The processor is a 4bit data device made using niobium/aluminum Josephson Junctions and operates at 4.2K
Digital communications consumes approximately 10 percent of global electricity and this could rise to 50 percent by 2030 if there is no change to the underlying technology, according to Christopher Ayala, an associate professor at Yokohama National University, and lead author of a research paper published in Journal: IEEE Journal of Solid-State Circuits
The processor uses an energy-efficient superconductor digital electronic structure, called the adiabatic quantum-flux-parametron (AQFP), as a building block.
“In this paper, we wanted to prove that the AQFP is capable of practical energy-efficient high-speed computing, and we did this by developing and successfully demonstrating a prototype 4-bit AQFP microprocessor called MANA (Monolithic Adiabatic iNtegration Architecture), the world’s first adiabatic superconductor microprocessor,” said Ayala.
MANA is a hybrid of RISC and dataflow architectures operating on 4-bit data words. The research demonstrates register file read/write access, ALU execution, hardware stalling, and program branching performed at 100 kHz under the cryogenic temperature of 4.2 K. On a separate chip the team showed the operation of individual execution units at up to 2.5GHz.
While the raw performance is modest the AQFP logic primitive has a switching energy of 1.4zJ per Josephson Junction when driven by a four-phase 5-GHz sinusoidal ac-clock at 4.2K.
Obviously considerable power has to be expended to cool the MANA to 4.2K.
“But even when taking this cooling overhead into account, the AQFP is still about 80 times more energy-efficient when compared to the state-of-the-art semiconductor electronic devices found in high-performance computer chips available today.”
The team is now looking to further optimize the design, increase operational speed and energy-efficiency
In addition to building standard microprocessors, the team is also interested in examining how AQFPs could assist in neuromorphic computing hardware and quantum computing applications.
Related links and articles: