
Nvidia uses GPUs and machine learning algorithms to design new video accelerators. Writes about it HPC Wire.
According to the company’s chief scientist and senior vice president of research, Bill Dally, artificial intelligence can be used effectively in four important areas of GPU design:
- voltage drop mapping;
- forecasting parasitic phenomena;
- placement and routing problems;
- automation of standard cell migration.
Voltage drop mapping shows engineers how power is distributed in new processors. According to Dalli, when using the standard design method, the necessary calculations are made in three hours. The use of an AI algorithm has reduced this process to three seconds with an accuracy of 94%.
“We can get very accurate stress estimates much faster than with conventional instruments and in a very short time,” Dalli said.
The engineers also used graph neural networks to analyze the problem of placing and routing processor components. Failure to do so will result in “data jams” similar to congestion on metropolitan roads, Dalli said, requiring chip layouts to be redesigned.
“He [алгоритм] shows problem areas, and we can act on them and iterate very quickly, without having to do a complete rerouting, ”the scientist added.
Automating standard cell migration with AI can help accelerate adoption of new standards. Dalli noted that the transition from 7nm to 5nm chip manufacturing process required a lot of labor. Reinforcement learning helped speed up this step and reduce errors in the design rules.
“This is a huge labor savings […]. In many cases, we also got a better design,” Dalli said.
Recall that in March 2022, Google introduced the PRIME algorithm, which helps to develop fast and compact processors for processing AI tasks.
In October 2021, the search giant talked about using reinforcement learning to reduce the time it takes to create chips from months to six hours.
In August, Samsung began using artificial intelligence to automate the process of developing computer chips.
Subscribe to Cryplogger news in Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER

Nvidia uses GPUs and machine learning algorithms to design new video accelerators. Writes about it HPC Wire.
According to the company’s chief scientist and senior vice president of research, Bill Dally, artificial intelligence can be used effectively in four important areas of GPU design:
- voltage drop mapping;
- forecasting parasitic phenomena;
- placement and routing problems;
- automation of standard cell migration.
Voltage drop mapping shows engineers how power is distributed in new processors. According to Dalli, when using the standard design method, the necessary calculations are made in three hours. The use of an AI algorithm has reduced this process to three seconds with an accuracy of 94%.
“We can get very accurate stress estimates much faster than with conventional instruments and in a very short time,” Dalli said.
The engineers also used graph neural networks to analyze the problem of placing and routing processor components. Failure to do so will result in “data jams” similar to congestion on metropolitan roads, Dalli said, requiring chip layouts to be redesigned.
“He [алгоритм] shows problem areas, and we can act on them and iterate very quickly, without having to do a complete rerouting, ”the scientist added.
Automating standard cell migration with AI can help accelerate adoption of new standards. Dalli noted that the transition from 7nm to 5nm chip manufacturing process required a lot of labor. Reinforcement learning helped speed up this step and reduce errors in the design rules.
“This is a huge labor savings […]. In many cases, we also got a better design,” Dalli said.
Recall that in March 2022, Google introduced the PRIME algorithm, which helps to develop fast and compact processors for processing AI tasks.
In October 2021, the search giant talked about using reinforcement learning to reduce the time it takes to create chips from months to six hours.
In August, Samsung began using artificial intelligence to automate the process of developing computer chips.
Subscribe to Cryplogger news in Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER