Cerebras reveals world's 'largest computer chip' for AI tasks

guest · Aug 19, 2019

Cerebras reveals world's 'largest computer chip' for AI tasks
August 19, 2019
https://www.bbc.co.uk/news/technology-49395577

The Wafer Scale Engine, designed by Cerebras Systems, is slightly bigger than a standard iPad.
The firm says a single chip can drive complex artificial intelligence (AI) systems in everything from driverless cars to surveillance software.
Why is the development important?
GPUs (graphics processing units) tend to have more cores, albeit less powerful ones.

This has traditionally made them the preferred option for artificial intelligence processes that can be broken down into several parts and run simultaneously, where the outcome of any one calculation does not determine the input of another.
But Cerebras' new chip has 400,000 cores, all linked to each other by high-bandwidth connections.

The firm suggests this gives it an advantage at handling complex machine learning challenges with less lag and lower power requirements than combinations of the other options.
Click to expand...

guest · Aug 22, 2019

6 Things to Know About the Biggest Chip Ever Built
August 21, 2019
https://spectrum.ieee.org/tech-talk...ngs-to-know-about-the-biggest-chip-ever-built

On Monday at the IEEE Hot Chips symposium at Stanford University, startup Cerebras unveiled the largest chip ever built. It is roughly a silicon wafer-size system meant to reduce AI training time from months to minutes. It is the first commercial attempt at a wafer-scale processor since Trilogy Systems failed at the task in the 1980s.
2 | Why do you need this monster?
Cerebras makes a pretty good case in its white paper [PDF] for why such a ridiculously large chip makes sense.

A big chip offers more silicon area for processor cores and the memory that needs to snuggle up next to it. And a high-bandwidth, low-latency connection is only achievable if data never has to leave the short, dense interconnects on a chip. Thus one big chip. [...]
Click to expand...

guest · Nov 19, 2019

World's Largest Chip Gets a New Home: Inside the Cerebras CS-1 System
Cerebras' world's largest chip takes compute to a whole new level
November 18, 2019
https://www.tomshardware.com/news/worlds-largest-chip-gets-a-new-home-cerebras-launches-cs-1-system

Cerebras Systems' announced its new CS-1 system here at Supercomputing 2019. The company unveiled its Wafer Scale Engine (WSE) at Hot Chips earlier this year, and the chip is almost as impressive as it is unbelievable: The world's largest chip, weighing in at an unbelievable 4000,000 cores, 1.2 trillion transistors, 46,225 square millimeters of silicon, and 18 GB of on-chip memory, all in one chip that is as large as an entire wafer.
Add in that the chip sucks 15kW of power and features 9 PB/s of memory bandwidth, and you've got a recipe for what is unquestionably the world's fastest AI processor.

Cerebras has pulled off that feat, and today the company unveiled the system and that the Argonne National Laboratory has already adopted it. The company also provided us detailed schematics of the internals of the system.
A pod of Google's TPU v3 chips consumes 100kW of power, but only provides 1/3 the performance of a single SC-1 system. That means the SC-1 draws 1/5th the power and is 1/30th the size, yet is three times faster than an entire TPU pod.
Click to expand...

Argonne National Laboratory Deploys Cerebras CS-1, the World’s Fastest Artificial Intelligence Computer

guest · Aug 19, 2020

Cerebras teases second-generation wafer-scale AI chip
...which takes up an entire silicon wafer and has 850,000 individual compute cores
August 18, 2020
https://www.zdnet.com/article/cerebras-teases-second-generation-wafer-scale-ai-chip/

Cerebras Systems, the Los Altos, California startup that a year ago unveiled the biggest chip ever seen, this afternoon gave a preview of its second-generation chip.

The second-gen WSE, or "wafer-scale engine," chip, currently "running in our labs," will offer 850,000 individual compute cores in a chip that takes up almost the entire surface of a traditional silicon wafer, according to Cerebras executive Sean Lie. Lie was addressing the audience of Hot Chips, a computer chip conference taking place virtually this year.
Click to expand...

The processor has 2.6 trillion transistors in total, and it is manufactured by Taiwan Semiconductor in the company's 7-nanometer fabrication process. That is more than double the 400,000 cores and 1.2 trillion transistors in the original, Gen-1 WSE.
Lie told the audience to wait for details "in coming months."
Click to expand...

guest · Nov 17, 2020

Cerebras’ wafer-size chip is 10,000 times faster than a GPU
November 17, 2020
https://venturebeat.com/2020/11/17/cerebras-wafer-size-chip-is-10000-times-faster-than-a-gpu/

Cerebras Systems and the federal Department of Energy’s National Energy Technology Laboratory announced that the company’s CS-1 system is more than 10,000 times faster than a graphics processing unit (GPU).
On a practical level, that means that AI neural networks that in the past took months to train, can now train in minutes on the Cerebras system.

Cerebras makes the world’s largest computer chip, the WSE.
Each piece of the chip, dubbed a core, is interconnected in a sophisticated way to other cores. The interconnections are designed to keep it all functioning at high speeds so the transistors all work together as one.
Click to expand...

Feldman said in an interview with VentureBeat that the CS-1 was also 200 times faster than the Joule Supercomputer, which is No. 82 on the list of the top 500 supercomputers in the world.
“It shows record-shattering performance,” Feldman said. “It also shows that wafer scale technology has applications beyond AI.”
Click to expand...

guest · Aug 20, 2021

The World’s Largest Computer Chip
In the race to accelerate A.I., the Silicon Valley company Cerebras has landed on an unusual strategy: go big.
August 20, 2021
https://www.newyorker.com/tech/annals-of-technology/the-worlds-largest-computer-chip

Other companies are also making so-called A.I. accelerators; Cerebras’s competitors—Groq, Graphcore, and SambaNova—have raised more than two billion dollars in capital combined. But Cerebras’s approach is unique.
Instead of making chips in the usual way—by printing dozens of them onto a large wafer of silicon, cutting them out of the wafer, and then wiring them to one another—the company has made one giant “wafer-scale” chip.

In the end, Feldman said, the mega-chip design offers several advantages. Cores communicate faster when they’re on the same chip: instead of being spread around a room, the computer’s brain is now in a single skull. Big chips handle memory better, too.
Click to expand...

guest · Aug 24, 2021

Cerebras prepares for the era of 120 trillion-parameter neural networks
August 24, 2021
https://www.zdnet.com/article/cereb...ra-of-120-trillion-parameter-neural-networks/

Artificial intelligence in its deep learning form is producing neural networks that will have trillions and trillions of neural weights, or parameters, and the increasing scale presents special problems for the hardware and software used to develop such neural networks.

"In two years, models got a thousand times bigger and they required a thousand times more compute," says Andrew Feldman, co-founder and CEO of AI system maker Cerebras Systems, summing up the recent history of neural nets in an interview with ZDNet via Zoom.
Cerebras issued a press release announcing the new computers.

Cerebras, which competes with the AI leader, Nvidia, and with other AI startups, such as Graphcore and SambaNova Systems, aims to lead in performance when training those increasingly large networks.
Click to expand...

In the past year, what had been the world's largest neural net as measured by neural weights, OpenAI's GPT-3 natural language processing program, with 175 billion weights, was eclipsed by Google's 1.6-trillion-parameter model, the Switch Transformer.
Such huge models run into issues because they stretch beyond the bounds of a single computer system.

And how to cluster becomes the crucial issue, because each machine must be kept busy or else the utilization drops.
Hence, the problem Feldman and Cerebras set about to solve is to handle larger and larger networks in a way that will get better utilization of every computing element, and thereby lead to better performance, and by extension, better energy usage.
Click to expand...

The new computers include three parts that interoperate. One is an update of the company's computer that contains its Wafer-Scale Engine or WSE, chip, the largest chip ever made. That system is called the CS-2. Both WSE2 and CS-2 were introduced in April.

The new elements this week are a rack-mounted box called MemoryX, which contains 2.4 petabytes combined of DRAM and NAND flash memory, to store all the weights of the neural net. A third box is a so-called fabric machine that connects the CS-2 to the MemoryX, called SwarmX. The fabric can connect as many as 192 CS-2 machines to the MemoryX to build a cluster that works cooperatively on a single large neural net.
Click to expand...

Cerebras: Cerebras Systems Announces World’s First Brain-Scale Artificial Intelligence Solution

Technology Breakthroughs Enable Training of 120 Trillion Parameters on Single CS-2, Clusters of up to 163 Million Cores with Near Linear Scaling, Push Button Cluster Configuration, Unprecedented Sparsity Acceleration
Click to expand...

Log in or Sign up

Cerebras reveals world's 'largest computer chip' for AI tasks

guest Guest

guest Guest

guest Guest

guest Guest

guest Guest

guest Guest

guest Guest

Log in or Sign up

Cerebras reveals world's 'largest computer chip' for AI tasks

guest Guest

guest Guest

guest Guest

guest Guest

guest Guest

guest Guest

guest Guest

Useful Searches