, space) in proportion to the provided FLOPs. Professors have to pay for the compute nodes. The costs like high-performance connectivity and storage, system management, electricity and, cooling are taken over by EPFL.

Previously Vittoria was working at the School of Basic Sciences as facility manager for the data center and as a cluster administrator. Vittoria decided to apply for this new position to broaden her horizons.

We wish Vittoria a great success in her new function and thanks for her big support of hpc-ch activities.

Interview with George Lake, University of Zurich about HPC, Astrophysics and Switzerland

Thursday, December 8th, 2011

George Lake is professor for astrophysics at the University of Zurich (UZH). At his visit to the hpc-ch booth at SC11 we interviewed him about his research activities. George told us that at UZH there are different research groups working on dark matter, large scale structure of the universe and galaxy and clusters of galaxies. Most of the matter in the universe is dark matter, a mysterious component we still do not understand but it drives the process of galaxies formation and evolution. The researchers at UZH recently discovered that dark matter is clustered in little lumps that are present even in the disk of our galaxy. Currently they are studying both novel observational approaches to detect these lumps and their theoretical consequences on the process of galaxy and galaxy cluster formation.

For many years George has been involved in supercomputing . He was first one of the leading scientists for a large NASA program, HPCC/ESS (High Performance Computing and Communications for Earth and Space Sciences), then he was chief scientist at the ARSC supercomputing center.  The NASA was the one where Tom Sterling initiated the Beowulf cluster project. Originally the Beowulf was a gigaflop workstation. The idea was to create a personal supercomputer setup on your desk. George was the first to say “workstations heck, I’m building a server”.

George also boosted the research and supercomputing environment in Switzerland. The general envornment in Switzerland has very balanced investments. We have a national supercomputing centre in Manno (Ticino)  and the university has an own cluster. There are good investments in research groups to develop next generation software to use next generation systems (HP2C initiative). It is a confluence of things that the US is tried to achieve for many years and the Swiss have accomplished.