In a keynote today, Bill Daly, chief scieist and senior vice preside of research at Nvidia, highlighted significa gains in hardware performance that have paved the way for advances in artificial ielligence and offer exciting opportunities for further advances in machine learning.
According to Hoshio, Senior Scieist Bill Daly preseed research that promises to take machine learning to unprecedeed levels.
In a talk at Hot Chips, an annual eve for processor and system architects, Daly showcased a range of techniques currely in use, some of which are showing significa results.
“Advances in artificial ielligence have been remarkable thanks to improved hardware, and those advances are still held back by deep learning hardware,” says Daly, one of the world’s leading computer scieists and former chair of Stanford University’s computer science departme.
For example, he showed how ChatGPT, a large language model (LLM) used by millions of people, can suggest an outline for your speech. Such capabilities owe much to GPU gains in AI inference performance over the past decade, he said.
Researchers are preparing the next wave of advances. Daly shared details of a test chip that demonstrated impressive performance of nearly 100 tera-operations per watt in a low-power, low-power memory (LLM) configuration.
Through a rece experime, researchers have discovered a low-power way to speed up transformer models used in generative artificial ielligence. This technique involves the use of four-bit calculations, which is considered a simplified numerical method. This method shows promising prospects for improvemes and providing more benefits in the future.
Daly has discussed ways to speed up calculations and save energy using logarithmic mathematics as an approach to achieving these goals. The approach is detailed in a pate filed by NVIDIA in 2021.
He has explored dozens of other techniques for customizing hardware specifically for AI tasks. This customization involves creating new data types or operations to optimize hardware performance in AI applications.
Daly noted that researchers must develop hardware and software together and make thoughtful choices about how to allocate energy resources. For example, minimizing data transfer in memory and communication circuits should be prioritized.
“Being a computer engineer in this day and age is exciting because they are playing an influeial role in the importa revolution that is happening in artificial ielligence,” Daly said. “The true exte of this revolution is not yet fully understood, and that makes it all the more exciting.”
