Friday, April 16, 2021

U.S. Plans Supercomputer Push

Wall Street Journal: Oak Ridge National Laboratory, AMD and Nvidia are teaming up to create a new supercomputer that should be more powerful–and more energy efficient–than existing systems. Called “Titan,” the system, which should be completed next year, will harness the power of graphics processing units (GPUs) to acheive more than 20 petaflops, or a thousand trillion operations per second. “Because we’re increasingly power constrained, the only path forward for increasing performance is GPUs,” said Nvidia’s Steve Scott. “This is by far the biggest endorsement or validation of that path yet.”

The U.S. long topped the list of the world’s fastest computers, but lost the title to a Chinese system about a year ago. A Japanese supercomputer, the K, took the top slot in June. If the new U.S. system delivers the expected performance, it should be twice as fast as the K and three times as energy efficient.

Similar articles

Latest Articles

IT Planning During a...

Without a doubt, 2020 changed everything. I like to compare it to a science fiction movie where time travel is involved. Clearly, we have...

Best Data Quality Tools...

Data quality is a critical issue in today’s data centers. The complexity of the Cloud continues to grow, leading to an increasing need for...

NVIDIA’s New Grace ARM/GPU...

This week is NVIDIA’s GTC, or GPU Technology Conference, and they likely should have changed the name to ATC because this year – it...

What is Data Segmentation?

Definition of Data Segmentation Data segmentation is the process of grouping your data into at least two subsets, although more separations may be necessary on...