|
|
|
| News |
| Argonne Leadership Computing Facility |
| Leading-Edge Data Analytics, Visualization Planned |
| The IBM Blue Gene/P Intrepid at the Argonne Leadership Computing Facility (ALCF) will soon have the data analytics and visualization capability to complement its distinction as the fastest computer in the world for open science and the third fastest overall computer in the world. |
 |
| Figure 6. Images from a large, 3D, multi-scale, multi-physics simulation of buoyancy-driven turbulent nuclear combustion carried out on the Intrepid supercomputer at the ALCF. This work was carried out by the DOE NNSA ASC/Alliance Center for Astrophysical Thermonuclear Flashes and the NSF Physics Frontier Joint Institute for Nuclear Astrophysics at The University of Chicago. The computational resources needed to do the simulation were awarded to the Flash Center under the DOE Office of Science INCITE program. The images were produced by the Futures Lab at Argonne National Laboratory. |
|
| Argonne awarded GraphStream, Inc., Belmont, CA, a contract that will help to make data analytics and visualization at this scale possible through the world's largest installation of NVIDIA Quadro Plex S4 external graphics processing units (GPU). This new supercomputer installation, nicknamed Eureka , will allow researchers to explore and visualize the data they produce with Intrepid. The powerful installation will offer 104 dual quad core servers with 208 Quadro FX5600 GPUs in the S4s. |
| "During a massive computation on Intrepid, torrents of data can be unleashed onto the multi-petabyte parallel file system," ALCF acting director Pete Beckman said. "For example, in just a little over a minute, Intrepid can produce the equivalent of 1,000 DVDs of file data. Eureka will be used to peer ever deeper into scientists' data, from simulations of the electrical signals of the human heart to exploding supernova. Aided by Eureka, scientists will plow through the tidal wave of data produced by Intrepid faster than ever before, searching for new insights." |
Most applications that run on large-scale systems like Intrepid generate huge volumes of data that represent the results of the calculations. An essential tool for understanding those results after the run has completed is to be able to explore rapidly the output data and convert it to a visual representation (figure 6). To do so at the scale required by Intrepid applications requires a system with Eureka's power.
|
