Take this $15m and make us some ultra-energy-efficient superconductor chips, scientists told
A fair price to get everyone to stop talking about Moore's Law for good
Researchers in the US have received a $15 million National Science Foundation (NSF) award to develop superconductor chips that ought to be much faster and use significantly less energy than the hardware the world today relies on for computing.
A team at the University of Southern California's Viterbi School of Engineering is leading the effort, and it goes by the name DISCoVER, a rather fun acronym that stands for Design and Integration of Superconductive Computation for Ventures beyond Exascale Realization.
As the name suggests, the scientists are looking to use superconducting materials as an alternative to today's semiconductors to develop new kinds of superfast and highly energy efficient integrated circuits that can enable sustainable and large-scale exascale computing.
Creating supercomputers that can deliver more than one exaflop, or one quintillion floating-point operations per second, has been a strategically important goal for the United States and other countries, including China, as they can dramatically speed up critical research projects, ranging from drug development to climate change modeling.
There is a concern, however, that today's approaches to designing and fabricating silicon processors will hit a wall and no longer scale sufficiently to provide post-exaflop performance, hence the need for things like superconductor research to hopefully overcome that technological barrier.
Margaret Martonosi, the NSF's assistant director for computing and information science and engineering, said the $15 million award to DISCoVER, announced on Friday, is meant to "support efforts that envision future materials for computing systems in a post-Moore's Law era."
- Good news: Boffins have finally built room-temperature superconductors. Bad news: You'll need a laser, a diamond anvil, and a lot of pressure
- Brain-like neurochips good for supercomputers, not just AI, says Sandia
- Microsoft quantum lab retracts published paper: Readings that cast doubt on crucial discovery went AWOL
- Drama as boffins claim to reach the Holy Grail of superconductivity
DISCoVER's work entails developing complete hardware and software systems that "enable the design, optimization, and demonstration of novel superconducting devices, single flux quantum logic circuits, and superconductive systems with very high performance and ultra-high energy efficiency, approaching the theoretical limit of energy efficiency."
More specifically, the team is focused on chips that use niobium-based Josephson junctions, devices that consist of two superconducting materials that are connected by a non-superconducting material. These devices can only operate at the super low temperature of 4.2 Kelvin (equal to -452 degrees Fahrenheit or -269 degrees Celsius), and they store logic values of zeroes and ones "by creating or removing persistent currents in superconducting loops."
The real neat thing about these superconducting loops is that they "exhibit zero resistance and thus, do not lose energy," as stated by DISCoVER. This is a big reason why superconductor chips have such staggering implications for energy efficiency in computing.
A long road ahead
There is a tremendous amount of work to be done, so DISCoVER is divvying it up between the USC Viterbi team and researchers at several other universities, which includes Auburn University in Alabama, Cornell University in New York, Northeastern University in Boston, Northwestern University in Illinois, University of Rochester in New York, and Yokohama National University in Japan.
The USC Viterbi team will focus its efforts on developing superconductive circuits and architectures for a wide range of applications, including general-purpose processors, neural network accelerators, and classical control systems for quantum computers.
The other university researchers, on the other hand, will work in tandem with the USC Viterbi team on enabling the "design and prototyping of a superconductive system of cryogenic computing cores," which carries the unbelievably cool acronym of SuperSoCC.
The SuperSoCC work will involve a focus on novel materials and devices, on-chip memory design, and interfaces that will allow the SuperSoCC to interact with room-temperature electronics.
DISCoVER believes the SuperSOCC could be at least 100 times more energy efficient than traditional chips made using silicon-based CMOS transistors while providing the same level of performance as "state-of-the-art" multi-core semiconductor chips. On the flip side, the team thinks the SuperSoCC could provide at least 100 times faster performance at the same energy level as CMOS-based chips.
Notably, DISCoVER said these major gains are possible despite the energy cost of cryogenic cooling, which is required for the SuperSOCC.
Ultimately, DISCoVER hopes to "empower a new generation of diverse engineers and entrepreneurs who will bring superconductive devices and circuits to the mainstream of high-performance computing."
"With fundamental CMOS scaling limits close in sight, the time is ripe for an expedition to explore emerging disruptive computing technologies," said Massoud Pedram, a USC professor and green computing expert who is leading DISCoVER. ®