Large Hadron Collider Experiments Step Up the Data Processing Game With GPUs

upstart writes:

Large Hadron Collider Experiments Step Up the Data Processing Game With GPUs:

Analyzing as many as one billion proton collisions per second or tens of thousands of very complex lead collisions is not an easy job for a traditional computer farm. With the latest upgrades of the LHC experiments due to come into action next year, their demand for data processing potential has significantly increased. As their new computational challenges might not be met using traditional central processing units (CPUs), the four large experiments are adopting graphics processing units (GPUs).

GPUs are highly efficient processors, specialized in image processing, and were originally designed to accelerate the rendering of three-dimensional computer graphics. Their use has been studied in the past couple of years by the LHC experiments, the Worldwide LHC Computing Grid (WLCG), and CERN openlab. Increasing the use of GPUs in high-energy physics will improve not only the quality and size of the computing infrastructure, but also the overall energy efficiency.

"The LHC's ambitious upgrade program poses a range of exciting computing challenges; GPUs can play an important role in supporting machine-learning approaches to tackling many of these," says Enrica Porcari, Head of the CERN IT department. "Since 2020, the CERN IT department has provided access to GPU platforms in the data center, which have proven popular for a range of applications. On top of this, CERN openlab is carrying out important investigations into the use of GPUs for machine learning through collaborative R&D projects with industry, and the Scientific Computing Collaborations group is working to help port - and optimize - key code from the experiments."

Read more of this story at SoylentNews.