Adiabatic Quantum-Flux-Parametron: Towards Building Extremely Energy-Efficient Circuits and Systems

Abstract

Adiabatic Quantum-Flux-Parametron (AQFP) logic is an adiabatic superconductor logic family that has been proposed as a future technology towards building extremely energy-efficient computing systems. In AQFP logic, dynamic energy dissipation can be drastically reduced due to the adiabatic switching operations using AC excitation currents, which serve as both clock signals and power supplies. As a result, AQFP could overcome the power/energy dissipation limitation in conventional superconductor logic families such as rapid-single-flux-quantum (RSFQ). Simulation and experimental results show that AQFP logic can achieve an energy-delay-product (EDP) near quantum limit using practical circuit parameters and available fabrication processes. To shed some light on the design automation and guidelines of AQFP circuits, in this paper we present an automatic synthesis framework for AQFP and perform synthesis on 18 circuits, including 11 ISCAS-85 circuit benchmarks, 6 deep-learning accelerator components, and a 32-bit RISC-V ALU, based on our developed standard cell library of AQFP technology. Synthesis results demonstrate the significant advantage of AQFP technology. We forecast 9,313×, 25,242× and 48,466× energy-per-operation advantage, compared to the synthesis results of TSMC (Taiwan Semiconductor Manufacturing Company) 12 nm fin field-effect transistor (FinFET), 28 nm and 40 nm complementary metal-oxide-semiconductor (CMOS) technology nodes, respectively.

Design of a Power Efficient Artificial Neuron Using Superconducting Nanowires

“…However, given that superconducting platforms have no dissipation in their interconnects in their DC state, we believe that it is reasonable to project in such a way. We have also assumed that the constant applied bias current will not significantly affect the overall power consumption, based on previously proposed superconducting architectures that use a current dividing network made of inductors rather than resistors to eliminate the majority of dissipation from static biasing, as has been suggested for single flux quantum electronics (Mukhanov, 2011). In doing so, it is apparent that the nanowire neuron can be a highly competitive technology from a power and speed perspective, and that operation at cryogenic temperatures does not pose a serious disadvantage to its overall performance.…”

Compact Superconducting Lookup Table Composed of Two-Dimensional Memory Cell Array Reconfigured by External DC Control Currents

“…J OSEPHSON junction [1] (JJ)-based superconducting circuits [2], [3] are attracting attention as an alternative technology to semiconductor integrated circuits because of its high-speed operation and superior energy efficiency [4], [5]. To date, the operation of large-scale superconducting digital circuits has been applied as information processing circuits [6], [7], [8].…”

A semi-custom design methodology and environment for implementing superconductor adiabatic quantum-flux-parametron microprocessors

“…Superconductor electronics have the potential to provide a high-performance, energy-efficient computing platform to power the present era of 'internet of things', big data, and social media [1][2][3]. Several energy-efficient superconductor logic families exist to provide such a platform, including energy-efficient RSFQ logic [4], energy-efficient SFQ logic [5], reciprocal quantum logic (RQL) [6], LR-biased RSFQ logic [7], and low voltage RSFQ (LV-RSFQ) logic [8].…”

“…But as with any new technology, one must consider additional overhead when it comes to building systems beyond simple logic gates. A design study on AQFP logic was conducted in [3]. It synthesized a set of benchmark circuits and performed a data-dependent energy analysis while taking into account the additional overhead of buffering data to ensure phase-to-phase propagation and synchronization of signals.…”