Artificial intelligence simulates microprocessor performance in real time

This approach is detailed in an article presented at MICRO-54: the 54th IEEE / ACM International Symposium on MicroArchitecture.Micro-54 is one of the top conferences in the field of computer architecture and was selected as the best publication of the conference.
“This is a problem that needs to be studied in depth and has traditionally relied on additional circuitry to solve it,” said Zhiyao Xie, lead author of the article and doctoral student in the lab of Yiran Chen, professor of electricity and computer engineering at Duke. “But our approach works directly on background microprocessors, which opens up a lot of new opportunities. I think that’s why people are so excited about it. ”

In modern computer processors, the computation cycle is 3 trillion times per second. Tracking the energy consumed for such a fast conversion is important to maintaining the performance and efficiency of the entire chip. If a processor consumes too much power, it can overheat and cause damage. Sudden fluctuations in power demand can lead to internal electromagnetic complications that slow down the entire processor.
By implementing software that can predict and prevent these unwanted extremes, computer engineers can protect their hardware and improve its performance. But such a plan would come at a cost. Keeping up to date with modern microprocessors often requires valuable additional hardware and computing power.
“APOLLO comes close to an ideal power estimation algorithm that is both precise and fast and can easily be integrated into a low power cost processing core,” said Xie. “Since it can be used in any type of processing unit, it could become a common component in future chip designs.”
The secret to Apollo’s power is artificial intelligence. The algorithm developed by Xie and Chen uses artificial intelligence to identify and select the 100 signals most closely related to power consumption among the millions of signals from the processor. The company then built a power model from those 100 signals and monitored them to predict the performance of the entire chip in real time.
Because this learning process is autonomous and data-driven, it can be implemented on most computer processor architectures, even those that have not yet been invented. While it doesn’t need any human designer expertise to do its job, the algorithm can help human designers do theirs.
“Once the AI ​​picks out 100 signals, you can look at the algorithm and see what they are,” Xie said. in relation to power consumption and performance. “
This work is part of a collaboration with Arm Research, a computer engineering research organization that aims to analyze disruptions affecting industry and create advanced solutions that can be deployed years in advance.APOLLO has been validated on some of the best processors today with the help of ARM Research. But the algorithm needs to be thoroughly tested and evaluated on more platforms before it can be adopted by commercial computer manufacturers, the researchers said.
“Arm Research has partnered with and secured funding from some of the best-known companies in the industry, such as Intel and IBM, and forecasting power consumption is one of their top priorities,” said Chen. “Programs like this provide our students with an opportunity to work with these industry leaders, and these results make them want to continue working with and hire Duke graduates.”
This study was conducted by the Arm Research High-Performance AClass CPU Research research program and was partially supported by the National Science Foundation (NSF-2106828, NSF-2112562) and Semiconductor Research Corporation (SRC).