Dejkala
No Result
View All Result
  • Home
  • Tech
  • Banking & loan
  • Games
  • Car’s & Bike’s
  • Home
  • Tech
  • Banking & loan
  • Games
  • Car’s & Bike’s
No Result
View All Result
Dejkala
No Result
View All Result
Home Latest update

AI is running out of computing power. IBM says the answer is this new chip- Dejkala

by hasibul
November 1, 2022
in Latest update
0
AI is running out of computing power. IBM says the answer is this new chip- Dejkala
0
VIEWS
Share on FacebookShare on Twitter


close up of the IBM Artificial Intelligence Unit chip

A close up of the IBM Artificial Intelligence Unit chip.

Image: IBM

The hype suggests that artificial intelligence (AI) is already everywhere, but in reality the technology that drives it is still developing. Many AI applications are powered with chips that weren’t designed for AI – instead, they rely on general-purpose CPUs and GPUs created for video games. That mismatch has led to a flurry of investment – from tech giants such as IBM, Intel and Google, as well as from startups and VCs – into the design of new chips expressly designed for AI workloads. 

As the technology improves, enterprise investment will surely follow. According to Gartner, AI chip revenue totaled more than $34 billion in 2021 and is expected to grow to $86 billion by 2026. Additionally, the research firm said, less than 3% of data center servers in 2020 included workload accelerators, while more than 15% are expected to by 2026. 

IBM Research, for its part, just unveiled the Artificial Intelligence Unit (AIU), a prototype chip specialized for AI. 

“We’re running out of computing power. AI models are growing exponentially, but the hardware to train these behemoths and run them on servers in the cloud or on edge devices like smartphones and sensors hasn’t advanced as quickly,” said IBM.

Also: Can AI help solve education’s big data problems?

The AIU is the first complete system-on-a-chip (SoC) from the IBM Research AI Hardware Center designed expressly to run enterprise AI deep-learning models. 

IBM argues that the “workhorse of traditional computing”, otherwise known as CPU, was designed before deep learning arrived. While CPUs are good for general-purpose applications, they aren’t so good at training and running deep-learning models that require massively parallel AI operations.

“There’s no question in our minds that AI is going to be a fundamental driver of IT solutions for a long, long time,” Jeff Burns, director of AI Compute for IBM Research, told ZDNET. “It’s going to be infused across the computing landscape, across these complicated enterprise IT infrastructures and solutions in a very broad and diffuse way.”

For IBM, it makes the most sense to build complete solutions that are effectively universal, Burns said, “so that we can integrate those capabilities into different compute platforms and support a very, very broad variety of enterprise AI requirements.”

The AIU is an application-specific integrated circuit (ASIC), but it can be programmed to run any type of deep-learning task. The chip features 32 processing cores built with 5 nm technology and contains 23 billion transistors. The layout is simpler than that of a CPU, designed to send data directly from one compute engine to the next, making it more energy efficient. It’s designed to be as easy to use as a graphics card and can be plugged into any computer or server with a PCIe slot.

To conserve energy and resources, the AIU leverages approximate computing, a technique IBM developed to trade computational precision in favor of efficiency. Traditionally, computation has relied on 64- and 32-bit floating point arithmetic, to deliver a level of precision that’s useful for finance, scientific calculations and other applications where detailed accuracy matters. However, that level of precision isn’t really necessary for the vast majority of AI applications. 

“If you think about plotting the trajectory of an autonomous driving vehicle, there’s no exact position in the lane where the car needs to be,” Burns explains. “There’s a range of places in the lane.”

Neural networks are fundamentally inexact – they produce an output with a probability. For instance, a computer vision program might tell you with 98% certainty that you’re looking at a picture of a cat. Even so, neural networks were still initially trained with high-precision arithmetic, consuming significant energy and time. 

Also: I tested out an AI art generator and here’s what I learned

The AIU’s approximate computing technique allows it to drop from 32-bit floating point arithmetic to bit-formats holding a quarter as much information. 

To ensure the chip is truly universal, IBM has focused on more than just hardware innovations. IBM Research has put a huge emphasis on foundation models, with a team of somewhere between 400 and 500 people working on them. In contrast to the AI models that are built for a specific task, foundation models are trained on a broad set of unlabeled data, creating a resource akin to a gigantic database. Then, when you need a model for a specific task, you can retrain the foundation model using a relatively small amount of labeled data. 

Using this approach, IBM intends to tackle different verticals and different AI use cases. There are a handful of domains for which the company is building foundation models – those use cases cover areas such as chemistry and time series data. Time series data, which simply refers to data that’s collected over regular intervals of time, is critical for industrial companies that need to observe how their equipment is functioning. After building foundation models for a handful of key areas, IBM can develop more specific, vertical-driven offerings. The team has also ensured the software for the AIU is completely compatible with IBM-owned Red Hat’s software stack. 


ShareTweetShare

Related Posts

Philips Evnia 7000 monitor review: It shines bright, but doesn’t spark envy- Dejkala
Latest update

Philips Evnia 7000 monitor review: It shines bright, but doesn’t spark envy- Dejkala

June 8, 2023
Adobe brings Firefly, ‘commercially safe’ image-generating AI, to the enterprise- Dejkala
Latest update

Adobe brings Firefly, ‘commercially safe’ image-generating AI, to the enterprise- Dejkala

June 8, 2023
ChatGPT for iOS gets support for Siri and Shortcuts- Dejkala
Latest update

ChatGPT for iOS gets support for Siri and Shortcuts- Dejkala

June 8, 2023
Boeing hit with a lawsuit over alleged “theft” of SLS rocket tools- Dejkala
Latest update

Boeing hit with a lawsuit over alleged “theft” of SLS rocket tools- Dejkala

June 8, 2023
The Bizarre Reality of Getting Online in North Korea- Dejkala
Latest update

The Bizarre Reality of Getting Online in North Korea- Dejkala

June 8, 2023
A survey of 472 corporate board directors ahead of the SEC's cyber-risk regulations: 76% have at least one expert, 62% say risk awareness is improving, and more (Wall Street Journal)- Dejkala
Latest update

A survey of 472 corporate board directors ahead of the SEC's cyber-risk regulations: 76% have at least one expert, 62% say risk awareness is improving, and more (Wall Street Journal)- Dejkala

June 8, 2023
Next Post
Twitter disrupts a China-based influence campaign ahead of the US midterms, spanning nearly 2,000 accounts; two networks skewed right and another left (Washington Post)- Dejkala

Twitter disrupts a China-based influence campaign ahead of the US midterms, spanning nearly 2,000 accounts; two networks skewed right and another left (Washington Post)- Dejkala

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Categories

  • Earn Money Online
  • Game news and review
  • Laptops
  • Latest update
  • Smartphone Reviews & News
  • TODAY Tech News
  • Upcoming Technology
  • Wordpress plugin
  • WordPress themes
  • World Wide Bike Reviews and News
  • World Wide Car News

Recommended

Black Friday robot vacuum deal 2022: Anker’s Eufy drops to $119- Dejkala

Black Friday robot vacuum deal 2022: Anker’s Eufy drops to $119- Dejkala

November 26, 2022
Twitch is trying to fix an issue that’s preventing people from watching streams- Dejkala

Twitch is trying to fix an issue that’s preventing people from watching streams- Dejkala

January 3, 2023
In an open letter, Cameron Winklevoss says Digital Currency Group CEO Barry Silbert has engaged in "bad faith stall tactics" since halting Genesis withdrawals (Olga Kharif/Bloomberg)- Dejkala

In an open letter, Cameron Winklevoss says Digital Currency Group CEO Barry Silbert has engaged in "bad faith stall tactics" since halting Genesis withdrawals (Olga Kharif/Bloomberg)- Dejkala

January 2, 2023
Sources: Apple plans a smart-home display-like mode in iOS 17, with notifications and information like weather, when an iPhone is locked and in landscape mode (Mark Gurman/Bloomberg)- Dejkala

Sources: Apple plans a smart-home display-like mode in iOS 17, with notifications and information like weather, when an iPhone is locked and in landscape mode (Mark Gurman/Bloomberg)- Dejkala

May 24, 2023
Sources: Microsoft faces a shortage of GPUs for AI and is rationing access to them for internal teams, as it prepares to announce GPT-4 tools for Office 365 (Aaron Holmes/The Information)- Dejkala

Sources: Microsoft faces a shortage of GPUs for AI and is rationing access to them for internal teams, as it prepares to announce GPT-4 tools for Office 365 (Aaron Holmes/The Information)- Dejkala

March 15, 2023
The day reality became unbearable: A peek beyond Apple’s AR/VR headset- Dejkala

The day reality became unbearable: A peek beyond Apple’s AR/VR headset- Dejkala

June 4, 2023
Philips Evnia 7000 monitor review: It shines bright, but doesn’t spark envy- Dejkala

Philips Evnia 7000 monitor review: It shines bright, but doesn’t spark envy- Dejkala

June 8, 2023
Adobe brings Firefly, ‘commercially safe’ image-generating AI, to the enterprise- Dejkala

Adobe brings Firefly, ‘commercially safe’ image-generating AI, to the enterprise- Dejkala

June 8, 2023
ChatGPT for iOS gets support for Siri and Shortcuts- Dejkala

ChatGPT for iOS gets support for Siri and Shortcuts- Dejkala

June 8, 2023

Categories

  • Earn Money Online
  • Game news and review
  • Laptops
  • Latest update
  • Smartphone Reviews & News
  • TODAY Tech News
  • Upcoming Technology
  • Wordpress plugin
  • WordPress themes
  • World Wide Bike Reviews and News
  • World Wide Car News

Pages

  • About Us
  • Banking & loan
  • Car’s & Bike’s
  • Contact Us
  • Games
  • Home
  • Home 2
  • Privacy Policy
  • Tech

© 2022 Dejkala

No Result
View All Result
  • Homepages
    • Home – Layout 1
    • Home – Layout 2

© 2022 Dejkala