Since 1987, OSC has been providing our clients services in four areas, or functions:
Supercomputing. OSC provides the computational power and storage that scientists need to meet their research goals. Whether researchers need to harness the incredible power of a parallel processor cluster to better understand deep space, a vector processor machine to do weather modeling, or a mid-size shared memory processor system to model the human heart, OSC has the hardware and software solutions to meet their needs.
Research. A staff of high performance computing and networking research experts maintain active research programs in HPC and Networking, Homeland Security and Defense, Environmental Sciences, Engineering and Life Sciences. Our goals are to lead science and engineering research efforts, assist researchers with custom needs and collaborate with regional, national and international researchers in groundbreaking initiatives.
Education. OSC has a national reputation for its training and education programs. Staff teach faculty and student researchers through scientific computing workshops, one-on-one classes, and web-based portal training. Ohio students gain exposure to the world of high performance computing and networking during our annual summer institutes for young women in middle school and for junior and senior high school students. And, the statewide, virtual Ralph Regula School of Computational Science coordinates computational science and engineering education activities for all levels of learning.
Cyberinfrastructure. The Ohio Supercomputer Center’s cyberinfrastructure and software development researchers provide the user community with various high performance computing software options. This variety enables researchers to select parallel computing languages they most prefer, and just as important, it creates a test bed for exploring these systems. By taking a holistic approach to generating efficient supercomputing applications for researchers, the Center’s cyberinfrastructure and software development research capitalizes on all the components within the cycle of innovation — development, experimentation, and analysis - and continuously improves the services provided.
Researchers at Ohio University recently discovered that disrupting COVID-19’s RNA and its ability to reproduce may be an additional way to stop the virus in conjunction with the vaccine. Jennifer Hines, Ph.D., a professor in the Department of Chemistry and Biochemistry, and students in her lab utilized the Ohio Supercomputer Center (OSC) to analyze the three-dimensional structure of RNA.
The Ohio Supercomputer Center (OSC) hosted the Statewide Users Group (SUG) conference virtually on Thursday, adapting the biannual conference to an online environment after the spring edition of the event was cancelled due to the coronavirus. The Zoom gathering consisted of committee meetings, a keynote address, updates from OSC and breakout meetings.
The Ohio Supercomputer Center’s (OSC) most efficient supercomputer system, the Pitzer Cluster, just received a major upgrade—in the middle of a global pandemic.
Over the summer, the two-year-old, liquid-cooled cluster gained nearly 400 nodes and 20,000 cores, increasing the system to more than 650 nodes and almost 30,000 cores in total. The nine new racks were delivered by a team from Dell EMC who carefully adhered to COVID-19 safety protocols. The OSC staff completed the onsite assembly and testing before making the expanded computing power available to OSC clients.
An approximately 3-hour downtime for the Pitzer system is scheduled starting from 9 a.m. Tuesday, September 22, 2020, to finalize the Slurm transition on the Pitzer system. This will affect the Pitzer legacy nodes (compute and login nodes), as well as the new Pitzer hardware. During this downtime time, users will not be able to access Pitzer and submit jobs. Other OSC services, including Owens and Ruby Clusters, web portals, and HPC file servers will be available, while users will expect a small interruption to OnDemand at the beginning of downtime
The purposes of the SUG Conference are to:
We will host a keynote address within an area of interest to OSC clients.
As citizens around the world first caught wind about the COVID-19 virus, almost no one predicted that it would become an international pandemic with such far-reaching effects. Wasiur KhudaBukhsh, a president’s postdoctoral scholar at the Mathematical Biosciences Institute at The Ohio State University, was no exception.
XSEDE along with the Pittsburgh Supercomputing Center is pleased to present a two day Big Data and Machine Learning workshop.
This workshop will focus on topics such as Hadoop and Spark and will be presented using the Wide Area Classroom (WAC) training platform.
Due to COVID-19, this workshop will be remote, using zoom.
Registration
Register by going to: https://portal.xsede.org/course-calendar
This workshop will focus on how to run parallel R jobs using resources at the Ohio Supercomputer Center. This workshop will cover topics such as:
- How to access R and RStudio at OSC
- Running R using Rstudio OnDemand App vs Terminal App
- How to install R packages locally as well as details on packages available for multi-core and multi-node parallelism
- Hands-on examples for running parallel R
This is a virtual hands-on workshop and attendance will be limited.
Registration is now closed.
This workshop will focus on how to run parallel R jobs using resources at the Ohio Supercomputer Center. This workshop will cover topics such as:
- How to access R and RStudio at OSC
- Running R using Rstudio OnDemand App vs Terminal App
- How to install R packages locally as well as details on packages available for multi-core and multi-node parallelism
- Hands-on examples for running parallel R
This is a virtual hands-on workshop and attendance will be limited.
Registration is closed. Please register for a future event.
XSEDE, along with the Pittsburgh Supercomputing Center is pleased to present an OpenACC GPU programming workshop on Tuesday, March 3, 11am - 5pm.
OpenACC is the accepted standard using compiler directives to allow quick development of GPU capable codes using standard languages and compilers. It has been used with great success to accelerate real applications within very short development periods. This workshop assumes knowledge of either C or Fortran programming. It will have a hands-on component using the Bridges computing platform at the Pittsburgh Supercomputing Center.
