Katie Antypas strode across the stage at Kaiser Center in downtown Oakland before an audience composed of scholars, kids and residents. “What happens when you are sitting at home, you open up your laptop?” she asked. “Your laptop starts to get hot.”
As the first speaker at the “8 Big Ideas” event, Antypas announced a supercomputer system called Cori, which will come online in 2016. During the talk, she broke the complicated idea into understandable daily situations and digestible concepts with the charisma of a TED Talks performer.
Antypas is the service department head for the National Energy Research Scientific Computing Center and one of the eight speakers at the “8 Big Ideas” event last Wednesday, which was hosted by the Lawrence Berkeley National Laboratory as part of its “Science at the Theater” initiative. During the event, eight scientists were invited to present game-changing concepts and progressive ideas in eight minutes each.
Science at the Theater has been part of the lab’s outreach program for 10 years. The idea is to get the audience more involved and create a program that is less a lecture, and more a conversation. “We could choose any number, but we decided on eight because it is really a matter of minutes. Eight multiplied by eight is 64,” said Jeff Miller, the head of public affairs at the lab and the main organizer of the event. “We don’t want our program to run longer than hour. It is also to give the scientists a certain amount of time to explain their big ideas. ”
“We used to do it exclusively in Berkeley, but we decided that we wanted to take it to other locations,” Miller said. “Last spring, we did one in Richmond. We are experimenting with the program to bring our science to where people are, instead making them come to us.”
“Typically, a desktop or laptop system has one, two or four processor cores,” said Antypas as she continued her talk. But for a supercomputer system, the number will be much bigger—100,000 processor cores. “Can you imagine how much power or energy a desktop or laptop system that contains more than 100,000 processing cores will use everyday?” Antypas asked the audience.
The heating problem for these computers has been a puzzle for a long time. With a laptop, people can use a fan as a way to cool it down. But for supercomputers, a fan is not enough. “We also use another technique, which is called liquid cooling,” Antypas said, “because it is actually more efficient to cool these computers with liquid than air alone.” But using all these cooling methods will lead to a giant energy bill.
Another problem is that today’s computers trap too much heat. Thanks to what programmers call Moore’s Law, she said, every two years, the numbers of transistors on computer chips doubles. In the 1970s, 80s and 90s, these transistors just got thinner and tinier and processors got faster and faster. “But something happened in 2004,” Antypas said. “What happened is that these transistors were getting so small, so thin, that they were unable to dissipate the heat.”
And that’s a problem, because not being able to cool a computer limits its abilities. “We’ve got a huge demand of computing from our scientists, but we do not have the ability to power these computers,” said Antypas. “What we are doing at Berkeley lab is that we provide scientists with efficient computing.”
The Cori system will be a more energy-efficient system because it will have over 60 lightweight processor cores in a single chip operating at a low speed. With these tiny processors, the Cori system will offer scientists more powerful supercomputers without increasing energy expenditure, Antypas said.
Her talk won applause from the audience in that she translated many complicated terms into digestible ideas. So did the other seven projects, which included a pill to treat people exposed to radioactive materials, a portable solar-powered refrigerator for vaccines and combustion science for cleaner fuels.
“These guys are really good,” said Adam Glickman, a first-time attendee, who praised the scientists for explaining concepts using comparisons to daily life. “They are like this level,” he said, raising his hand to his eyebrow. But, he continued, “They are good at bring things down to people’s level. The more similes, the more you understand some of the concept.”
“We tried to work with the scientists to remind them that they are speaking to people who may not be scientists,” said Miller. “It is not a formal scientific presentation. We look for a wide range of topics and things are really a big idea, things can fundamentally change people’s life and have a practical application. It is about practical application and tremendous social benefit. The science is not for profit—this is for the public.”