Categories
Argonne Leadership Computing Facility

IIT team competes, surges in annual cluster challenge

scc-sc15-iit.web
An IIT student team placed fourth in an annual 48-hour competition that challenges young computer scientists to tune and run a series of high-performance computing codes, non-stop, on a small cluster they build from their own design. The team of 5 computer science undergrads and one junior from Naperville Central High School competed with 8 other teams from around the world at the Student Cluster Competition at SC’15 in Austin, TX.
This year’s 5-node cluster design was built using Intel components. William Scullin and Ben Allen, both HPC systems administrators at ALCF, and Ioan Raicu, assistant professor of computer science at IIT and a guest researcher in Argonne’s MCS Division, worked closely with the team as coaches and mentors. Argonne and Intel provided technical and financial support. To read more about the competition, click here.

Categories
Argonne Leadership Computing Facility Education

Argonne coding campers, class of 2015

codingcampIn July, I participated in Argonne’s first summer coding camp, a computer science education opportunity attended by 42 local high school students and organized in partnership with the DuPage County chapter of the Afro-Academic, Cultural, Technological and Scientific Olympics (ACT-SO).

A small team of Argonne computer scientists designed and taught the four-day programming curriculum, which could serve as a future model for teacher training and classroom implementation. It’s the start of good things to come in this important outreach area.

Read the article here.

Categories
Argonne Leadership Computing Facility

Cooley: more memory, faster results

CooleyToday at ALCF, a powerful new cluster with terabytes of RAM and GPU memory stands ready to meet our user community’s data analysis needs. Cooley, the follow-on system to Tukey, will support more exploration capabilities, including in-situ analysis and unprecedented volume-rendered visualization. Cooley shares the same software environment, network, and file systems as ALCF’s supercomputer, Mira, enabling direct access to Mira-generated results.
An article about the new system and links to Cooley user documentation can be found here.

Categories
Argonne Leadership Computing Facility

Aurora is coming. Step one: Theta

After much anticipatioaurora2n, the Department of Energy recently announced that industry partners Intel and Cray would be delivering Argonne’s next supercomputer, Aurora. The new system will be a first-of-its-kind product from the market-leading chipmaker and the renowned computer manufacturer, and is expected to be at least 18 times more powerful than the Argonne Leadership Computing Facility’s current system, Mira.

Mira has lots of science to accomplish between now and the time Aurora arrives on the scene in 2018, but the planning phase officially kicked off this week with a call for proposals for Aurora’s pre-production system, Theta.

The Early Science program for Theta is accepting proposals through May 22. Selected projects will get early access to the machine and support from ALCF staff and postdocs. Look for Aurora’s Early Science Program call for proposals next spring.

Categories
Argonne Leadership Computing Facility Publications Research

CiSE publishes first issue dedicated to Leadership Computing

GEI cover_edited-1Advances in Leadership Computing, the first of a two-part CiSE Special Issue on Leadership Computing, is now available online. In two consecutive publications, this special issue will explore nine projects that are using leadership systems to expand the frontiers of their fields.
The September/October issue features five articles on topics that include simulating the Universe, enhancing the understanding of wall-bounded turbulence, devising an approach that computes the energy dispatch of electrical power grid systems under uncertainty, gleaning new insights into fusion plasma turbulence, and a recent advance in quantum-mechanical computational methods that can be used to search for optimal materials such as batteries and photo-electrochemical cells.

Categories
Argonne Leadership Computing Facility

Improved Cetus development system enables new HPC use cases

cetus3Mira’s testing and development system, a Blue Gene/Q called Cetus, has grown to 4 racks to allow users to debug their project code at an even larger scale before moving to Mira.
This upgrade will support new types of HPC workloads. Smaller jobs (128-2048 nodes) will now be allowed to run for up to 12 hours. Longer running jobs (128-1024 nodes) will be allowed to run for up to 7 days, which is suitable for analysis activities since Cetus and Mira share the same file system.

Categories
Argonne Leadership Computing Facility Research

Summer start to new simulation science projects

membrane_alcfEach year, the DOE’s Advanced Scientific Computing Research program, or ASCR, dedicates roughly 30% of the computing resources at its three supercomputing facilities to projects pursuing DOE mission research. The yearlong ASCR Leadership Computing Challenge (ALCC) awards, which begin July 1, aim to advance clean energy technologies, to better understand climate and environmental systems, and to respond to potential disasters.
ASCR recently awarded 19 new ALCC projects a total of 1.64 billion core-hours at the Argonne Leadership Computing Facility, expanding both the scope of scientific simulation research happening at ALCF and the community of researchers that will be capable of using a leadership-class system. Read more about the individual projects here.
Image: Christopher Knight, Argonne National Laboratory

Categories
Argonne Leadership Computing Facility

Ying Li, ALCF's first Margaret Butler Postdoctoral Fellow

YingLiUniversity of Southern California doctoral student Ying Li will join ALCF this fall as the 2014 Margaret Butler Postdoctoral Fellow. Li is the first recipient of the ALCF fellowship that was announced during the spring 2013 Celebration of Thirty Years of Parallel Computing at Argonne, to commemorate a pioneering woman and scientist who programmed the first digital computers at Argonne in the 1950s, helped design subsequent ones, and contributed to simulations of nuclear power reactors.
Li, who graduates this summer with a doctorate in materials science and a master’s degree in computer science, belongs to the new generation of computational scientists. As a member of prominent computational materials science research team led by USC professor Priya Vashishta, Li has already worked on massively parallel computers, including Argonne’s Mira, in several investigations involving reactive force-field molecular dynamics simulations of upwards of one million atoms. To learn more about Ying Li, see ALCF’s recent feature.

Categories
Argonne Leadership Computing Facility

How to write a successful INCITE proposal

2015_incite_webinars
On April 22 and May 15, the INCITE program will host short webinars for anyone who’s interested in applying for 2015 INCITE time on Titan, the 27-petaflops Cray XK7 at Oak Ridge Leadership Computing Facility, or on Mira, the 10-petaflops IBM Blue Gene/Q at Argonne Leadership Computing Facility.
The Innovative and Novel Computational Impact on Theory and Experiment (INCITE) program, now in its tenth year, provides huge core-hour allocations on these two DOE production systems, at no cost to the researcher, to pursue breakthroughs in science and engineering.
During the sessions, INCITE Program Manager Julia White and LCF center representatives will provide tips for submitting a successful INCITE proposal, help you gauge your project’s readiness, describe the review process, and answer your questions. Registration is open.
INCITE 2015 call for proposals opens April 16 and closes June 27, 2014.

Categories
Argonne Leadership Computing Facility Research

Mira provides new insight into subatomic particles

ESP-Pieper-620_newA team of scientists has, for the first time, calculated several fundamental properties of the carbon-12 nucleus using one of the world’s fastest supercomputers, setting the stage for more reliable neutrino detector calibrations and better supernovae explosion simulations.
The work, published last summer in Physical Review Letters, involved researchers from Argonne, Los Alamos, and Jefferson national laboratories, Middle Tennessee State University, and Old Dominion University. The team, led by Argonne Senior Physicist Steven Pieper, was one of 16 that were granted early access to Mira last year, and used their core-hour allocation to prepare the Green’s function Monte Carlo (GFMC) code for the new machine’s scale and architecture in order to run the carbon-12 simulations.
In the past 15 years, researchers have developed the GFMC algorithm as a powerful and accurate method for computing properties of light nuclei. Understanding the many-body interactions within the nucleus is critical to a real understanding of the physics of nucleonic matter. Electron scattering experiments in the quasi-elastic regime, where the dominant process is knocking a single nucleon out of the nucleus, are underway at Jefferson Lab for a range of nuclei. Using Mira, the team has included new, complex interactions within the nucleus and predicted the results of a Jefferson Lab experiment, bringing theoretical prediction closer to experimental data in the high-momentum transfer tail. Read more about the work here.