Tag Archives: energy
#435541 This Giant AI Chip Is the Size of an ...
People say size doesn’t matter, but when it comes to AI the makers of the largest computer chip ever beg to differ. There are plenty of question marks about the gargantuan processor, but its unconventional design could herald an innovative new era in silicon design.
Computer chips specialized to run deep learning algorithms are a booming area of research as hardware limitations begin to slow progress, and both established players and startups are vying to build the successor to the GPU, the specialized graphics chip that has become the workhorse of the AI industry.
On Monday Californian startup Cerebras came out of stealth mode to unveil an AI-focused processor that turns conventional wisdom on its head. For decades chip makers have been focused on making their products ever-smaller, but the Wafer Scale Engine (WSE) is the size of an iPad and features 1.2 trillion transistors, 400,000 cores, and 18 gigabytes of on-chip memory.
The Cerebras Wafer-Scale Engine (WSE) is the largest chip ever built. It measures 46,225 square millimeters and includes 1.2 trillion transistors. Optimized for artificial intelligence compute, the WSE is shown here for comparison alongside the largest graphics processing unit. Image Credit: Used with permission from Cerebras Systems.
There is a method to the madness, though. Currently, getting enough cores to run really large-scale deep learning applications means connecting banks of GPUs together. But shuffling data between these chips is a major drain on speed and energy efficiency because the wires connecting them are relatively slow.
Building all 400,000 cores into the same chip should get round that bottleneck, but there are reasons it’s not been done before, and Cerebras has had to come up with some clever hacks to get around those obstacles.
Regular computer chips are manufactured using a process called photolithography to etch transistors onto the surface of a wafer of silicon. The wafers are inches across, so multiple chips are built onto them at once and then split up afterwards. But at 8.5 inches across, the WSE uses the entire wafer for a single chip.
The problem is that while for standard chip-making processes any imperfections in manufacturing will at most lead to a few processors out of several hundred having to be ditched, for Cerebras it would mean scrapping the entire wafer. To get around this the company built in redundant circuits so that even if there are a few defects, the chip can route around them.
The other big issue with a giant chip is the enormous amount of heat the processors can kick off—so the company has had to design a proprietary water-cooling system. That, along with the fact that no one makes connections and packaging for giant chips, means the WSE won’t be sold as a stand-alone component, but as part of a pre-packaged server incorporating the cooling technology.
There are no details on costs or performance so far, but some customers have already been testing prototypes, and according to Cerebras results have been promising. CEO and co-founder Andrew Feldman told Fortune that early tests show they are reducing training time from months to minutes.
We’ll have to wait until the first systems ship to customers in September to see if those claims stand up. But Feldman told ZDNet that the design of their chip should help spur greater innovation in the way engineers design neural networks. Many cornerstones of this process—for instance, tackling data in batches rather than individual data points—are guided more by the hardware limitations of GPUs than by machine learning theory, but their chip will do away with many of those obstacles.
Whether that turns out to be the case or not, the WSE might be the first indication of an innovative new era in silicon design. When Google announced it’s AI-focused Tensor Processing Unit in 2016 it was a wake-up call for chipmakers that we need some out-of-the-box thinking to square the slowing of Moore’s Law with skyrocketing demand for computing power.
It’s not just tech giants’ AI server farms driving innovation. At the other end of the spectrum, the desire to embed intelligence in everyday objects and mobile devices is pushing demand for AI chips that can run on tiny amounts of power and squeeze into the smallest form factors.
These trends have spawned renewed interest in everything from brain-inspired neuromorphic chips to optical processors, but the WSE also shows that there might be mileage in simply taking a sideways look at some of the other design decisions chipmakers have made in the past rather than just pumping ever more transistors onto a chip.
This gigantic chip might be the first exhibit in a weird and wonderful new menagerie of exotic, AI-inspired silicon.
Image Credit: Used with permission from Cerebras Systems. Continue reading
Posted in Human Robots
#435520 These Are the Meta-Trends Shaping the ...
Life is pretty different now than it was 20 years ago, or even 10 years ago. It’s sort of exciting, and sort of scary. And hold onto your hat, because it’s going to keep changing—even faster than it already has been.
The good news is, maybe there won’t be too many big surprises, because the future will be shaped by trends that have already been set in motion. According to Singularity University co-founder and XPRIZE founder Peter Diamandis, a lot of these trends are unstoppable—but they’re also pretty predictable.
At SU’s Global Summit, taking place this week in San Francisco, Diamandis outlined some of the meta-trends he believes are key to how we’ll live our lives and do business in the (not too distant) future.
Increasing Global Abundance
Resources are becoming more abundant all over the world, and fewer people are seeing their lives limited by scarcity. “It’s hard for us to realize this as we see crisis news, but what people have access to is more abundant than ever before,” Diamandis said. Products and services are becoming cheaper and thus available to more people, and having more resources then enables people to create more, thus producing even more resources—and so on.
Need evidence? The proportion of the world’s population living in extreme poverty is currently lower than it’s ever been. The average human life expectancy is longer than it’s ever been. The costs of day-to-day needs like food, energy, transportation, and communications are on a downward trend.
Take energy. In most of the world, though its costs are decreasing, it’s still a fairly precious commodity; we turn off our lights and our air conditioners when we don’t need them (ideally, both to save money and to avoid wastefulness). But the cost of solar energy has plummeted, and the storage capacity of batteries is improving, and solar technology is steadily getting more efficient. Bids for new solar power plants in the past few years have broken each other’s records for lowest cost per kilowatt hour.
“We’re not far from a penny per kilowatt hour for energy from the sun,” Diamandis said. “And if you’ve got energy, you’ve got water.” Desalination, for one, will be much more widely feasible once the cost of the energy needed for it drops.
Knowledge is perhaps the most crucial resource that’s going from scarce to abundant. All the world’s knowledge is now at the fingertips of anyone who has a mobile phone and an internet connection—and the number of people connected is only going to grow. “Everyone is being connected at gigabit connection speeds, and this will be transformative,” Diamandis said. “We’re heading towards a world where anyone can know anything at any time.”
Increasing Capital Abundance
It’s not just goods, services, and knowledge that are becoming more plentiful. Money is, too—particularly money for business. “There’s more and more capital available to invest in companies,” Diamandis said. As a result, more people are getting the chance to bring their world-changing ideas to life.
Venture capital investments reached a new record of $130 billion in 2018, up from $84 billion in 2017—and that’s just in the US. Globally, VC funding grew 21 percent from 2017 to a total of $207 billion in 2018.
Through crowdfunding, any person in any part of the world can present their idea and ask for funding. That funding can come in the form of a loan, an equity investment, a reward, or an advanced purchase of the proposed product or service. “Crowdfunding means it doesn’t matter where you live, if you have a great idea you can get it funded by people from all over the world,” Diamandis said.
All this is making a difference; the number of unicorns—privately-held startups valued at over $1 billion—currently stands at an astounding 360.
One of the reasons why the world is getting better, Diamandis believes, is because entrepreneurs are trying more crazy ideas—not ideas that are reasonable or predictable or linear, but ideas that seem absurd at first, then eventually end up changing the world.
Everyone and Everything, Connected
As already noted, knowledge is becoming abundant thanks to the proliferation of mobile phones and wireless internet; everyone’s getting connected. In the next decade or sooner, connectivity will reach every person in the world. 5G is being tested and offered for the first time this year, and companies like Google, SpaceX, OneWeb, and Amazon are racing to develop global satellite internet constellations, whether by launching 12,000 satellites, as SpaceX’s Starlink is doing, or by floating giant balloons into the stratosphere like Google’s Project Loon.
“We’re about to reach a period of time in the next four to six years where we’re going from half the world’s people being connected to the whole world being connected,” Diamandis said. “What happens when 4.2 billion new minds come online? They’re all going to want to create, discover, consume, and invent.”
And it doesn’t stop at connecting people. Things are becoming more connected too. “By 2020 there will be over 20 billion connected devices and more than one trillion sensors,” Diamandis said. By 2030, those projections go up to 500 billion and 100 trillion. Think about it: there’s home devices like refrigerators, TVs, dishwashers, digital assistants, and even toasters. There’s city infrastructure, from stoplights to cameras to public transportation like buses or bike sharing. It’s all getting smart and connected.
Soon we’ll be adding autonomous cars to the mix, and an unimaginable glut of data to go with them. Every turn, every stop, every acceleration will be a data point. Some cars already collect over 25 gigabytes of data per hour, Diamandis said, and car data is projected to generate $750 billion of revenue by 2030.
“You’re going to start asking questions that were never askable before, because the data is now there to be mined,” he said.
Increasing Human Intelligence
Indeed, we’ll have data on everything we could possibly want data on. We’ll also soon have what Diamandis calls just-in-time education, where 5G combined with artificial intelligence and augmented reality will allow you to learn something in the moment you need it. “It’s not going and studying, it’s where your AR glasses show you how to do an emergency surgery, or fix something, or program something,” he said.
We’re also at the beginning of massive investments in research working towards connecting our brains to the cloud. “Right now, everything we think, feel, hear, or learn is confined in our synaptic connections,” Diamandis said. What will it look like when that’s no longer the case? Companies like Kernel, Neuralink, Open Water, Facebook, Google, and IBM are all investing billions of dollars into brain-machine interface research.
Increasing Human Longevity
One of the most important problems we’ll use our newfound intelligence to solve is that of our own health and mortality, making 100 years old the new 60—then eventually, 120 or 150.
“Our bodies were never evolved to live past age 30,” Diamandis said. “You’d go into puberty at age 13 and have a baby, and by the time you were 26 your baby was having a baby.”
Seeing how drastically our lifespans have changed over time makes you wonder what aging even is; is it natural, or is it a disease? Many companies are treating it as one, and using technologies like senolytics, CRISPR, and stem cell therapy to try to cure it. Scaffolds of human organs can now be 3D printed then populated with the recipient’s own stem cells so that their bodies won’t reject the transplant. Companies are testing small-molecule pharmaceuticals that can stop various forms of cancer.
“We don’t truly know what’s going on inside our bodies—but we can,” Diamandis said. “We’re going to be able to track our bodies and find disease at stage zero.”
Chins Up
The world is far from perfect—that’s not hard to see. What’s less obvious but just as true is that we’re living in an amazing time. More people are coming together, and they have more access to information, and that information moves faster, than ever before.
“I don’t think any of us understand how fast the world is changing,” Diamandis said. “Most people are fearful about the future. But we should be excited about the tools we now have to solve the world’s problems.”
Image Credit: spainter_vfx / Shutterstock.com Continue reading
Posted in Human Robots
#435474 Watch China’s New Hybrid AI Chip Power ...
When I lived in Beijing back in the 90s, a man walking his bike was nothing to look at. But today, I did a serious double-take at a video of a bike walking his man.
No kidding.
The bike itself looks overloaded but otherwise completely normal. Underneath its simplicity, however, is a hybrid computer chip that combines brain-inspired circuits with machine learning processes into a computing behemoth. Thanks to its smart chip, the bike self-balances as it gingerly rolls down a paved track before smoothly gaining speed into a jogging pace while navigating dexterously around obstacles. It can even respond to simple voice commands such as “speed up,” “left,” or “straight.”
Far from a circus trick, the bike is a real-world demo of the AI community’s latest attempt at fashioning specialized hardware to keep up with the challenges of machine learning algorithms. The Tianjic (天机*) chip isn’t just your standard neuromorphic chip. Rather, it has the architecture of a brain-like chip, but can also run deep learning algorithms—a match made in heaven that basically mashes together neuro-inspired hardware and software.
The study shows that China is readily nipping at the heels of Google, Facebook, NVIDIA, and other tech behemoths investing in developing new AI chip designs—hell, with billions in government investment it may have already had a head start. A sweeping AI plan from 2017 looks to catch up with the US on AI technology and application by 2020. By 2030, China’s aiming to be the global leader—and a champion for building general AI that matches humans in intellectual competence.
The country’s ambition is reflected in the team’s parting words.
“Our study is expected to stimulate AGI [artificial general intelligence] development by paving the way to more generalized hardware platforms,” said the authors, led by Dr. Luping Shi at Tsinghua University.
A Hardware Conundrum
Shi’s autonomous bike isn’t the first robotic two-wheeler. Back in 2015, the famed research nonprofit SRI International in Menlo Park, California teamed up with Yamaha to engineer MOTOBOT, a humanoid robot capable of driving a motorcycle. Powered by state-of-the-art robotic hardware and machine learning, MOTOBOT eventually raced MotoGPTM world champion Valentino Rossi in a nail-biting match-off.
However, the technological core of MOTOBOT and Shi’s bike vastly differ, and that difference reflects two pathways towards more powerful AI. One, exemplified by MOTOBOT, is software—developing brain-like algorithms with increasingly efficient architecture, efficacy, and speed. That sounds great, but deep neural nets demand so many computational resources that general-purpose chips can’t keep up.
As Shi told China Science Daily: “CPUs and other chips are driven by miniaturization technologies based on physics. Transistors might shrink to nanoscale-level in 10, 20 years. But what then?” As more transistors are squeezed onto these chips, efficient cooling becomes a limiting factor in computational speed. Tax them too much, and they melt.
For AI processes to continue, we need better hardware. An increasingly popular idea is to build neuromorphic chips, which resemble the brain from the ground up. IBM’s TrueNorth, for example, contains a massively parallel architecture nothing like the traditional Von Neumann structure of classic CPUs and GPUs. Similar to biological brains, TrueNorth’s memory is stored within “synapses” between physical “neurons” etched onto the chip, which dramatically cuts down on energy consumption.
But even these chips are limited. Because computation is tethered to hardware architecture, most chips resemble just one specific type of brain-inspired network called spiking neural networks (SNNs). Without doubt, neuromorphic chips are highly efficient setups with dynamics similar to biological networks. They also don’t play nicely with deep learning and other software-based AI.
Brain-AI Hybrid Core
Shi’s new Tianjic chip brought the two incompatibilities together onto a single piece of brainy hardware.
First was to bridge the deep learning and SNN divide. The two have very different computation philosophies and memory organizations, the team said. The biggest difference, however, is that artificial neural networks transform multidimensional data—image pixels, for example—into a single, continuous, multi-bit 0 and 1 stream. In contrast, neurons in SNNs activate using something called “binary spikes” that code for specific activation events in time.
Confused? Yeah, it’s hard to wrap my head around it too. That’s because SNNs act very similarly to our neural networks and nothing like computers. A particular neuron needs to generate an electrical signal (a “spike”) large enough to transfer down to the next one; little blips in signals don’t count. The way they transmit data also heavily depends on how they’re connected, or the network topology. The takeaway: SNNs work pretty differently than deep learning.
Shi’s team first recreated this firing quirk in the language of computers—0s and 1s—so that the coding mechanism would become compatible with deep learning algorithms. They then carefully aligned the step-by-step building blocks of the two models, which allowed them to tease out similarities into a common ground to further build on. “On the basis of this unified abstraction, we built a cross-paradigm neuron scheme,” they said.
In general, the design allowed both computational approaches to share the synapses, where neurons connect and store data, and the dendrites, the outgoing branches of the neurons. In contrast, the neuron body, where signals integrate, was left reconfigurable for each type of computation, as were the input branches. Each building block was combined into a single unified functional core (FCore), which acts like a deep learning/SNN converter depending on its specific setup. Translation: the chip can do both types of previously incompatible computation.
The Chip
Using nanoscale fabrication, the team arranged 156 FCores, containing roughly 40,000 neurons and 10 million synapses, onto a chip less than a fifth of an inch in length and width. Initial tests showcased the chip’s versatility, in that it can run both SNNs and deep learning algorithms such as the popular convolutional neural network (CNNs) often used in machine vision.
Compared to IBM TrueNorth, the density of Tianjic’s cores increased by 20 percent, speeding up performance ten times and increasing bandwidth at least 100-fold, the team said. When pitted against GPUs, the current hardware darling of machine learning, the chip increased processing throughput up to 100 times, while using just a sliver (1/10,000) of energy.
Although these stats are great, real-life performance is even better as a demo. Here’s where the authors gave their Tianjic brain a body. The team combined one chip with multiple specialized networks to process vision, balance, voice commands, and decision-making in real time. Object detection and target tracking, for example, relied on a deep neural net CNN, whereas voice commands and balance data were recognized using an SNN. The inputs were then integrated inside a neural state machine, which churned out decisions to downstream output modules—for example, controlling the handle bar to turn left.
Thanks to the chip’s brain-like architecture and bilingual ability, Tianjic “allowed all of the neural network models to operate in parallel and realized seamless communication across the models,” the team said. The result is an autonomous bike that rolls after its human, balances across speed bumps, avoids crashing into roadblocks, and answers to voice commands.
General AI?
“It’s a wonderful demonstration and quite impressive,” said the editorial team at Nature, which published the study on its cover last week.
However, they cautioned, when comparing Tianjic with state-of-the-art chips designed for a single problem toe-to-toe on that particular problem, Tianjic falls behind. But building these jack-of-all-trades hybrid chips is definitely worth the effort. Compared to today’s limited AI, what people really want is artificial general intelligence, which will require new architectures that aren’t designed to solve one particular problem.
Until people start to explore, innovate, and play around with different designs, it’s not clear how we can further progress in the pursuit of general AI. A self-driving bike might not be much to look at, but its hybrid brain is a pretty neat place to start.
*The name, in Chinese, means “heavenly machine,” “unknowable mystery of nature,” or “confidentiality.” Go figure.
Image Credit: Alexander Ryabintsev / Shutterstock.com Continue reading
Posted in Human Robots