Articles tagged with: GPU
OLCF staff members led a workshop January 10–12 to provide CAAR teams with a quickstart guide for using the Summitdev early access system, which features IBM’s POWER processors and NVIDIA’s Pascal GPU–based architecture.
Teams from St. Jude, Duke, Georgia Tech were some of the new entities at the latest OLCF Hackathon, held last month.
A team at the Oak Ridge Leadership Computing Facility recently addressed a performance bottleneck in one portion of an OLCF user’s application. Because of its efforts, the user’s team saw a sixfold performance improvement in the code.
OLCF representatives lead revised sessions and recruit for student practicums
For the sixth year in a row, staff from the Oak …
With the formation of the ADAC institute earlier this year, ORNL is partnering with supercomputing centers in Japan and Switzerland to work toward common goals, share expertise, and identify promising pathways for future high-performance computing systems.
This summer the Oak Ridge Leadership Computing Facility brought in 29 students whose backgrounds range from computer architecture, to mathematics and statistics, to artificial intelligence.
The University of Delaware hosted this year’s second OLCF-involved hackathon, where programmers from national laboratories, universities, and vendors gather to share application GPU portability expertise and learn how to program for a hybrid CPU–GPU machine like the OLCF’s Titan supercomputer.
Building on the success of the previous five sessions, the Dresden GPU hackathon—co-sponsored by the OLCF—welcomed 34 attendees on six teams.
A team led by OLCF’s Christos Kartsaklis has built a tool to help users to extract enough parallelism from their existing programs to take advantage of additional computational power.
Representatives from the OLCF held prominent roles at CSGF Program Review July 27–30 in Arlington, Virginia.