Synaptic Supercomputer Announcement

Today, IBM and Lawrence Livermore National Lab revealed the Synaptic Supercomputer made up of 16 TrueNorth Chips (16 Million Neurons, 4 Billion Synapses) that our group (myself included) has been working on over the last several months (and in some sense, years).

Here are a number of links to the announcements and news:
Wall-Street Journal [Subscription Required]
modha.org [Scaleup Synaptic Supercomputer Blog]
LLNL Perspective [Brian Van Essen]

Simultaneously, several of my colleagues have published a preprint of their work mapping Convolution Neural Networks onto TrueNorth:
Convolution Networks for Fast, Energy-Efficient Neuromorphic Computing

 

TrueNorth Named one of Year’s top 100 Inventions

TrueNorth was just named as one of R&D Magazine’s top 100 innovations in 2015.  In addition, it was also given one of only five Editors’ Choice awards. The R&D Award is described:

“Widely  ​recognized ​as ​the ​“Oscars ​of ​Invention”, ​the ​R&D ​ 100 ​Awards ​identify ​and ​celebrate ​the ​top ​technology ​products ​ of ​the ​year. ​Past ​winners ​have ​included ​sophisticated ​testing ​ equipment, ​innovative ​new ​materials, ​chemistry ​breakthroughs, ​ biomedical ​products, ​consumer ​items, ​and ​high-energy ​physics. ​ The ​R&D ​100 ​Awards ​spans ​industry, ​academia, ​and ​ government-sponsored ​research.”

 

http://rd100awards.com/2015-rd-100-award-winners

Boot Camp Prep – Behind the Scene: Hardware Edition

Today, we end our first week of a 3-week TrueNorth bootcamp, where we began to unveil and teach the ecosystem for TrueNorth. We take a look behind the scenes and present some of the effort the team has put forth when preparing the hardware for participants to learn on, play with, and eventually call their own.

The goal was simple: Assemble, test, and configure the first batch of 100 single-chip, index card-sized TrueNorth development boards (dubbed NS1e for Neurosynaptic System Evaluation Platform), 48 of which will be used as the playground for the Boot Camp participants. First to learn on, but eventually to take home and continue to develop their own algorithms and apply to their own applications. While seemingly straightforward, several items had to come together to allow us to provide users with an experience that has become expected of a development platform. While there was much to do, boards from the factory were received almost exactly one month to the day (actually less), leaving very little room for errors. Here is a timeline that summarizes our experiences as we worked to deliver the hardware in time for bootcamp:

07/01/15-07/06/15: NS1e boards are in-route from the factory, but there is little time to waste. We begin to create manufacturing and test scripts responsible for exercising board components as well as tracking boards as they execute the test procedures.

07/08/15: Boards are here! Less than one month away from bootcamp, we received NS1e boards in Almaden for assembly, test, and staging.

07/09/15: It was all hands on deck as we began to assemble and test the boards, attaching feet and heat sinks, everyone got involved in the fun! After boards were assembled, they were run through a round of testing which exercised TrueNorth and other discrete components to ensure functionality.

Jackson_final
Bryan Jackson assembling and testing NS1e True North development boards.

7/9/15: Due to the hardwork of the team and lab members, all boards were tested and configured by the end of the day!

Boards_P2
Assembled NS1e Boards.

07/10/15-07/24/15: With two weeks before we begin infrastructure testing the team still needed to decide how the NS1e boards would be finally configured. One important choice was which operating system would be loaded on the embedded Zynq platform: whether to use the strongly tested Petalinux or to push to provide Ubuntu. The team collectively decided to ensure the boards could run Ubuntu, which enables the NS1e platforms to pick up applications from the Linux community at large and expands the platforms versatility. To enable this, the team worked to resolve a few compatibility issues, but finally managed to get a working and tested image in time for infrastructure testing.

07/24/15-7/30/15: Infrastructure testing week! Due to the number of participants we split our 48 boards across 4 gateway servers. Testing now consists of ensuring each board is accessible by the servers and each has the latest version of the image containing FPGA firmware, OS, and the TrueNorth control software. S ome load testing is also performed to see what happens when many users are requesting to use boards simultaneously. Things mostly worked, and we fixed what didn’t.

Staging_final
Staging area for the 48 NS1e Development Boards the Participants will use while at Boot Camp.

07/31/2015: It is the weekend before bootcamp, so the team builds the final home of the NS1e development boards before they are finally transported to the classroom. Each of the NS1e platforms are placed into individual cases and inserted into a 6×8 array. The final rack contains the same number of neurons as a small mouse (48 Million Neurons and 12 Billion Synapses)! Now off to bootcamp!

This blog previously appeared on modha.org

I’ve Joined the Cognitive Computing group at IBM Research

As of March, I will be joining the Cognitive Computing Group at IBM Research, Almaden

This is certainly an exciting opportunity, especially considering where the computing industry is today with slowing technology scaling, increasing power densities, and higher importance being placed on analyzing disparate data-sets made up of ever-increasing size.

This seems to be the right time for a paradigm shift in computing to take place. While tradition computing has served us very well, and will continue to do so in the future for a variety of domains, sensor technologies and data collection methods have been improving at an exponential rate, while simultaneously becoming more pervasive in our every day lives. Although techniques which are able to analyze all of this new data exist, for many applications, none have been able to rival the power of the brain in terms of efficiency or computation capability. Today, we may have only scratched the surface of realizing what this data may be able to tell us using traditional models. Having a “programmable brain” at our fingertips may lead to many unforeseen discoveries and insights of the world around us. I am excited to be a part of it.

More information on the group and project can be found here:

IBM Research: Neurosynaptic Chip
Brain-inspired Computing: A Decade Long Journey (Dharmendra Modha, video)
IBM Colloquium: The Future of Cognitive Computing
Introducing a Brain-inspired Computer
Dharmendra Modha’s Cognitive Computing Blog

 

Newly Discovered Linux Trojan

Researchers at Kaspersky Labs and Symantec have recently disclosed the discovery of an extremely complex malware that is difficult to detect for Linux systems targeted at 45 government and pharmaceutical companies around the world:

Now researchers from Moscow-based Kaspersky Lab have detected Linux-based malware used in the same campaign. Turla was already ranked as one of the top-tier APTs, in the same league as the recently disclosed Regin for instance. The discovery of the Linux component suggests it is bigger than previously thought and may presage the discovery of still more infected systems.

“The [Turla] operations are being carried out in broader environments than we previously knew,” Kaspersky Lab expert Kurt Baumgartner told Ars. “All the other stuff we’ve seen from Turla has been windows based. This piece of the puzzle shows us that they do not limit themselves.”

Full article: Powerful, highly stealthy Linux trojan may have infected victims for years from Ars Technica

While it has just been disclosed, Turla was at least known about since August. One can again wonder how long this specific vulnerability may have been known about, however it’s encouraging that the malware was disclosed early, before the complete picture was established  (Related: Corporate Abuse of Our Data via Bruce Schnier).