ARC HPC Systems will undergo maintenance beginning at midnight on the morning of Tuesday, March 29, 2016. The purpose of this maintenance will be to migrate to a new shared Home directory on the file system that currently provides Home to NewRiver. This will provide two key benefits to users:
All files in your Home directory will be visible from all clusters. For example, you will see the same files in $HOME from both NewRiver and BlueRidge. This will make it easier to migrate work between clusters based on which hardware is best suited to the task or which resource is less busy.
The maximum Home directory size will be increased from 100 GB to 500 GB per user.
Dr. Nicholas Polys recently returned from the Federal In-service Training day where he showcased his work for AEC. The presentation took place in the Hirshhorn Auditorium and was focused on infrastructure based standards for X3D.
Researchers supported by the Institute for Creativity, Arts, and Technology are developing an interactive 3-D environment that will bring together data from multiple research locations, including water quality data, to produce more comprehensive models and analytics for community ecosystem monitoring, targeting ongoing research activities at Stroubles Creek and the Catawba Sustainability Center.
An Evaluation of the Effects of Hyper-Natural Components of Interaction Fidelity on Locomotion Performance in Virtual Reality
Mahdi Nabiyouni and Doug A. Bowman
A short description:
Hyper-natural interaction techniques are intentionally designed to enhance users’ abilities beyond what is possible in the real world. We compared such hyper-natural techniques to their natural counterparts on a wide range of locomotion tasks for a variety of measures. The results show that the effects of the hyper-natural transfer function was mostly positive, however, hyper-natural techniques designed to provide biomechanical assistance had lower performance and user acceptance than those based on natural walking movements.
Advanced Research Computing is pleased to announce the public release of its newest high-performance computing (HPC) system, NewRiver, to the academic and research community at Virginia Tech. The 134-node system has an aggregate peak computing capacity of 152 TFLOPs (trillions of floating point operations per second) and 33 terabytes (TB) of aggregate memory. In addition, NewRiver is one of the first computational clusters to use the latest generation of InfiniBand interconnect, EDR, which connects the compute and storages nodes at a peak speed of 100 Gigabits/second.
NewRiver is capable of tackling the full spectrum of computational workloads, from problems requiring hundreds of compute cores to data-intensive problems requiring large amount of memory and storage resources. NewRiver contains five compute engines designed for distinct workloads.
General – Distributed, scalable workloads. With two of Intel’s latest-generation Haswell processors, 24 cores, and 128 GB memory on each node, this 100-node compute engine is suitable for traditional HPC jobs and large codes using MPI.
Big Data – High performance data analytics. With 43.2 TB of direct-attached storage for each node, this system enables processing and analysis of massive datasets. The 16 nodes in this compute engine also have 512 gigabytes (GB) of memory, making them suitable for jobs requiring large memory.
GPU – Data visualization and code acceleration. Nvidia K80 GPUs in this system can be used for code acceleration. They will also provide remote rendering, allowing large datasets to be viewed in place without lengthy data transfers to desktop PCs. The 8 nodes in this compute engine also have 512 GB of memory, making them suitable for jobs requiring large memory.
Interactive – Rapid code development and interactive usage. Each of the eight nodes in this compute engine have 256 GB memory and a K1200 graphics card. A browser-based, client-server architecture allows for a responsive, desktop-like experience when interacting with graphics-intensive programs.
Very Large Memory – Graph analytics and very large datasets. With 3TB (3072 gigabytes) of memory, four 15-core processors and 6 direct attached hard drives, each of the two servers in this system will enable analysis of large highly-connected datasets, in-memory database applications, and speedier solution of other large problems.
ARC’s computational scientists and support staff are available to help faculty and students choose the right compute engine for their research. ARC offers assistance with code development and optimization for high performance computing systems and installation of software.
Access to ARC’s resources is available to all Virginia Tech faculty, staff, and students. Higher priority access can be purchased through the Investment Computing Program, which provides a way for departments and individual faculty members to gain access to a larger share of resources than it is otherwise possible for ARC to provide. ARC’s BlueRidge cluster was partially funded by the investment program.
This tutorial, given by Srijith Rajamohan, and Peter Radics, covers the Python programming language including all the information needed to participate in the XSEDE15 Modeling Day event on Tuesday, July 27th, 2015. Topics covered are variables, input/output, control structures, math libraries, and plotting libraries. This tutorial uses Anaconda Python Package, that you can download here .
BLACKSBURG, Va., May 15, 2015 – Vijay K. Agarwala has been named director of high performance computing for Advanced Research Computing, a unit of Information Technology at Virginia Tech. Agarwala will provide technical and strategic leadership for the group’s advanced computing infrastructure.
To read the full article featured on VT News, click here
Alzheimers disease is a disease that causes loss of brain functions that are involved in memory, communication, and thought. The amyloid β-peptide (Aβ has been identified as the core component of protein aggregates in the brain of Alzheimer's patients. The pathway by which Aβ leaves the cell membrane and self-associates is largely a mystery.
The lab of Dr. David Bevan, a faculty member of in the Biochemistry department at Virginia Tech, studies this peptide, with a focus on the association of Aβ with membranes. It is thought that small aggregates of Aβ cause toxicity by disrupting cell membranes. Preventing the formation of these aggregates is an approach that is being studied as way to treat Alzheimer's disease. Experimental work has identified the dietary compounds that may bind to Aβ and inhibit the damaging effects of this peptide.
Part of the challenge is understanding what happens on the molecular level, and it is difficult to apply experimental techniques to find out this mechanism. "It is thought that the onset and the progression of Alzheimer's are due to the aggregation of this particular peptide, and we are trying to understand the molecular mechanisms of the development of the disease," explains Dr. Bevan.
"But with computational methods, we can see at the atomistic level the kinds of interaction and so on. This may lead to changes in the structure of amyloid beta peptide as well as factors that increase the propensity to aggregate."
Computational simulations focus on understanding this effect with the goal of designing effective small molecule inhibitors of Aβ aggregation. The simulations are based on experiments using both in vitro and in vivo studies.
The research in Dr. Bevan' laboratory is focused on molecular modeling as an approach to studying protein structure and function. During the period from January 2011 until May 2012, his lab used 6,000,000 CPU hours on Advanced Research Computing System's (ARC's) now-retired System X supercomputer.
On March 20, 2013, ARC launched a new large-scale machine, BlueRidge, which is comprised of 318 Intel Sandy Bridge nodes. With a total of 5,088 cores and 20 TB of memory, BlueRidge is ARC's largest research computing system to date. Having access to Blue Ridge will help expand Dr. Bevan's research going forward.
He hopes that in some point, his lab will begin to try to simulate the process of protein folding, which takes anywhere from milliseconds to a second depending on the size of the protein and the nature of its folding habit.
"I think with Blue Ridge, we will be able to do that, again by working with fairly small proteins or peptides, especially those that have very distinct protein structure folds, we can simulate the process when they go from extended form into the folded form."
Recently, Dr. Bevan won the award for outstanding dissertation adviser in Science Technology, Engineering, and Mathematics. In addition, his graduate students, Justin Lemkul, a 2012 doctoral degree recipient in Biochemistry, and Nikki Lewis-Huff, a Ph.D. candidate in Bioinformatics and Computational Biology, have received several awards. Anne Brown, another graduate student from his lab, has been accepted into the College of Agriculture and Life Sciences Graduate Teaching Program.
He said that he tries to provide just enough mentoring to his students so they are able to develop their own ideas but do not get totally lost somewhere. "Giving them free reign, so they can conceive and develop their own ideas is important, because they are more enthusiastic about something they have thought about, and they want to see if they can actually perform it, in our case in simulations. When they have generated hypothesis, they want to develop that hypothesis further,"said Dr. Bevan
Other research projects in the Bevan lab are described on the Bevan Lab web site.