Please mark you calendar for this exciting Guest Seminar:
JLab Physicist Markus Diefenthaler
Thursday, August 29 at 2:00 pm in TORGERSEN 1100
Title Exploring the heart of matter at Jefferson Lab
Thomas Jefferson National Accelerator Facility in Newport News, Virginia, is a U.S. Department of Energy Office of Science national laboratory. Jefferson Lab’s unique and exciting mission is to expand humankind’s knowledge of the universe by studying the fundamental building blocks of matter within the nucleus: subatomic particles known as quarks and gluons. In my seminar, I will present our science program to understand the structure of atomic nuclei directly from the dynamics of their quarks and gluons, governed by the theory of their interactions, quantum chromodynamics (QCD), and motivate how advances in theory, accelerator and detector technologies, and in particular in computer science will enable a new frontier in nuclear science.
Organized In Cooperation with Advanced Research Computing and TLOS.
The VT Center for Human Computer Interaction (CHCI) published this nice summary of our high impact work at the biggest graphics conference in the world! Dr. Polys represented ARC's innovations in visual computing:
3D Models are increasingly valuable for safety and for scenery. ARC and CGIT collaborated to host researchers considering scenic resources inventory, including protocols and results for the Appalachian Trail:
Dr. Polys has been honored with an invitation to speak at an upcoming ISO-IEC meeting in Seoul, South Korea, Jan 21-25. Dr. Polys will be presenting on X3D/HL7 medical graphics and informatics work. Specifically, ARC's innovations with the international interactive 3D standards X3D, H-ANIM, and HL7 FHIR and Mixed and Augmented Reality (MAR) are converging to improve health outcomes across domains and conditions. The presentations and schedule are available here ; the Web3D twitter feed is here.
VT Biochemistry had a strong showing, presenting their results on using immersive visualization in VT's Visionarium Hypercube to engage and teach students (paper & presentation here).
The Technical Paper was presented and awarded Best Student Paper!
Dr. Srijith Rajamohan (email@example.com) presented a workshop on ‘Introduction to Machine Learning with TensorFlow and Keras’. The purpose of this workshop was to provide a formal introduction to the mathematical concepts underlying Machine Learning. This was augmented by hands-on examples in the Machine Learning framework TensorFlow and the Deep Learning framework Keras. The slides for this workshop can be found at https://srijithr.gitlab.io/post/pearc18/ .
Alana Romanella (firstname.lastname@example.org) served on the executive committee as Diversity and Workforce Development Chair and Chair Emeritus for the Student Program. She focused on promoting inclusivity through increasing individual diversity awareness skills and effective organizational systems that allowed for a more diverse conference.
Interested in joining us next year?
PEARC19, will be located in Chicago from July 28 – August 1, 2019, and will explore the current practice and experience in advanced research computing including modeling, simulation, and data-intensive computing. A primary focus next year will be on Machine Learning and Artificial Intelligence which are proving to be disruptive technologies in a diverse range of scientific fields from materials science to medicine. https://www.pearc19.pearc.org/
ARC released a new cluster named Huckleberry in late 2017. The Huckleberry system, accessed at huckleberry1.arc.vt.edu, was installed with deep learning applications in mind. To this end, it consists of 14 IBM “Minsky” S822LC nodes and NVIDIA's proprietary NVLink interconnect network. This system enables highly parallel and highly distributed workloads. IBM unveiled its deep learning AI toolkit called PowerAI alongside the launch of Minsky nodes that leverage CPUs linked to Power CPUs with NVLink making it possible to have high speed high performance computing. PowerAI is available under /opt/DL in Huckleberry.
Each compute node on Huckleberry (i.e. IBM “Minsky” nodes) consists of :
Two IBM Power8 with 10 cores, 8 threads per core and memory bandwidth 115gb/s per socket
Four NVIDIA P100 GPUs advertised to have 21 teraFLOPS of 16-bit floating-point performance ideal for deep learning applications deliver high performance, massive parallelism
NVIDIA's NVLink technology which provides high bandwidth data transfers between CPUs and GPUs; an improvement over PCI-Express
Mellanox EDR Infiniband (100 GB/s) interconnect used to connect compute nodes
The PowerAI toolkit contains Caffe, TensorFlow etc. which are optimized for the Power servers. IBM provides support for it as well.
While the rest of the clusters make use of the PBS batch systems, Huckleberry makes use of the Slurm batch system using the command sbatch.