Stories
Slash Boxes
Comments

SoylentNews is people

SoylentNews is powered by your submissions, so send in your scoop. Only 16 submissions in the queue.

Submission Preview

Link to Story

DARPA stories

Accepted submission by takyon at 2017-06-07 11:51:21
Science

https://www.hpcwire.com/off-the-wire/darpa-announces-topological-excitations-electronics-program/ [hpcwire.com]

DARPA's Topological Excitations in Electronics program, announced today, aims to investigate new ways to arrange these moments in novel geometries that are much more stable than the conventional parallel arrangement. If successful, these new configurations could enable bits of data to be made radically smaller than possible today, potentially yielding a 100-fold increase in the amount of storage achievable on a chip. It could also enable designs for completely new computer logic concepts and even for topologically protected "quantum" bits—the basis for long-sought quantum computers.

[...] Another unique characteristic about topological excitations is that they can be moved at significant speed with a small amount of current, allowing for fast read and write operations if, for example, they are placed on a track that runs in front of a read/write head, Ale said. Such an approach would make it possible to explore novel, 3-D approaches to chip design, enabling storage capabilities of 100 Terabits per square inch, 100 times more than the current limit of 1 Terabit per square inch in laboratory demos.

http://www.tomshardware.com/news/darpa-intel-qualcomm-graph-analytics,34665.html [tomshardware.com]

The Defense Advanced Research Projects Agency (DARPA) announced that it has selected five participants for its Hierarchical Identify Verify Exploit (HIVE) program to develop a high-performance data handling platform. Intel and Qualcomm will be among the five participants that will help the agency build the new graph analytics platform.

[...] A main objective of the HIVE program is to create a graph analytics processor, which can more efficiently find and represent links between data elements and categories. These could include person-to-person interactions, and disparate links such as geography, change in doctor visit trends, or social media and regional strife.

[...] DARPA believes that such a graph processor could achieve a "thousandfold improvement in processing efficiency," over today's best processors. That should enable the real-time identification of strategically important relationships as they unfold in the field, rather than after-the-fact in data centers.


Original Submission