• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.1
• /
• pp.51-58
• /
• 2007

This paper presented an adaptive pipeline architecture for a high-performance and low-power asynchronous processor. The proposed pipeline architecture employed a stage-skipping and a stage-combining scheme. The stage-skipping scheme can skip the operation of a bubble stage that is not used pipeline stage in an instruction execution. In the stage-combining scheme, two consecutive stages can be joined to form one stage if the latter stage is empty. The proposed pipeline architecture could reduce the processing time and power consumption. The proposed architecture supports multi-processing in the EX stage that executes parallel 4 instructions. We designed an asynchronous microprocessor to estimate the efficiency of the proposed pipeline architecture that was synthesized to a gate level design using a $0.35-{\mu}m$ CMOS standard cell library. We evaluated the performance of the target processor using SPEC2000 benchmark programs. The proposed architecture showed about 2.3 times higher speed than the asynchronous counterpart, AMULET3i. As a result, the proposed pipeline schemes and architecture can be used for asynchronous high-speed processor design

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.4
• /
• pp.85-94
• /
• 2003

The asynchronous design methods proved to have the higher performance in power consumption and execution speed than synchronous ones because it just needs to activate the required module without feeding clock in the system. Despite the advantage of CISC machine providing the variable addressing modes and instructions, its execution scheme is hardly suited for a synchronous Pipeline architecture and incurs a lot of overhead. This paper proposes a novel asynchronous pipeline architecture, A80sl, whose instruction set is fully compatible with that of Intel 80C51, an embedded micro controller. We classify the instructions into the group keeping the same execution scheme for the asynchronous pipeline and optimize it eliminating the bubble stage that comes from the overhead of the multi-cycle execution. The new methodologies for branch and various instruction lengths are suggested to minimize the number of states required for instructions execution and to increase its parallelism. The proposed A80C51 architecture is synthesized with 0.35${\mu}{\textrm}{m}$ CMOS standard cell library. The simulation results show higher speed than that of Intel 80C51 with 36 MHz and other asynchronous counterparts by 24 times.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.4
• /
• pp.812-822
• /
• 1997

In this paper, we propose an architecture of the asynchronous shared-bus type switch with priority and fairness schemes. The switch architecture is an input and output queueing system, and the priority scheme is implemented in both input and output queues. We analyze packet delay of both input and output queues. In the analysis, we consider to stations with asymmetric arrival rates. Although we make some approximations in the analysis, the numerical results show good agreements with the simulation results.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.5
• /
• pp.71-81
• /
• 2008

In this paper, we propose a novel Globally Asynchronous, Locally Dynamic System(GALDS) bus and demonstrate its performance. The proposed GALDS bus is the bidirectional multitasking bus with the segmented bus architecture supporting the concurrent operation of multi-masters and multi-slaves. By analyzing system tasks, the bus architecture chooses the optimal frequency for each If among multiples of bus frequency and thus we can reduce the overall power consumption. For efficient data communications between IPs operating in different frequencies, we designed an asynchronous and bidirectional FIFO based on an asynchronous wrapper with hand-shaking interface. In addition, since systems can be easily expandable by inserting bus segments, the proposed architecture has advantages in IP reusability and structural flexibility As a test example, a four-segment bus haying four masters and four slaves were designed by using Verilog HDL. We demonstrate multitasking operations with read/write data transfers by simulation when the ratios of operation frequency are 1:1, 1:2, 1:4 and 1:8. The data transfer mode is a 16 burst increment mode compatible with Advanced Microcontroller Bus Architecture(AMBA). The maximum operation latency of the proposed GALDS bus is 22 clock cycles for the bus write operation, and 44 clock cycles for read.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.45-50
• /
• 2017

Micro-service Architecture is a service architecture optimized for large-scale distributed systems such as real-time realistic broadcasting systems, so that are fiercely adopted by Global leading service platform vendors such as Netflix and Twitter due to the merit of horizontal performance scalability enabling the scale-out technique. In addition, micro-service architecture makes it possible to execute image processing and real-time data analysis using an asynchronous-based processing that are difficult to handle in Web API such as REST. In this paper, an event stream processing framework applicable to asynchronous based micro services is proposed in the sense that the accountability of event processing order is not guaranteed in the events such as IoT sensor data analysis or cloud-based image editing because these are the situations where the real-time media editing generates multiple event streams and asynchronous processes in the platform.

• ETRI Journal
• /
• v.35 no.3
• /
• pp.480-490
• /
• 2013

As technology evolves into the deep submicron level, synchronous circuit designs based on a single global clock have incurred problems in such areas as timing closure and power consumption. An asynchronous circuit design methodology is one of the strong candidates to solve such problems. To verify the feasibility and efficiency of a large-scale asynchronous circuit, we design a fully clockless 32-bit processor. We model the processor using an asynchronous HDL and synthesize it using a tool specialized for asynchronous circuits with a top-down design approach. In this paper, two microarchitectures, basic and enhanced, are explored. The results from a pre-layout simulation utilizing 0.13-${\mu}m$ CMOS technology show that the performance and power consumption of the enhanced microarchitecture are respectively improved by 109% and 30% with respect to the basic architecture. Furthermore, the measured power efficiency is about 238 ${\mu}W$/MHz and is comparable to that of a synchronous counterpart.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.5
• /
• pp.321-334
• /
• 2003

Globally-Asynchronous Locally-Synchronous (GALS) systems are worthy of notice as an adequate architecture for a large scaled chip design with guaranteeing easy designs and functional confidence. In this paper, we suggest an advanced structure of the interface unit which is indispensable for GALS systems by using stoppable clocks. The proposed interface unit is composed of a sender module and a receiver module. The sender module can carry out data transmission partially without the relation to an internal clock. We have designed it with 0.25${\mu}{\textrm}{m}$ standard cell library at the gate level and simulated its operation to show performance improvement. Finally, we constructed all example circuit with the interface unit and proved the correct operation of it.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.8
• /
• pp.1735-1740
• /
• 2005

SoC design integrates many IPs that operate at different frequencies and the use of the different clock for each IP makes the design the most effective one. An asynchronous FIFO is required as a kind of a buffer to connect IPs that are asynchronous. However, in many cases, asynchronous FIFO is designed improperly and the cost of the wrong design is high. In this paper, an asynchronous FIFO is designed to transfer data across asynchronous clock domains by using a valid bit scheme that eliminates the problem of the metastability and synchronization altogether. This FIFO architecture is described in HDL and synthesized to the Bate level to compare with other FIFO scheme. The subject mater of this paper is under patent pending.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.1038-1041
• /
• 2005

In today's SoC design, most of IPs which use the different clock frequency from that of the bus require asynchronous FIFOs. However, in many cases, asynchronous FIFO is designed improperly and the cost of the wrong design is high. In this paper, a register-based asynchronous FIFO is designed to transfer data in asynchronous clock domains by using a valid bits scheme that eliminates the problem of the metastability and synchronization altogether. This FIFO architecture is described in HDL and synthesized to the gate level to compare with other FIFO scheme.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.1
• /
• pp.1196-1204
• /
• 2001

In this paper, a new architecture of operating software associated with the component-based method is proposed. The proposed architecture comprises 문 execution module and a decision-making module. In order to make effective development and maintenance, the execution module is divided into three components. The components are referred to as Symbol, Gateway, and Control, respectively: The symbol component is for the GUI environments and the standard interfaces; the gateway component is for the network communication and the structure of asynchronous processes; the control component is for the asynchronous processing and machine setting or operations. In order to verify the proposed architecture, and off-line version of operating software is made, and its steps are as follows; I) Make virtual execution modules for the manufacturing devices such as dual-arm robot, handling robot, CNC, and sensor; ii) Make decision-making module; iii) Integrate the modules and GUI using a well-known development tools such as Microsofts Visual Basic; iv) Execute the overall operating software to validate the proposed architecture. The proposed software architecture in this paper has the advantages such as independent development of each module, easy development of network communication, and distributed processing of resources, and so on.