K, one of the world's fastest supercomputers based in Japan, is capable of 8.162 petaflops of performance, thanks to its insane 82,944 processors. The supercomputer is capable of driving 1016 billion operations per second, but even then, it is still hard pressed to compete with the brain in your head reading this article.
It took K around 40 minutes to simulate just 1 single second of human brain activity, even with all of its performance prowess. The experiment on simulated human brain activity involved 1.73 billion virtual nerve cells that were connected to 10.4 trillion virtual synapses, with every virtual synapse containing 24 bytes of memory.
NEST was used on the software side of things, which is a simulator for spiking neural network models that focuses on dynamics, size and structures of neural systems, versus exact morphology of individual neurons.
Just months ago the US government was shut down, with hundreds of thousands of jobs in the air, millions of US citizens affected, but that's nothing when it comes to the blank cheques it signs to the National Security Agency for "research".
The US spy agency is reportedly working on a quantum computer that would break through any encryption thanks to its pure, insane amount of processing power. Edward Snowden is behind the leaks - come on, you're not surprised now, are you - revealing a program that is worth some $79.7 million, dubbed "Penetrating Hard Targets".
The Washington Post is reporting the news, stating that the majority of the research is being done at the University of Maryland's Laboratory for Physical Sciences.
I don't know why it hasn't built its own yet, but The Pentagon has just dangled a carrot in front of hackers' eyes: offering up The Cyber Grand Challenge. The challenge will run for three years, with contestants needing to meet the Defense Advanced Research Projects Agency's (DARPA) requests.
DARPA would like to see a fully automated system that is capable of protecting itself from hackers, with the ability to respond to attacks within a matter of hours or seconds, versus a couple of days. The system, that I'm going to call Skynet, should be capable of updating its own cote on-the-fly and have decent reasoning abilities that are better than human experts based on vulnerability scanner signatures, intrusion detection signatures and security patches.
There are three prizes on offer by the government, the first is the grand prize of $2 million, with second and third places seeing a nice $1 million and $750,000 respectively. With all of the power, technology and secrecy, it's truly mind boggling that DARPA can't just build Skynet on its own.
It looks like the NSA's latest data center based in Utah is having all sorts of issues, with The Wall Street Journal reporting that it has seen 10 meltdowns happen in the last 13 months alone thanks to electrical surges.
This means that the NSA is using so much power trying to keep track on every human being on Earth that it is killing its data centers. Hundreds of thousands of dollars, if not millions of dollars in hardware has been killed, not to count the amount of man hours that would be pumped into the data center to try and fix things.
The WSJ somehow got its hands on a project documents that detail the issues the NSA is facing at its Utah data center, with arc fault failures being the core issues. An official who spoke with the WSJ described it as "a flash of lightning inside a 2-foot box" that caused huge explosions, melting metal and outright destroying circuits inside the data center.
US tax payer NSA spends over $1 million a month in power alone, chewing over 65 megawatts of juice, which is enough to power a city containing 20,000 people, this is a big issue. Backup generators have so far failed tests, with the cooling systems untested and then mixing in that the government and its contractors are disagreeing about "the adequacy of the electrical cooling systems" it truly is a laugh.
Something that doesn't mean much in mainstream news today, is going to mean worlds more in the coming decades, and this is quantum computing. Google and NASA announced their Quantum Artificial Intelligence Lab back in May, but now we get to check it out, in the video below.
The video comes thanks to the two giants making a short film for the Imagine Film Science Festival, with Google and NASA explaining that the AI lab would eventually solve optimization problems that are quite simply beyond the scope of traditional computers. NASA could use the quantum computing to help them look deeper into the dark beyond that is space, while Google could use it to improve medicine - especially with its latest announcement.
It's an interesting video, where we get to take a look into one of D-Wave's second-generation quantum computers, where each system requires a giant enclosure to keep the hardware temps down to near absolute zero. I'm guessing that this system could most likely run Crysis (that joke is getting really old, but someone has to say it, right?).
A team of artificial and natural knowledge researchers from the University of Illinois at Chicago have IQ-tested one of the most advanced artificial intelligence systems in the world to see how smart it is.
The results? It is about as smart as the average four-year-old child. The UIC team will report their findings in detail at the US Artificial Intelligence Conference in Bellevue, Washington, tomorrow. The UIC team put an artificial intelligence system developed at MIT called 'ConceptNet4' through the verbal parts of the Weschsler Preschool and Primary Scale of Intelligence Test, which is a standard IQ assessment for young children.
They found that ConceptNet4 had the IQ of a four-year-old child, but unlike most children, the machine's scores were quite uneven throughout most of the test. Robert Sloan, Professor and head of Computer Science at UIC and lead author of the study said: "If a child had scores that varied this much, it might be a symptom that something was wrong."
LSI Corporation have something kinda big to talk about for the weekend, and that news is IBM are now offering versions of their High IOPS Modular Adapters based on LSI's Nytro WarpDrive technology. These models join a growing list of PCIe Flash cards that are designed to be used with IBM System x server series.
IBM's System x server series are used by large clients that require insane speed for Big Data analytics. LSI's Nytro WarpDrive products provide ultra-low-latency, high-performance storage for data-intensive applications, all while helping cloud and enterprise datacenters reduce their storage footprint, as well as those ever-increasing energy costs. The IBM High IOPS capacity options range from 300GB to 800GB of SLC and MLC Flash memory for IBM System x servers.
You've probably never heard of Total, but what they're digging around the world to find you most likely use - oil and gas. Total are one of the world's major oil and gas groups, and on March 25 they will announce they're working with SGI for their new supercomputer.
SGI will be helping Total out with their SGI ICE X HPC system as the platform for its Total's new supercomputer named "Pangea." The companies will work together on Pangea, hoping to allow for more efficient upstream oil and gas exploration, as well as the discovery of reserves under challenging geological conditions. The new supercomputer will help scientists develop more complete visualizations of seismic landscapes over time, which will provide them with a better idea of what is happening beneath the Earth's surface.
Pangea is quite capable, delivering performance of up to 2.3 PFLOPS - considering the world's fastest supercomputers are only 10x faster than that - it still makes Pangea mighty fast. Pangea's unique computing architecture is based over 110,000 calculation cores, 7PB of storage, and an innovative cooling system that is intertwined with the processors. Power requirements sit at 2.8mW.
NVIDIA begins shipping GRID VCA, costs just $24,900 - features 8 GPUs, 16 threads of CPU and 192GB of RAM
NVIDIA have begun shipping their GRID Visual Computing Appliance (VCA), where designers, animators and visual production users can purchase for just $24,900. On top of this, there is a $2,400 yearly software license fee.
What do you get for $25,000? 8 GPUs, 16 threads of CPU and 192GB of RAM capable of delivering service up to 8 users, with the 16 GPU model doubling this to 16 simultaneous users. If a studio had a decent amount of designers or artists, this could definitely be an option worth looking into.
Apple did have the datacenter-designed Xserve for quite a while, but when they went into retirement Apple fans were left with no alternative. But there is someone who has thought of a way around this.
Over at Steve's Blog, who is anonymous, he has thought up of a solution to Apple's Xserve who has disappeared from the market. "Steve" has worked with vendors to developed a custom 1U shelving, cooling from car radiators and four-in-one power cables that cram 160 Mac mini's as well as a managing Xserve into a single enclosure.
This is quite the feat considering 160 machines would all obviously run hot, and we all know heat rises. Each machine sports a quad-core Core i7 processor and an SSD and this cluster features double the cores at 640 cores, when compared to the competing Xserve cluster. There's power consumption savings and a 45-second, network-controlled reboot with the cluster.