• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 춘계학술대회
• /
• pp.712-713
• /
• 2011

본 논문에서는 파이프라인 구조의 연산회로를 효율적으로 검증하기 위한 AMBA AXI Slave 하드웨어 구조를 제안하고, 설계 예로 파이프라인 곱셈기를 내장한 구조를 제시하였다. 제안한 AXI Slave 회로는 입출력 버퍼 블록 메모리, 제어용 레지스터, 파이프라인 구조 연산 회로, 파이프라인 제어회로, AXI 버스 슬레이브 인터페이스로 구성된다. 주요 동작 과정은 입력 버퍼 메모리와 외부 마스터 사이의 버스트 데이터 전송, 제어 레지스터에 동작 모드 설정, 입력 버퍼 메모리에 담긴 데이터에 대한 반복적인 파이프라인 연산회로 동작, 출력 버퍼 메모리에 담긴 출력 데이터와 외부 마스터 사이의 버스트 데이터 전송으로 나누어진다. 제안한 AXI slave 구조는 범용 인터페이스 구조를 갖고 있으므로 파이프라인 구조 구조의 연산회로를 내장한 AMBA AHB와 AXI slave에 응용이 가능하다.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 2004년도 추계종합학술대회 논문 초록집
• /
• pp.225-225
• /
• 2004

• 한국정보통신학회논문지
• /
• 제8권3호
• /
• pp.570-576
• /
• 2004

본 논문에서는 고속 무선 LAN에서 사용하는 IEEE 802.11a OFDM(Orthogonal Frequency Division Multiplexing)에서 주요 구성인 IFFT/FFT(Inverse Fast Fourier Transform/Fast Fourier Transform)에 대한 설계에 대해 비교하였다. 설계된 IFFT/FFT는 무선 LAN의 표준에 맞게 64 point의 FFT로 연산을 수행하며, S/P(Serial-to-Parallel)이나 P/S(Parallel-to-Serial)변환기가 필요 없는 Pipelined FFT의 구조로 설계하였다. 그 중 Radix-2 알고리즘을 이용한 R22SDF(Radix-2 Single-path Delay Feedback) 방식, R2SDF(Radix-2 Single-path Delay Feedback) 방식과 Radix-4 알고리즘을 이용한 R4SDF(Radix-4 Single-path Delay Feedback) 방식, R4SDC(Radix-4 Single-path Delay Commutator) 방식을 사용하여 비교하였다. 하드웨어 구현 시 발생하는 오차를 줄이기 위해 Butterfly 연산 후 일부 소수점을 가지고 계산하는 구조로 설계하였다. R22SDF 방식을 이용할 경우 메모리를 제외한 전체 게이트 수가 44,747 개로 다른 구조에 비해 적은 하드웨어와 낮은 오차율을 가진다.

• 전자공학회논문지A
• /
• 제31A권3호
• /
• pp.18-27
• /
• 1994

An 8-bit 2-stage pipelined current mode A/D converter is designed with a new architecture, where the wideband track-and-hold amplifiers which have 2 integrators in parallel sample input signal twice per clock cycle. The conversion speed of the A-D converter is two times faster than that of conventional pipelined method. The converter is designed to be operated at the power supply voltage of 3.3V with the input dynamic range of 0-256$\mu$A. HSPICE simulation results show the performance of up to 55Msamples/s and power consumption of 150mW with the parameters of ISRC $1.5\mu$m BICMOS process. The chip area is 3${\times}4mm^{2}$.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 하계종합학술대회 논문집(1)
• /
• pp.7-10
• /
• 2004

This paper describes techniques to implement low-cost adapt ive Pipelined LMS filter for ASIC implement ions of high communication receivers. Power consumpiton can be reduced using a careful selection of architectural, algorithmic, and VLSI circuit techlifue A Pipelined architecture for the strength-reduced algorithm is then developed via the relaxed look-ahead transformation. This technique, which is an approximation of the conventional look-ahead compution, maintains the functionality of the algorithm rather than the input-output behavior Convergence maiysis of the Proposed architecture has been presented and support via simulation results. The resulting pipelined adaptive filter achives a higher though put requires lower power as compared to the filter using the serial algorithm.

• Journal of Information Processing Systems
• /
• 제15권2호
• /
• pp.374-385
• /
• 2019

This paper presents an optimal implementation of a Daubechies-based pipelined discrete wavelet packet transform (DWPT) processor using finite impulse response (FIR) filter banks. The feed-forward pipelined (FFP) architecture is exploited for implementation of the DWPT on the field-programmable gate array (FPGA). The proposed DWPT is based on an efficient transpose form structure, thereby reducing its computational complexity by half of the system. Moreover, the efficiency of the design is further improved by using a canonical-signed digit-based binary expression (CSDBE) and advanced functional sharing (AFS) methods. In this work, the AFS technique is proposed to optimize the convolution of FIR filter banks for DWPT decomposition, which reduces the hardware resource utilization by not requiring any embedded digital signal processing (DSP) blocks. The proposed AFS and CSDBE-based DWPT system is embedded on the Virtex-7 FPGA board for testing. The proposed design is implemented as an intellectual property (IP) logic core that can easily be integrated into DSP systems for sub-band analysis. The achieved results conclude that the proposed method is very efficient in improving hardware resource utilization while maintaining accuracy of the result of DWPT.

• 전자공학회논문지A
• /
• 제31A권3호
• /
• pp.53-67
• /
• 1994

This paper describes the design of a high-level synthesis system. SODAS-VP. which automatically generates hardwares executing operation sequences in pipelined fashion.Target architecture and clocking schemes to drive pipelined datapath are determined, and the handling of pipeline hazards which degrade the performance of pipeline is considered. Partitioning of an operation into load, operation, and store stages, each of which is executed in partitiones control step, is performend. Pipelinecl hardware is generated by handling pipeline hazards with internal forwarding or delay insertion techniques in partitioning process and resolving resource conflicts among the partitioned control steps with similarity measure as a priority function in module allocation process. Experimental results show that SODAS-VP generates hardwares that execute faster than those generated by HAL and ALPS systems. SODAS-VP brings improvement in execution speed by 17.1% and 7.4% comparing with HAL and ALPS systems for a MCNC benchmark program, 5th order elliptical wave filter,respectively.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.837-840
• /
• 2005

This paper presents 3D graphics lighting processor based on vector processing using pipeline chaining. The lighting process of 3D graphics rendering contains many arithmetic operations and its complexity is very high. For high throughput, proposed processor uses pipelined functional units. To implement fully pipelined architecture, we have to use many functional units. Hence, the number of functional units is restricted. However, with the restricted number of pipelined functional units, the utilization of the units is reduced and a resource reservation problem is caused. To resolve these problems, the proposed architecture uses vector processing using pipeline chaining. Due to its pipeline chaining based architecture, it can perform 4.09M vertices per 1 second with 100MHz frequency. The proposed 3D graphics lighting processor is compatible with OpenGL ES API and the design is implemented and verified on FPGA.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.63-66
• /
• 1999

Echo and near-end crosstalk(NEXT) can be generated in two-wire duplex transmission. In this paper investigates how to cancel echoes of high speed communication. A pipeline algorithm is used to remove the echoes that high speed communication. It is least mean squared(LMS) algorithm based on the relaxed look-ahead concept, is focused on the pipelined LMS, and its performance is compared to that of the serial LMS algorithm. And we design pipelined adaptive filtering. In advanced of the hardware implementation with VHDL code the performance of pipelined LMS algorithm is verified by the computer simulation.

• 인터넷정보학회논문지
• /
• 제7권1호
• /
• pp.49-57
• /
• 2006

본 논문에서는 128-bit 블록암호인 SEED 알고리즘을 하드웨어로 구현하는데 있어서 면적을 줄이고 연산속도를 증가시키는 회로구조에 대하여 논하였고 설계결과를 기술하였다. 연산속도를 증가시키기 위해 pipelined systolic array 구조를 사용하였으며, 입출력회로에 어떤 버퍼도 사용하지 않는 간단한 구조이다. 이 회로는 10 MHz 클럭을 사용하여 최대 320 Mbps의 암호화속도를 달성할 수 있다. 회로설계는 VHDL 코딩방식으로 수행하였으며, 50,000 gates 급의 FPGA에 구현하였다.