Home Technology IBM launches New Power9 Chip for AI and Machine Learning

IBM launches New Power9 Chip for AI and Machine Learning

IBM has been a leader in the world of technology for a long time now and one of the areas it has come to specialize in is computing. Artificial intelligence (AI) and machine learning (ML) applications require a lot of computing power in order to operate efficiently. The way this is handled is through the use of processing chips. IBM’s new chip is called the Power9 and it’s one of the most advanced chips around.

Rather than sell the chip directly to consumers, IBM intends to sell to cloud vendors and third-party manufactures. At the same time, the company is also launching a new computer called AC922 that is being powered by this chip, to show off just how good it is. The chips will also be offered as part of a service that will be available via the cloud.

Power9 Chip for AI and Machine learning

The Power9 chip has been designed specifically to be able to handle the requirements of AI frameworks such as Caffe, TensorFlow, and Chainer. According to IBM, the chip should give data scientists enough increased speed to build and run their AI models much faster than before.

MORE – IBM Watson: What you Need to Know

“Power9 is a chip which has a new systems architecture that is optimized for accelerators used in machine learning. Intel makes Xeon CPUs and Nervana accelerators and NVIDIA makes Tesla accelerators. IBM’s Power9 is literally the Swiss Army knife of ML acceleration as it supports and an astronomical amount of IO and bandwidth, 10X of anything that’s out there today,” said Patrick Moorhead, principal analyst at Moor Insights & Strategy.

NVIDIA is a company that’s also booming in AI applications at the moment, and so teaming up with IBM seemed only logical. “Modern workloads are becoming accelerated and the Nvidia GPU is a common accelerator. We have seen this trend coming. We built a deep relationship with them and a partnership between the Power system and the GPU. We have a unique bus that runs between the processor and the GPU and has 10x peak bandwidth over competitive systems,” said Brad McCredie. IBM fellow and vice president of cognitive systems.

As well as IBM’s own computer, the new chips will also be powering a supercomputer that’s in the process of being built at the moment by scientists at the Lawrence Livermore and OakRidge National Laboratories. The supercomputer is called Summit and will be built upon thousands of Power9 computers, at an estimated cost of around $325 million.

Source Techcrunch

Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...