http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Optimizing Fsync Performance with Dynamic Queue Depth Adaptation
Park, Daejun,Kim, Min Ji,Shin, Dongkun The Institute of Electronics and Information Engin 2015 Journal of semiconductor technology and science Vol.15 No.5
Existing flash storage devices such as universal flash storage and solid state disk support command queuing to improve storage I/O bandwidth. Command queuing allows multiple read/write requests to be pending in a device queue. Because multi-channel and multi-way architecture of flash storage devices can handle multiple requests simultaneously, command queuing is an indispensable technique for utilizing parallel architecture. However, command queuing can be harmful to the latency of fsync system call, which is critical to application responsiveness. We propose a dynamic queue depth adaptation technique, which reduces the queue depth if user application is expected to send fsync calls. Experiments show that the proposed technique reduces the fsync latency by 79% on average compared to the original scheme.
Optimizing Fsync Performance with Dynamic Queue Depth Adaptation
Daejun Park,Min Ji Kim,Dongkun Shin 대한전자공학회 2015 Journal of semiconductor technology and science Vol.15 No.5
Existing flash storage devices such as universal flash storage and solid state disk support command queuing to improve storage I/O bandwidth. Command queuing allows multiple read/write requests to be pending in a device queue. Because multi-channel and multi-way architecture of flash storage devices can handle multiple requests simultaneously, command queuing is an indispensable technique for utilizing parallel architecture. However, command queuing can be harmful to the latency of fsync system call, which is critical to application responsiveness. We propose a dynamic queue depth adaptation technique, which reduces the queue depth if user application is expected to send fsync calls. Experiments show that the proposed technique reduces the fsync latency by 79% on average compared to the original scheme.
Experiment of HDR10 Down/Up-sampling through MATLAB Implementation
Daejun Park,Jechang Jeong 대한전자공학회 2017 대한전자공학회 학술대회 Vol.2017 No.1
As the video industry supports UHD resolution, the discussion of the HDR/WCG technology for realvideo are underway. Many techniques for light intensity and color gamut discussed by experts offer viewers an experience of realness. To encode HDR sequences, HEVC Main10 profile is used after HDR-to- SDR format conversion (i.e. HDR10 process). Through HDR10 process, the conversion from a half float 4:4:4 RGB linear-light format with high bit to 4:2:0 10bits Y’CbCr is obtained. HDR output sequence can be obtained by performing a reverse process, HEVC decoding and SDR-to-HDR format conversion. The loss of image information occurs in the above procedure, especially in Y’CbCr down/up-sampling procedure. In this work, we experimented with different filters to optimize HDR10 down/up-sampling process. We implemented the core techniques of HDR10 in Matlab programming in order to utilize the existing filters. In this paper, the necessity of the filter selection algorithm in down-conversion process is proposed. By presenting the difference between the CIE1931 x’y’ gamut of several filters, we show a variety of problems that can occur in the HDR video compression.
스마트폰의 어플리케이션 업데이트 패턴을 고려한 데이터 중복제거 기법 연구
박대준(Daejun Park),최동수(Dongsoo Choi),신동군(Dongkun Shin) 한국정보과학회 2012 한국정보과학회 학술발표논문집 Vol.39 No.1A
스마트폰의 어플리케이션은 어플리케이션 생태계의 발전에 따라 그 수가 많아지고, 업데이트 또한 잦아졌다. 어플리케이션의 업데이트는 낸드 플래시 메모리에 이전 버전을 삭제하고, 새로운 버전의 어플리케이션에 대한 쓰기 명령을 내린다. 따라서 사용자는 낸드 플래시 메모리에서의 상대적으로 느린 쓰기 명령에 의해 스마트폰의 성능의 저하를 느끼고 낸드 플래시 메모리는 반복되는 지우기/쓰기 동작에 의해 수명이 단축된다. 본 논문에서는 업데이트 되는 스마트폰 어플리케이션 데이터가 이전 버전과 큰 차이가 없다는 것에 착안하여 데이터 중복제거를 통해 업데이트 성능을 향상시키고 낸드 플래시 메모리의 수명을 향상시키는 기법을 제안하고 있으며, 실험을 통해서 어플리케이션들에 대한 중복 제거율을 관찰하였다.