• Journal of Semiconductor Engineering
• /
• 제2권3호
• /
• pp.142-153
• /
• 2021

Recent research on synaptic devices has been reviewed from the perspective of hardware-based neuromorphic computing. In addition, the backgrounds of neuromorphic computing and two training methods for hardware-based neuromorphic computing are described in detail. Moreover, two types of memristor- and CMOS-based synaptic devices were compared in terms of both the required performance metrics and low-power applications. Based on a review of recent studies, additional power-scalable synaptic devices such as tunnel field-effect transistors are suggested for a plausible candidate for neuromorphic applications.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2004년도 춘계 학술발표대회 논문집
• /
• pp.290-291
• /
• 2004

• 한국IT서비스학회지
• /
• 제5권1호
• /
• pp.47-59
• /
• 2006

According to the policy for "e-Korea construction" of Korean government, Investment of information system during the past decade are dramatically increasing. More than a half of this investment is cost of hardware infrastructure. So, accurate hardware sizing are essential for higher efficiency of investment. Accurate hardware sizing benefits are generally viewed in terms of the avoidance of excess equipment and lost opportunity costs by not being able to support business needs. Unfortunately, however, little research effort to make the hardware sizing methodology are doing. We propose a sizing method for information system in public sector. This method is determinate empirical study that are gathering and analyzing cases, making method and reviewing expert. Finally we are proposed calculating method for hardware components that is CPU, memory, internal and external disk according to the application system type which is OLTP, Web, WAS. Our study certainly will act as a catalyst for higher investment-efficiency of the future information programs in public sector.

• 한국정보전자통신기술학회논문지
• /
• 제10권2호
• /
• pp.141-146
• /
• 2017

본 논문에서는 저전력 영상 특징 추출 하드웨어 설계를 위한 하드웨어 폴딩 기법 기반 저면적 Gradient magnitude 연산기 구조를 제안한다. 하드웨어 복잡도를 줄이기 위해 Gradient magnitude 벡터의 특징을 분석하여 기존 알고리즘을 하드웨어를 공유하여 사용할 수 있는 알고리즘으로 변경하여 Folding 구조가 적용될 수 있도록 했다. 제안된 하드웨어 구조는 기존 알고리즘의 특징을 최대한 이용했기 때문에 데이터 품질의 열화가 거의 없이 구현될 수 있다. 제안된 하드웨어 구조는 Altera Quartus II v16.0 환경에서 Altera Cyclone VI (EP4CE115F29C7N) FPGA를 이용하여 구현되었다. 구현 결과, 기존 하드웨어 구조를 이용하여 구현한 연산기와의 비교에서 41%의 logic elements, 62%의 embedded multiplier 절감 효과가 있음을 확인했다.

• International Journal of Advanced Culture Technology
• /
• 제4권4호
• /
• pp.30-37
• /
• 2016

In this paper, the method of controlling the clock that is inputted on the hardware from the application, and the hardware design method are to be proposed. When the hardware is synthesized to the Field Programmable Gate Array(FPGA), the input clock is fixed, and when the input clock is changed, the synthesis process must be passed again to require more time. To solve this problem, the Mixed-Mode Clock Manager(MMCM) module is mounted to control the MMCM module from the application. The controlled MMCM module controls the input clock of the module. The experiment was process the Neural Network algorithm in the x86 CPU and SIMT based processor mounted the FPGA. The results of the experiment, SIMT-based processors, the time that is processed at a frequency of 50MHz was 77ms, 100MHz was 34ms. There was no additional synthesis time due to a change of the clock frequency.

• Journal of Information Processing Systems
• /
• 제9권3호
• /
• pp.499-510
• /
• 2013

Hardware-Software co-simulation of a multiple image encryption technique shall be described in this paper. Our proposed multiple image encryption technique is based on the Latin Square Image Cipher (LSIC). First, a carrier image that is based on the Latin Square is generated by using 256-bits of length key. The XOR operation is applied between an input image and the Latin Square Image to generate an encrypted image. Then, the XOR operation is applied between the encrypted image and the second input image to encrypt the second image. This process is continues until the nth input image is encrypted. We achieved hardware co-simulation of the proposed multiple image encryption technique by using the Xilinx System Generator (XSG). This encryption technique is modeled using Simulink and XSG Block set and synthesized onto Virtex 2 pro FPGA device. We validated our proposed technique by using the hardware software co-simulation method.

• 전기전자학회논문지
• /
• 제17권2호
• /
• pp.202-207
• /
• 2013

본 논문은 기존의 FAST와 BRIEF 알고리즘을 Zynq-7000 Soc Platform에서 하드웨어로 구현했다. 대표적으로 SIFT 나 SURF 알고리즘을 사용하여 특징점 기반 하드웨어 가속기로 구현 하지만, 하드웨어 비용과 내부 메모리가 많이 필요하다. 제안하는 FAST & BRIEF 가속기는 기존의 SIFT 나 SURF 가속기 보다 내부 메모리 사용량을 약 57%, 하드웨어 비용을 약 70% 정도 감소하고, 수행 시간은 Clock 당 0.17 Pixel를 처리한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 추계학술발표대회
• /
• pp.42-45
• /
• 2012

A network processor (NP) is an application-specific instruction-set processor for fast and efficient packet processing. There are many issues in compiler's code generation and optimization due to NP's hardware constraints and special hardware support. In this paper, we describe in detail how to resolve the issues. Our compiler was developed on LLVM 3.0 and the NP target was our in-house network processor which consists of 32 64-bit RISC processors and supports multi-context with special hardware structures. Our compiler incurs only 9.36% code size overhead over hand-written code while satisfying QoS, and the generated code was tested on a real packet processing hardware, called S20 for code verification and performance evaluation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권4호
• /
• pp.1146-1165
• /
• 2022

A huge amount of data in the form of videos and images is being produced owning to advancements in sensor technology. Use of low performance commodity hardware coupled with resource heavy image processing and analyzing approaches to infer and extract actionable insights from this data poses a bottleneck for timely decision making. Current approach of GPU assisted and cloud-based architecture video analysis techniques give significant performance gain, but its usage is constrained by financial considerations and extremely complex architecture level details. In this paper we propose a data pipeline system that uses open-source tools such as Apache Spark, Kafka and OpenCV running over commodity hardware for video stream processing and image processing in a distributed environment. Experimental results show that our proposed approach eliminates the need of GPU based hardware and cloud computing infrastructure to achieve efficient video steam processing for face detection with increased throughput, scalability and better performance.

• 전자통신동향분석
• /
• 제38권5호
• /
• pp.12-22
• /
• 2023

The development of neural networks is evolving towards the adoption of transformer structures with attention modules. Hence, active research focused on extending the concept of lightweight neural network algorithms and hardware acceleration is being conducted for the transition from conventional convolutional neural networks to transformer-based networks. We present a survey of state-of-the-art research on lightweight neural network algorithms and hardware architectures to reduce memory usage and accelerate both inference and training. To describe the corresponding trends, we review recent studies on token pruning, quantization, and architecture tuning for the vision transformer. In addition, we present a hardware architecture that incorporates lightweight algorithms into artificial intelligence processors to accelerate processing.