Blog Page


Algorithm Predicts Processor Power Consumption Incredibly Fast – Unite.AI

Computer engineers at Duke University have developed a new artificial intelligence (AI) method that can accurately predict the power consumption of any type of computer processor. The most impressive feature of this new method is its ability to carry this out over a trillion times per second, all while using very little computation power itself.
The new technique is called APOLLO, and it has been validated on real-world, high-performance microprocessors. It could be applied in many different ways, including to improve the efficiency and inform the development of microprocessors. 
The research detailing this new method was published at MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture. 
Zhiyao Xie is first author of the paper and a PhD candidate in the laboratory of Yiran Chen, who is a professor of electrical and computer engineering at Duke.
“This is an intensively studied problem that has traditionally relied on extra circuitry to address,” said Xie. “But our approach runs directly on the microprocessor in the background, which opens many new opportunities. I think that’s why people are excited about it.”
Modern computer processors rely on cycles of computations that are made 3 trillion times per second. In order to maintain the chip’s performance and efficiency, the power consumption of these fast transitions must be tracked. When a processor draws too much power, it can result in overheating and damage. When the power changes fast, it can cause internal electromagnetic complications that result in a slower processor.
Software can predict and stop these extremes, and computer engineers can use it to protect hardware and increase performance. However, this process requires extra hardware and computational power.
“APOLLO approaches an ideal power estimation algorithm that is both accurate and fast and can easily be built into a processing core at a low power cost,” Xie said. “And because it can be used in any type of processing unit, it could become a common component in future chip design.”
APOLLO draws on artificial intelligence for its power. The algorithm relies on AI to identify and select 100 of a processor’s millions of signals, which correlate with its power consumption. Those 100 signals are then used to build a power consumption model, and the algorithm monitors them to predict the chip’s performance in real-time. 
This process is autonomous and data driven, meaning it  can be implemented on nearly any type of computer processor architecture. 
“After the AI selects its 100 signals, you can look at the algorithm and see what they are,” Xie said. “A lot of the selections make intuitive sense, but even if they don’t, they can provide feedback to designers by informing them which processes are most strongly correlated with power consumption and performance.”
The researchers say that the algorithm still needs further testing and comprehensive evaluations on different platforms. This is required before it can be adopted by commercial computer manufacturers.
Human Brain Project Releases New Paper on Exascale Computing Power
Alex McFarland is a Brazil-based writer who covers the latest developments in artificial intelligence & blockchain. He has worked with top AI companies and publications across the globe.
Scientists Create Self-Powered, Aqueous Robot That Runs Without Electricity
AI Uses Reinforcement Learning to Navigate Oceans
Statistical Model Helps Detect Misinformation on Social Media
Scientists Create First-Ever Self-Replicating, Living Robots
AI System Identifies COVID-19 Patients Who Require ICU
New Machine Learning Approach Could Accelerate Drug Design
Advertiser Disclosure: Unite.AI is committed to rigorous editorial standards to provide our readers with accurate information and news. We may receive compensation when you click on links to products we reviewed.
Copyright © 2021 Unite.AI


× How can I help you?