HPC : CUDA: WEEK IN REVIEW GPU-Accelerated Nanotechnology

Thursday, 12 June 2014

CUDA: WEEK IN REVIEW GPU-Accelerated Nanotechnology

Thur., June 12, 2014, Issue #112

Read Newsletter Online | See Previous Issues

WELCOME TO CUDA: WEEK IN REVIEW
News and resources for the worldwide GPU and parallel programming community.

CUDA PRO TIP

Learn about the performance implications of the Tail Effect and how to work around it on the Parallel Forall Blog.

CUDA SPOTLIGHT

GPU-Accelerated Nanotechnology
This week's Spotlight is on Dr. Mark Bathe, associate professor of biological engineering at the Massachusetts Institute of Technology. Mark's lab focuses on in silico design and programming of synthetic nucleic acid scaffolds.

Mark comments: "GPU computing plays a major enabling role in diverse aspects of our technology developments." Read the Spotlight.

CUDA NEWS

Stanford Launches the HIVE

Stanford University announced the HIVE, a state-of-the-art facility for scientific visualization in the Huang Engineering Center.

"Researchers are creating tremendous amounts of data through computations, simulations, measurements, sensor readings and so forth. We have to have a way to visualize such data in ways that allow us to see the big picture and also zoom in on the detail," said Dr. Margot Gerritsen, director of Stanford's Institute for Computational and Mathematical Engineering (ICME).

The HIVE consists of 35 high-definition displays, synched with NVIDIA technology, that can work together to offer a detailed view of one image, or display side-by-side visualizations of different images.

New Image & Signal Processing Research
Solutions provider SagivTech collaborated with the University of Bremen (Germany), EPFL (Switzerland) and others on the UNLoCX project. Funded by the European Commission, UNLoCX conducted numerical experiments with mass spectrometry imaging data on GPUs, reducing processing times from several hours to several minutes. The goal is to tackle complex applications in life sciences and ultra-precise audio signal processing which presently cannot be solved appropriately with existing algorithms. The results are described in a paper recently published in Advances in Computational Mathematics (June 2014).