• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.426-432
• /
• 2001

This paper is implementation of cellular automata neural network system using evolving hardware concept. This system is a living creatures'brain based on artificial life techniques. Cellular automata neural network system is based on the development and the evolution, in other words, it is modeled on the ontogeny and phylogney of natural living things. The phylogenetic mechanism are fundamentally non-deterministic, with the mutation and recombination rate providing a major source of diversity. Ontogeny is deterministic and local physics. Cellular automata is developed from initial cells, and evaluated in given environment. And genetic algorithms take a part in adaptation process. In this paper we implement this system using evolving hardware concept. Evolving hardware is reconfigurable hardware whose configuration si under the control of an evolutionary algorithm. We design genetic algorithm process for evolutionary algorithm and cells in cellular automata neural network for the construction of reconfigurable system. The effectiveness of the proposed system if verified by applying it to Exclusive-OR.

• Journal of Power Electronics
• /
• v.17 no.1
• /
• pp.56-66
• /
• 2017

Fast and accurate fault detection is the primary step and one of the most important tasks in fault tolerant converters. In this paper, a fast and simple method is proposed to detect and diagnosis the faulty cell in a cascaded H-bridge multilevel inverter under a short circuit fault. In this method, the reference voltage is calculated using switching control pulses and DC-Link voltages. The comparison result of the output voltage and the reference voltage is used in conjunction with active cell pulses to detect the faulty cell. To achieve this goal, the cell which is active when the Fault signal turns to "0" is detected as the faulty cell. Furthermore, consideration of generating the active cell pulses is completely described. Since the main advantage of this method is its simplicity, it can be easily implemented in a programmable digital device. Experimental results obtained with an 11-level inverter prototype confirm the effectiveness of the proposed fault detection technique. In addition, they show that the diagnosis method is unaffected by variations of the modulation index.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.2
• /
• pp.24-30
• /
• 2009

In this paper, the FPGA modem platform complying with 3GPP Release 7 eHSPA specifications and its regularized verification flow are proposed. The FFGA platform consists of modem board supporting physical layer requirements, MCU and DSP core embedded control board to drive the modem board, and peripheral boards for RF interfacing and various equipment interfaces. On the other hand, the proposed verification flow has been regularized into three categories according to the correlation degrees of hardware-software inter-operation, such as simple function test, scenario test call processing and system-level performance test. When it comes to real implementations, the emulation verification strategy for low power mobile SoC is also introduced.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1321-1327
• /
• 2019

This paper describes an efficient hardware implementation of modular square root (MSQR) computation over GF(p), which is the operation needed to map plaintext messages to points on elliptic curves for elliptic curve (EC)-ElGamal public-key encryption. Our method supports five sizes of elliptic curves over GF(p) defined by the National Institute of Standards and Technology (NIST) standard. For the Koblitz curves and the pseudorandom curves with 192-bit, 256-bit, 384-bit and 521-bit, the Euler's Criterion based on the characteristic of the modulo values was applied. For the elliptic curves with 224-bit, the Tonelli-Shanks algorithm was simplified and applied to compute MSQR. The proposed method was implemented using the finite field arithmetic circuit with 32-bit datapath and memory block of elliptic curve cryptography (ECC) processor, and its hardware operation was verified by implementing it on the Virtex-5 field programmable gate array (FPGA) device. When the implemented circuit operates with a 50 MHz clock, the computation of MSQR takes about 18 ms for 224-bit pseudorandom curves and about 4 ms for 256-bit Koblitz curves.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.6
• /
• pp.459-468
• /
• 2003

This paper proposes a novel low-cost and high-speed Reed-Solomon (RS) decoder based on a new degree computationless modified Euclid´s (DCME) algorithm. This architecture has quite low hardware complexity compared with conventional modified Euclid´s (ME) architectures, since it can remove completely the degree computation and comparison circuits. The architecture employing a systolic away requires only the latency of 2t clock cycles to solve the key equation without initial latency. In addition, the DCME architecture using 3t＋2 basic cells has regularity and scalability since it uses only one processing element. The RS decoder has been synthesized using the 0.25${\mu}{\textrm}{m}$. Faraday CMOS standard cell library and operates at 200MHz and its data rate suppots up to 1.6Gbps. For tile (255, 239, 8) RS code, the gate counts of the DCME architecture and the whole RS decoder excluding FIFO memory are only 21,760 and 42,213, respectively. The proposed RS decoder can reduce the total fate count at least 23% and the total latency at least 10% compared with conventional ME architectures.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.24-35
• /
• 2018

Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2014.02a
• /
• pp.307-307
• /
• 2014

정보화 시대로 접어들면서 동일한 공간에 더 많은 정보를 저장할 수 있고, 보다 빠른 동작이 가능한 비휘발성 메모리 소자에 대한 요구가 증가하고 있다. 하지만, 최근 비휘발성 메모리 소자 관련 연구보고에 따르면, 메모리 소자의 소형화 및 직접화 측면에서, 전하 저장을 기반으로 하는 기존의 Floating-Gate(FG) Flash 메모리는 20 nm 이하 공정에서 한계가 예측 되고 있다. 따라서, 이러한 FG Flash 메모리의 한계를 해결하기 위해, 기존에 FET 기반의 FG Flash 구조와 같은 3 terminal이 아닌, Diode와 같은 2 terminal로 동작이 가능한 ReRAM, PRAM, STT-MRAM, PoRAM 등 저항변화를 기반으로 하는 다양한 종류의 차세대 메모리 소자가 연구되고 있다. 그 중, 저항 변화 메모리(ReRAM)는 CMOS 공정 호환성, 3D 직접도, 낮은 소비전력과 빠른 동작 속도 등의 우수한 동작 특성을 가져 차세대 비휘발성 메모리로 주목을 받고 있다. 또한, 상하부 전극의 2 terminal 만으로 소자 구동이 가능하기 때문에 Passive Crossbar-Array(CBA)로 적용하여 플래시 메모리를 대체할 수 있는 유력한 차세대 메모리 소자이다. 하지만, 이를 현실화하기 위해서는 Passive CBA 구조에서 발생할 수 있는 Read Disturb 현상, 즉 Word-Line과 Bit-Line을 통해 선택된 소자를 제외하고 주변의 다른 소자를 통해 흐르는 Sneak Leakage Current(SLC)를 차단하여 소자의 메모리 State를 정확히 sensing하기 위한 연구가 선행 되어야 한다. 따라서, 현재 이러한 이슈를 해결하기 위해서, 많은 연구 그룹에서 Diodes, Threshold Switches와 같은 ReRAM에 Selector 소자를 추가하는 방법, 또는 Self-Rectifying 특성 및 CRS 특성을 보이는 ReRAM 구조를 제안 하여 SLC를 차단하고자 하는 연구가 시도 되고 있지만, 아직까지 기초연구 단계로서 아이디어에 대한 가능성 정도만 보고되고 있는 현실 이다. 이에 본 논문은 Passive CBA구조에서 발생하는 SLC를 해결하기 위한 새로운 아이디어로써, 본 연구 그룹에서 선행 연구로 확보된 안정적인 저항변화 물질인 SiN를 정류 특성을 가지는 n-Si/Ti 기반의 Schottky Diode와 결합함으로써 기존의 CBA 메모리의 Read 동작에서 발생하는 SLC를 차단 할 수 있는 1SD-1R 구조의 메모리 구조를 제작 하였으며, 본 연구 결과 기존에 문제가 되었던 SLC를 차단 할 수 있었다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.10
• /
• pp.89-96
• /
• 2003

In this paper, a CCSDS(Consultative Committee for Space Data Systems) telecommand(TC) decryptor for the security of geostationary communications satellite was implemented. For the confidentiality of CCSDS TC datalink security, Option-A which implements the security services below the transfer sublayer was selected. Also CFB(Cipher Feedback) operation mode of DES(Data Encryption Standard) was used for the encryption of 56-bit data bits in 64-bit codeblock. To verify Decryptor function, the DES CFB logic implemented on A54SX32 FPGA(Field Programmable Gate Array) was integrated with interface and control logics in a PCB(Printed Circuit Board). Using a function test PC, the encrypted codeblocks were generated, transferred into the decryptor, decrypted, and the decrypted codeblocks were transmitted to the function test PC, and then compared with the source codeblocks. Through LED(Light Emitting Diode) ON operation by driving the relay related to Op-code decoded and the comparison between the codeblock output waveforms measured and those simulated, the telecommand decryptor function was verified.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.1
• /
• pp.110-115
• /
• 2006

STSAT-2 is the first satellite which will be launched by the first Korean Space Launch Vehicle(KSLV). Ground station Baseband Control system(GBC) is now developed for STSAT-2. GBC has two functions. One is control data path between satellite control computers and ground station antennas(1.5M, 3.7M, 13M) automatically. The other is sending and receiving data between ground station and satellite. GBC is implemented by FPGA(Field-Programmable Gate Array) which includes almost all logic(for MODEM, PROTOCOL and GBC system control). MODEM in GBC has two uplink FSK modulators(1.2[kbps], 9.6[kbps]) and six downlink FSK demodulators(9.6[kbps], 38.4[kbps]). In hardware, STSAT-2 GBC is smaller than STSAT-1 GBC. In function, STSAT-2 GBC has more features than STSAT-1 GBC. This paper is about GBC structure, functions and test results.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.9
• /
• pp.789-794
• /
• 2014

The FPGA is used to the high speed digital satellite communication on the Digital Signal Process Unit of the next generation GEO communication satellite. The high capacity FPGA has the high power dissipation and it is difficult to satisfy the derating requirement of temperature. This matter is the major factor to degrade the equipment life and reliability. The thermal control at the equipment level has been worked through thermal conduction in the space environment. The FPGA of CCGA or BGA package type was mounted on printed circuit board, but the PCB has low efficient to the thermal control. For the FPGA heat dissipation, the heat sink was applied between part lid and housing of equipment and the performance of heat sink was confirmed via thermal vacuum test under the condition of space qualification level. The FPGA of high power dissipation has been difficult to apply for space application, but FPGA with heat sink could be used to space application with the derating temperature margin.