Design and implementation of control system for superconducting RSFQ circuit

The superconducting rapid single flux quantum(RSFQ)integrated circuit is a promising solu-tion for overcoming speed and power bottlenecks in high-performance computing systems in the post-Moore era.This paper presents an architecture designed to improve the speed and power limitations of high-performance computing systems using superconducting technology.Since superconducting microprocessors,which operate at cryogenic temperatures,require support from semiconductor cir-cuits,the proposed design utilizes the von Neumann architecture with a superconducting RSFQ mi-croprocessor,cryogenic semiconductor memory,a room temperature field programmable gate array(FPGA)controller,and a host computer for input/output.Additionally,the paper introduces two key circuit designs:a start/stop controllable superconducting clock generator and an asynchronous communication interface between the RSFQ and semiconductor chips used to implement the control system.Experimental results demonstrate that the proposed design is feasible and effective,provi-ding valuable insights for future superconducting computer systems.

An Asynchronous Implementation of Add-Compare-Select Processor for Communication Systems

A novel asynchronous ACS(add-compare-select) processor for Viterbi decoder is described.It is controlled by local handshake signals instead of the globe clock.The circuits of asynchronous adder unit,asynchronous comparator unit,and asynchronous selector unit are proposed.A full-custom design of asynchronous 4-bit ACS processor is fabricated in CSMC-HJ 0.6μm CMOS 2P2M mixed-mode process.At a supply voltage of 5V,when it operates at 20MHz,the power consumption is 75.5mW.The processor has no dynamic power consumption when it awaits an opportunity in sleep mode.The results of performance test of asynchronous 4-bit ACS processor show that the average case response time 19.18ns is only 82% of the worst-case response time 23.37ns.Compared with the synchronous 4-bit ACS processor in power consumption and performance by simulation,it reveals that the asynchronous ACS processor has some advantages than the synchronous one.

An Asynchronous 32×8-Bit Multiplier Based on LDCVSPG Logic

An asynchronous high-speed pipelined 32×8-bit array multiplier based on latched differential cascode voltage switch with pass-gate （LDCVSPG） logic is presented. The multiplier is based on 4-phase dual-rail protocol. HSPICE analysis using device parameters of Central Semiconductor Manufacturing Corporation （CSMC＇s） 0.6μm CMOS technology is also given, and the result shows that the average data throughput of the multiplier is 375 MHz.

Optimization design of a full asynchronous pipeline circuit based on null convention logic

This paper proposes a new optimization method to improve the performance of a null convention logic asynchronous pipeline.Parallel combinational logic modules in the pipelines can work alternately in null and data cycles by using a parallel processing mode.The complete waiting time for both null and data signals of combinational logic output in previous asynchronous register stage is reduced by decoupling the output from combinational logic modules.Performance penalty brought by null cycle is reduced while the data processing capacity is increased.The novel asynchronous pipeline based on asynchronous full adders with different bit widths as asynchronous combination logic modules is simulated using 0.18-μm CMOS technology.Based on 6 bits asynchronous adder as asynchronous combination logic modules, the simulation result of this new pipeline proposal demonstrates a high throughput up to 72.4% improvement with appropriate power consumption.This indicates the new design proposal is preferable for high-speed as ynchronous designs due to its high throughput and delay-insensitivity.

Implementation of low-swing differential interface circuits for high-speed on-chip asynchronous interconnection

A novel low-swing interface circuit for high-speed on-chip asynchronous interconnection is proposed in this paper. It takes a differential level-triggered latch to recover digital signal with ultra low-swing voltage less than 50 mV, and the driver part of the interface circuit is optimized for low power using the driver-array method, With a capacity to work up to 500 MHz, the proposed circuit, which is simulated and fabricated using SMIC 0.18-pm 1.8-V digital CMOS technology, consumes less power than previously reported designs.

Investigation of Asynchronous Pipeline Circuits Based on Bundled-Data Encoding: Implementation Styles, Behavioral Modeling,and Timing Analysis

As VLSI technology enters the post-Moore era, there has been an increasing interest in asynchronous design because of its potential advantages in power consumption, electromagnetic emission, and automatic speed scaling capacity under supply voltage variations. In most practical asynchronous circuits, a pipeline forms the micro-architecture backbone, and its characteristics play a vital role in determining the overall circuit performance.In this paper, we investigate a series of typical asynchronous pipeline circuits based on bundled-data encoding,spanning different handshake signaling protocols such as 2-phase(micropipeline, Mousetrap, and Click), 4-phase(simple, semi-decoupled, and fully-decoupled), and single-track(GasP). An in-depth review of each selected circuit is conducted regarding the handshaking and data latching mechanisms behind the circuit implementations, as well as the analysis of its performance and timing constraints based on formal behavior models. Overall, this paper aims at providing a survey of asynchronous bundled-data pipeline circuits, and it will be a reference for designers interested in experimenting with asynchronous circuits.

A self-circulation structure for pipeline control

This paper proposes a circuit structure which can be used for both synchronous and asynchronous pipeline control. It is a self-circulation structure with embedded delay network, and a pipeline can be controlled by this structure with the interconnection of adjacent stages. This paper first proposes a basic circuit structure, then a linear pipeline is designed with self-circulation structure. The performance of linear pipeline is analyzed, and a 16-bit digital signal processor (DSP) with the structure is designed to prove the validity of the structure. Results show that about 10%-15% power consumption is saved with self-circulation structure compared with synchronous counterpart, while almost the same performance is achieved.

Design and Tool Flow of a Reconfigurable Asynchronous Neural Network Accelerator

Convolutional Neural Networks(CNNs)are widely used in computer vision,natural language processing,and so on,which generally require low power and high efficiency in real applications.Thus,energy efficiency has become a critical indicator of CNN accelerators.Considering that asynchronous circuits have the advantages of low power consumption,high speed,and no clock distribution problems,we design and implement an energy-efficient asynchronous CNN accelerator with a 65 nm Complementary Metal Oxide Semiconductor(CMOS)process.Given the absence of a commercial design tool flow for asynchronous circuits,we develop a novel design flow to implement Click-based asynchronous bundled data circuits efficiently to mask layout with conventional Electronic Design Automation(EDA)tools.We also introduce an adaptive delay matching method and perform accurate static timing analysis for the circuits to ensure correct timing.The accelerator for handwriting recognition network(LeNet-5 model)is implemented.Silicon test results show that the asynchronous accelerator has 30%less power in computing array than the synchronous one and that the energy efficiency of the asynchronous accelerator achieves 1.538 TOPS/W,which is 12%higher than that of the synchronous chip.

Low Latency High Throughout Circular Asynchronous FIFO

This paper describes a circular first in first out （FIFO） and its protocols which have a very low latency while still maintaining high throughput. Unlike the existing serial FIFOs based on asynchronous micropipelines, this FIFO＇s cells communicate directly with the input and output ports through a common bus, which effectively eliminates the data movement from the input port to the output port, thereby reducing the latency and the power consumption. Furthermore, the latency does not increase with the number of FIFO stages. Single-track asynchronous protocols are used to simplify the FIFO controller design, with only three C-gates needed in each cell controller, which substantially reduces the area. Simulations with the TSMC 0.25 μm CMOS logic process show that the latency of the 4-stage FIFO is less than 581 ps and the throughput is higher than 2.2 GHz.