824 research outputs found
Understanding the Performance Characteristics of Computational Storage Drives: A Case Study with SmartSSD
No full textThe emerging computational storage drives (CSDs) provide new opportunities by moving data computation closer to the storage. Performing computation within storage drives enables data pre/post-processing without expensive data transfers. Moreover, large amounts of data can be processed in parallel thanks to the nature of the field-programmable gate array (FPGA) included in CSDs. In a CSD, there are several implementation techniques that support parallel processing, each of which provides a different degree of parallelism. However, without sufficient understanding of the parallel processing techniques of CSD, it can lead to overhead due to misuse rather than benefiting from task offloading. Thus, to exploit the best performance of CSDs, it is important to properly adjust the degree of parallelism of each implementation technique. In this paper, we focus on the study of the differences in CSD performance according to various combinations of parallel processing techniques. To investigate the performance differences, we implement and offload the data verification algorithm to the CSD and analyze the performance and resource utilization. The experimental results show that implementing the data verification algorithm with a sufficient understanding of CSD's parallel processing techniques can improve the performance by up to 20 times. Moreover, even with the same degree of parallelism, the performance can differ by 59% depending on the combination of implementation techniques. These results imply that proper orchestration of different implementation techniques leads to better performance and efficient resource utilization.N
Data for: DOSE COEFFICIENTS OF MESH-TYPE ICRP REFERENCE COMPUTATIONAL PHANTOMS FOR EXTERNAL EXPOSURES OF NEUTRONS, PROTONS, AND HELIUM IONS
No full textA comprehensive set of dose coefficients for external exposures of neutrons, protons, and helium ions, which were produced by conducing Monte Carlo particle transport simulations with the adult male and female mesh-type ICRP reference computational phantom
The City Image in Yeom Sang Seobs Novels
No full text이 글은 식민지시기 염상섭 소설이 재현하고 있는 도시 이미지의 총체성을 분석하는 것을 목적으로 한다. 염상섭은 서울 토박이 작가로서, 경성 도시공간을 적극적으로 활용하는 소설을 다수 남겼다. 사랑과 죄, 광분, 삼대, 무화과등의 장편소설은 경성 전역을 배경으로 하여, 도시공간의 입체적 면모를 보여주고 있다. 우선 염상섭은 인종적으로 분할되어 있는 심상지리를 넘어 실제적
인 경성 이미지를 그렸다. 그는 일본인 거주지역인 남촌, 조선인 거주지역인 북촌이라는 공간분할에 매이지 않고, 북촌 속에 존재하는 일본인, 그리고 남촌 속에 존재하는 조선인 등(심상지리적 차원에서) 타자의 공간에 진입한 인물들을 묘사했다. 이를 통해 경성이 지니고 있는 본래의 복잡성을 바르게 표현할 수 있었다. 그리고 염상섭은 서로 다른 두 계급을 연애관계를 통해 연결시킴으로써, 서로 다른 사회적 공간들을 전체적으로 포착했다. 그는 계급적인 격차를 지리적인 거리로 환산시키는 수법을 사용했다. 이때 계급적⋅신분적인 격차를 지닌 연인들은, 지리적으로도 멀리 떨어져 있는 것으로 표현되었다. 즉 염상섭은 멀리 떨어져 있는 계급을 연결시킴으로써, 멀리 떨어져 있는 사회적 공간들을 전체적으로 묘사했다. 이를 통해 염상섭은 도시의 총체성을 재현하는 데 성공할 수 있었다. 이는 염상섭이 도시의 여러 장소들을 더 많이, 더 빈번하게 다루었다는 의미에 국한되지 않는다. 염상섭은 도시의 일부, 혹은 파편(fragment)을 넘어서, 도시의 총체성(totality)를 재현하는 데 성공했다. 지도를 활용하는 문학지리(literary geography)의 방법을 사용하여 이를 증명하도록 하겠다.This paper aims to analyze the totality of the city image presented in Yeom Sang Seobs novels. Yeom, as a Seoul born author, wrote a number of work depicting various city areas in Seoul. Love and Sin, Rampage, The Three Generations, and Fig show the multi-dimensional faces of Seoul and its bottomless depths. Firstly, Yeom draws an actual city image of Seoul rather than the imagined geography divided by ethnicity. In the colonial period, the idea of the southern village (namchon, the Japanese district) and the northern village (bukchon, the Korean district) was commonly accepted. These geographical names suggest that Seoul was actually divided and that it was difficult to traverse to the other side as it was intuitively split. Yeom, however, did not fence himself with such imagined geography. He shows that the division was not absolute. He focused on the Japanese living in the north, and Koreans dwelling in the south. As a result, his works make manifest the complexity of city spaces. Secondly, Yeom combined distant classes and its social spaces. By doing so, he managed to unveil the whole city. In his novels, heros and heroines are geographically distant from each other. Furthermore, their economical and class status are also very different. In this case, the distance between one another reflects their social difference. It makes us see the city as a whole. This is because that two halves (two different classes and also two different spaces) are combined. Yeom is thus successful in representing the totality of the city space. This is not only because he wrote about more places than other writers; rather than depicting only a part of the city or the city in fragments, he represented the totality of Seoul. This paper aims to demonstrate this point by using maps and methods of literary geography
Effects of Stratified EGR on the Performance of a Liquid Phase LPG Injection Engine
No full textThe authors would like to thank the Korean Ministry of Science and Technology for funding this research through national research laboratory (NRL) scheme and engineering research center (ERC) program to CERC (Combustion Engineering Research Center)
Nanofluidics and microfluidics : systems and applications / Shaurya Prakash and Junghoon Yeom.
No full textengineering bookfair2015Includes bibliographical references and index.xvii, 294 pages :To provide an interdisciplinary readership with the necessary toolkit to work with micro- and nanofluidics, this book provides basic theory, fundamentals of microfabrication, advanced fabrication methods, device characterization methods and detailed examples of applications of nanofluidics devices and systems. Case studies describing fabrication of complex micro- and nanoscale systems help the reader gain a practical understanding of developing and fabricating such systems. The resulting work covers the fundamentals, processes and applied challenges of functional engineered nanofluidic systems.-- Source other than Library of Congress
Effects of Exhaust Throttling on Engine Performance and Residual Gas in an SI Engine
No full textThe author would like to thank CERC (Combustion Engineering Research Center), KAIST for the financial support
Concurrent and Robust End-to-End Data Integrity Verification Scheme for Flash-Based Storage Devices
No full textThe amount of data generated by scientific applications on high-performance computing systems is growing at an ever-increasing pace. Most of the generated data are transferred to storage in remote systems for various purposes such as backup, replication, or analysis. To detect data corruption caused by network or storage failures during data transfer, the receiver system verifies data integrity by comparing the checksum of the data. However, the internal operation of the storage device is not sufficiently investigated in the existing end-to-end integrity verification techniques. In this paper, we propose a concurrent and reliable end-to-end data integrity verification scheme considering the internal operation of the storage devices for data transfer between high-performance computing systems with flash-based storage devices. To perform data integrity verification including data corruptions that occurred inside the storage devices, we control the order of I/O operations considering the internal operations of the storage devices. Also, to prove the effectiveness of the proposed scheme, we devise a prototype that injects faults on the specific layer of the storage stack and examines detection of faults. We parallelize checksum computation and overlap it with I/O operations to mitigate the overhead caused by I/O reordering. The experimental results show that the proposed scheme reduces the entire data transfer time by up to 62% compared with the existing schemes while ensuring robust data integrity. With the prototype implementation, our scheme detects failures on NAND flash memory inside storage devices that cannot be detected with the existing schemes.N
Mobility support in content centric networks
No full textContent-centric networking (CCN) is designed for efficient dissemination of information. Several architectures are proposed for CCN recently, but mobility issues are not considered sufficiently. We classify traffic types of CCN into real-time and non real-time. We examine mobility problems for each type, and suggest the possible hand-off schemes over CCN. Then, we analyze the delay performance in terms of simulation study. We believe that the proposed schemes can be merged as a part of the CCN easily, since they comply with the inherent nature and rules of the CCN
Zoology of domain walls in quasi-2D correlated charge density wave of 1T-TaS2
No full text© 2021, The Author(s).Domain walls in correlated charge density wave compounds such as 1T-TaS2 can have distinct localized states which govern physical properties and functionalities of emerging quantum phases. However, detailed atomic and electronic structures of domain walls have largely been elusive. We identify using scanning tunneling microscope and density functional theory calculations the atomic and electronic structures for a plethora of discommensuration domain walls in 1T-TaS2 quenched metastably with nanoscale domain wall networks. The domain walls exhibit various in-gap states within the Mott gap but metallic states appear in only particular types of domain walls. A systematic understanding of the domain-wall electronic property requests not only the electron counting but also including various intertwined interactions such as structural relaxation, electron correlation, and charge transfer. This work guides the domain wall engineering of the functionality in correlated van der Waals materials.11Nsciescopu
An adaptive page replacement scheme for scientific applications
No full text© 2020 IEEE.Memory management is playing an increasingly important role in application performance owing to the rapid increase in the amount of data utilized in modern computing workloads and the slow growth in the capacity of the main memory devices. We also observe that recent scientific applications are processing huge amount of data never been seen before. Scientific applications show a tendency to repeat operations on intermediate data using loops, but such access patterns are hard to be appropriately handled by LRU, which is generally used as a page replacement policy in operating systems. In this paper, we propose an adaptive page replacement (APR) scheme, which deals with looping access patterns in scientific applications. APR detects various looping access patterns online and handles them while considering the resulting performance. It can be implemented using limited events or information (e.g., page faults and access bits) provided by the virtual memory subsystem of operating systems. We evaluate APR through trace-driven simulation with traces extracted from workloads in the SPLASH-2x benchmark. Throughout the comparison with multiple previous schemes, we demonstrate that APR successfully improves the performance over the previous schemes by avoiding their downsides.N
- …
