Industry News

IBM unveiled AIU chip: 5nm 32 core, 23 billion transistors

Update time : 2022-11-14 10:57:28

In October, IBM unveiled its first Artificial Intelligence Unit (AIU) system-on-chip, an application-specific integrated circuit (ASIC) designed to train and run deep learning models that require large-scale parallel computing faster and more efficiently.
In the past few years, the industry has mainly used CPUs and GPUs to run deep learning models, but as the number of artificial intelligence models is growing exponentially, deep learning models are becoming larger and larger, with billions or even trillions of parameters. The computing power required is also getting higher and higher, and the growth of AI computing power of chips with traditional architectures such as CPUs and GPUs has encountered bottlenecks.
According to IBM, deep learning models have traditionally relied on a combination of CPUs and GPU coprocessors to train and run models. The flexibility and high precision of CPUs are well suited for general-purpose software applications, however, CPUs are at a disadvantage when it comes to training and running deep learning models that require massively parallel AI operations. Both CPUs and GPUs were designed before the deep learning revolution, and now their efficiency growth has lagged behind the exponential growth of deep learning computing power. What the industry really needs is general-purpose chips optimized for matrix and vector multiplication types for deep learning.
Based on this, the IBM Research AI Hardware Center has been focusing on developing next-generation chips and artificial intelligence systems for the past five years, hoping to improve the efficiency of artificial hardware intelligence by 2.5 times by 2029 and be able to train and run artificial intelligence models 1,000 times faster than in 2019.
The latest AIU chip is the first IBM chip to be customized for modern AI statistics. IBM says AIU can solve complex problems in vector computation and perform data analytics faster than CPU capabilities. The AIU chip is a complete system-on-chip based on an extended version of the proven AI accelerator built into IBM's previous Telum chip (7nm process) and uses a more advanced 5nm process with 32 processing cores and 23 billion transistors.
The IBM AIU is also designed to be as easy to use as a graphics card. It can be plugged into any computer or server with a PCIe slot. IBM said: "Deploying AI to sort cats and dogs in photos is a fun academic exercise. But it won't solve the pressing problems we face today. For us to get AI to solve real-world complexities - like predicting the next hurricane Ian, or whether we're heading for a recession - we need enterprise-grade, industrial-grade hardware. Our AIU takes that vision one step closer."

Previous : Littelfuse - Compact SMD TVS Diodes Offer High Reliability, Increase Surge Handling by 66% for Aerospace Electronics Applications

Next : Nissan's U.S. plant to cut production due to lack of cores, or lose 9,000 units

How many chips does a car need?

Sep .19.2024

Automotive chips can be divided into four types according to their functions: control (MCU and AI chips), power, sensors, and others (such as memory). The market is monopolized by international giants. The automotive chips people often talk about refer to

Position and Function of Main Automotive Sensors

Sep .18.2024

The function of the air flow sensor is to convert the amount of air inhaled into the engine into an electrical signal and provide it to the electronic control unit (ECU). It is the main basis for determining the basic fuel injection volume. Vane type: The

Chip: The increasingly intelligent electronic brain

Sep .14.2024

In this era of rapid technological development, we often marvel at how mobile phones can run various application software smoothly, how online classes can be free of lag and achieve zero latency, and how the functions of electronic devices are becoming mo

LDA100 Optocoupler: Outstanding Performance, Wide Applications

Sep .13.2024

In terms of characteristics, LDA100 is outstanding. It offers AC and DC input versions for optional selection, enabling it to work stably in different power supply environments. The small 6-pin DIP package not only saves space but also facilitates install

About Us

About Us What we do Quality People

Products

CHIP/IC Active devices Passive device Components OTHER

China electronic components supplier----Wah Luen Shing Electronic.----www.wlschip.com

Leave a message