• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1161-1164
• /
• 1998

We designed a DSP core simulator with C language, that is able to simulate 5-stage pipelined DSP core, named YS-DSP. It can emulate all 5 stage pipelines in the DSP core. It can also emulate memory access, exception processing, and DSP parallel processing. Each pipeline stage is implemented by combination of one or more functions to process parts of each stage. After modeling and validating the simulator, we can use it to verify and to complement the DSP core HDL model and to enhance its performance.

• KSCI Review
• /
• v.8 no.2
• /
• pp.24-32
• /
• 2001

본 연구에서는 VHDL을 이용하여 16-비트의 파이프라인 SIC를 함수적 레벨에서 기술하여 구현하고. 그 프로세서의 동작을 확인하였다. 구현된 파이프라인 SIC를 시뮬레이션할 때 그 프로세서 내에서 실행되는 테스트 벡터를 기호로 표시된 명령어로 먼저 설정하여 규정하고, 구현된 명령어 세트를 프로그래밍하여 입력하였다. 따라서 본 연구에서 제시된 테스트 벡터를 이용한 시뮬에이션 방법은 프로세서의 동작을 쉽게 확인할 수 있었으며, 정확한 시뮬레이션을 할 수 있었고, VHDL을 이용하므로써 구현시 프로세서의 동작을 문서화하는 것이 간편하였다.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1280-1283
• /
• 2002

This paper discusses issues in VLSI design and implementation of high performance datapath circuits. Of particular concern will he various types of multiplier and adder, which are fundamental to DSP operations. Performance comparison will be provided in terms of sampling speed, layout area, and in particular, power consumption, with techniques that may be applied to reduce power dissipation also suggested. As an example, a low power, high performance recursive filter achieved through bit-level pipelining technique is illustrated

• Proceedings of the IEEK Conference
• /
• 2003.07b
• /
• pp.835-838
• /
• 2003

본 논문에서는 현재 MPEG, JPEG 압축 알고리즘에서 쓰이는 DCT(Discrete Cosine Transform)기반의 손실 영상 압축에 사용되는 양자화(Quantization) 처리에 필요한 나눗셈 연산기를 제안한다. 영상 데이터 처리를 위한 양자화기(Quantizer)는 DCT로부터 매 사이클마다 영상 데이터를 입력 받아 양자화 처리를 해야하며 보다 나은 영상 데이터를 위해 최종 나눗셈 결과 즉, 몫을 소수 첫째자리에서 반올림(Rounding)해야 한다. 이를 위해 반올림 동작이 추가된 Pipelined Nonrestoring Array Divider를 설계하였다. 제안된 방법의 타당성을 검증하기 위해 DCT로부터 나온 영상 데이터를 제안된 구조의 양자화기로 양자화하여 일반 양자화기에서 나온 압축된 데이터와 비교해 보았다. 또한 합성기(Synthesis)를 통하여 실제 하드웨어 크기를 분석하였다.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.12
• /
• pp.122-134
• /
• 1994

Design of a heuristic algorithm for high level synthesis of multichip architecture is presented in this paper. Considering the design constraints: individual chip area, I/O pin counts, chip-to-chip interconnection counts, interchip communication delay, and chip latecy, the proposed system automatically generates pipelined multichip architectures from behavioral descriptions. For efficient mulichip synthesis, a new methodology is proposed, which performs partitioning and schedulting of SFG into multichip architectures simultaneously. Experimental results for several benchmark programs show that the systems can be used for designing multichip hardware efficiently.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.9
• /
• pp.10-21
• /
• 1997

In this paper, we propose multiple instruction issuable multi-streaming as a processor architecture for 3D graphics processor. Multistreaming can eliminate inteferences within concurrently executing instructions inthe pipelined processor to allow enough parallelism for parallel processing. Through cycle level simulation study, we show that the proposed architecture outperforms a conventional RISC processor, MIPS R3000 by three times with reasonable resource overheads. Multiple instruction issuable multistreaming processor will be a bood architecture for instruction processor when a large number of threads are guaranteed.

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.285-288
• /
• 2001

In this paper a design of cryptographic coprocessor which implements AES Rijndael algorithm is described. To achieve average throughput of 1 round per 5 clocks, subround pipelined scheme is applied. To apply the coprocessor to various applications, three key sizes such as 128, 192, 256 bits are supported. The cryptographic coprocessor is designed using 0.25${\mu}{\textrm}{m}$ CMOS technology and consists of about 36, 000 gates. Its peak performance is about 512 Mbps encryption or decryption rate under 200 Mhz clock frequency and 128-bit key ECB mode(AES-128ECB).

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.5
• /
• pp.25-32
• /
• 1998

In this paper, SA (shape adaptive)-DCT is implemented using a datapath with 4 MACs (multiplication & accumulator). DCT is a well-known bottleneck of real-time video compression using MPEG-like schemes. High-speed pipelined MACs presented here implement real-time DCT. A datapath in this paper executes DCT/IDCT algorithms for QCIF 15fps(frame per second), maximum rate of VLBV(very low bitrte video) in MPEG-4. A 32bit accumulator in a MAC prevents distortion caused by fixed-point process. It can be applied to various operations such as ME (motion estimation) and MC(motion compensation) with a absolutor and a halfer.

• Journal of Biomedical Engineering Research
• /
• v.9 no.1
• /
• pp.87-92
• /
• 1988

In this paper, a new focusing method, to be called the pipelined sampled delay focusing (PSDF), is implemented. This method improves the lateral resolution in ultrasound imaging system. In PSDF, the analog belay lines are no longer necessary because sampling sum process can replace the conventional delay sum process. Also, the method offers continuous dynamic focusing on the resolution pixel basis, and eliminates the constraint that the maximum delay time is less than the sampling interval. Second order sampling is adopted in order to extend the sampling interval.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10c
• /
• pp.46-48
• /
• 2001

본 논문에서는 Baugh-Wooley 승산 알고리즘을 '8x8-bit 15 stage 파이프라인 배열 숭산기', '8x8-bit 2 stage 파이프라인 배열 숭산기', '순수 조합 논리 배열 승산기'의 방식으로 FPGA상에서 구현하였으며, 각 구현방식의 성능을 비교 분석하였다.