• Proceedings of the KIPE Conference
• /
• 2007.07a
• /
• pp.223-225
• /
• 2007

본 논문에서는 FPGA(Field Programmable Gate Array) 기반의 전류 제어기를 설계하고 구현하였다. 기존의 DSP (Digital Signal Processor) 기반의 전류 제어기는 알고리즘 연산으로 인해 일반적으로 한 샘플링의 디지털 시지연이 발생한다. 반면에, FPGA 기반의 전류제어기는 FPGA의 높은 연산 능력을 이용하여, 알고리즘 연산에 필요한 시간을 감소시킬 수 있다. 이는 시지연이 물리적으로 줄기 때문에, 어떠한 시지연 보상 알고리즘 없이 전류 제어기의 대역폭을 향상시킬 수 있다. 구현된 FPGA 기반의 전류 제어기의 성능은 실험을 통해 검증되었다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2006.07a
• /
• pp.319-319
• /
• 2006

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 1998.12a
• /
• pp.483-493
• /
• 1998

본 논문에서 DES를 대체하기 위해 몇 년에 걸쳐 제안된 관용 암호알고리즘의 하나인 IDEA(International Data Encryption Algorithm)의 구현을 제안하고자 한다. IDEA의 암호화 수행시간의 개선을 위하여 VHDL(VHSIC Hardware Description Language)을 이용하여 하드웨어로 설계하였고 설계된 알고리즘은 EDA tool인 Synopsys를 사용하여 Synthesis하였으며, Xilinx의 FPGA XC4052XL을 이용하여 One Chip화 시켰다. 입력 클럭으로 30MHz를 사용하였을 때, data arrival time은 780.09ns였으며, 80.01 Mbps의 속도로 동작하였다. 본 논문은 설계 언어로서 VHDL을 사용하였고, FPGA Chip에 구현하여 동작 확인을 하였다.

• Journal of IKEEE
• /
• v.19 no.1
• /
• pp.10-17
• /
• 2015

In this Paper, an efficient method of FPGA based design and implementation of Sobel Edge detector block using 3-Line buffers is presented. The FPGA provides the proper and sufficient hardware for image processing algorithms with flexibility to support Sobel edge detection algorithm. A pipe-lined method is used to implement the edge detector. The proposed Sobel edge detection operator is an model using of Finite State Machine(FSM) which executes a matrix mask operation to determine the level of edge intensity through different of pixels on an image. This approach is useful to improve the system performance by taking advantage of efficient look up tables, flip-flop resources on target device. The proposed Sobel detector using 3-line buffers is synthesized with Xilinx ISE 14.2 and implemented on Virtex II xc2vp-30-7-FF896 FPGA device. Using matlab, we show better PSNR performance of proposed design in terms of 3-Line buffers utilization.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.2
• /
• pp.1-12
• /
• 2013

Information Security System is implemented in software, hardware and FPGA device. Implementation of S/W provides high flexibility about various information security algorithm, but it has very vulnerable aspect of speed, power, safety, and performing ASIC is really excellent aspect of speed and power but don't support various security platform because of feature's realization. To improve conflict of these problems, implementation of recent FPGA device is really performed. The goal of this thesis is to design and develop a FPGA hardware accelerator for information security system. It performs as AES, SHA-256 and ECC and is controlled by the Integrated Interface. Furthermore, since the proposed Security Information System can satisfy various requirements and some constraints, it can be applied to numerous information security applications from low-cost applications and high-speed communication systems.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.19-24
• /
• 2020

This paper presents a 3-level, 2-level SVPWM technique with 100 kHz switching using Verilog HDL, one of the languages of FPGA. In the case of IGBT devices mainly used in inverters, they have a switching frequency around 20kHz. Recent research and development of next-generation power semiconductor devices such as GAN has enabled switching of more than 100kHz, which can miniaturize power converters, and apply various new algorithms due to the injection of harmonics. In the existing system using the IGBT, the control using the DSP is common, but the controller configuration for 100 kHz switching requires the use of FPGA. Therefore, this paper explains the theory and implementation of SVPWM applied to two-level and three-level inverters using FPGAs and verifies the performance through the output waveform. In addition, this paper implements 3-level SVPWM by using only one carrier instead of using two carriers in the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.850-858
• /
• 2022

To deploy Gate Recurrent Units (GRU) on resource-constrained embedded devices, this paper presents a reconfigurable FPGA-based GRU accelerator that enables structured compression. Firstly, a dense GRU model is significantly reduced in size by hybrid quantization and structured top-k pruning. Secondly, the energy consumption on external memory access is greatly reduced by the proposed reuse computing pattern. Finally, the accelerator can handle a structured sparse model that benefits from the algorithm-hardware co-design workflows. Moreover, inference tasks can be flexibly performed using all functional dimensions, sequence length, and number of layers. Implemented on the Intel DE1-SoC FPGA, the proposed accelerator achieves 45.01 GOPs in a structured sparse GRU network without batching. Compared to the implementation of CPU and GPU, low-cost FPGA accelerator achieves 57 and 30x improvements in latency, 300 and 23.44x improvements in energy efficiency, respectively. Thus, the proposed accelerator is utilized as an early study of real-time embedded applications, demonstrating the potential for further development in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.237-240
• /
• 2012

This paper describes an implementation of ARIA crypto algorithm which is a KS (Korea Standards) block cipher algorithm. The ARIA crypto-core supports three master key lengths of 128/192/256-bit specified in the standard and the four modes of operation including ECB, CBC, CTR and OFB. To reduce hardware complexity, a hardware sharing is employed, which shares round function in encryption/decryption module with key initialization module. The ARIA crypto-core is verified by FPGA implementation, the estimated throughput is about 1.07 Gbps at 167 MHz.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1527-1539
• /
• 2015

In this paper the hardware implementation of the direct torque control based on the fuzzy logic technique of induction motor on the Field-Programmable Gate Array (FPGA) is presented. Due to its complexity, the fuzzy logic technique implemented on a digital system like the DSP (Digital Signal Processor) and microcontroller is characterized by a calculating delay. This delay is due to the processing speed which depends on the system complexity. The limitation of these solutions is inevitable. To solve this problem, an alternative digital solution is used, based on the FPGA, which is characterized by a fast processing speed, to take the advantage of the performances of the fuzzy logic technique in spite of its complex computation. The Conventional Direct Torque Control (CDTC) of the induction machine faces problems, like the high stator flux, electromagnetic torque ripples, and stator current distortions. To overcome the CDTC problems many methods are used such as the space vector modulation which is sensitive to the parameters variations of the machine, the increase in the switches inverter number which increases the cost of the inverter, and the artificial intelligence. In this paper an intelligent technique based on the fuzzy logic is used because it is allows controlling the systems without knowing the mathematical model. Also, we use a new method based on the Xilinx system generator for the hardware implementation of Direct Torque Fuzzy Control (DTFC) on the FPGA. The simulation results of the DTFC are compared to those of the CDTC. The comparison results illustrate the reduction in the torque and stator flux ripples of the DTFC and show the Xilinx Virtex V FPGA performances in terms of execution time.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.38 no.1
• /
• pp.69-78
• /
• 2001

This paper presents the design and FPGA implementation of a FLEX PSP(Protocol Signal Processor) for the portable high speed paging system. In this approach, two algorithms are newly proposed for implementing the PSP which provides capabilities of the maximum 6,400bps at speed, high-channel throughput, real time error correction and an effective frame search function. One is an accurate symbol synchronization algorithm which is applied for synchronizing the interleaved 4-level bit symbols which are received at input stage of A/D converter, and the other is a modified fast decoding algorithm which is provided for realizing double error correction of (31,21)BCH signal. The PSP is composed of six functional modules, and each module is modelled in VHDL(VHSIC Hardware Description Language). Both functional simulation and logic synthesis have performed for the proposed PSP through the use of Synopsys$^{TM}$ tools on a Axil-320 Workstation, and where Altera 10K libraries are used for logic synthesis. From logic synthesis, we can see that the number of gates is about 2,631. For FPGA implementation, timing simulation is performed by using Altera MAX+ PLUS II, and its results will be also given. The PSP which is implemented in 6 FPGA devices on a PCB has been verified by means of Logic Analyzer.r.