• Title/Summary/Keyword: Many-core architecture

Search Result 136, Processing Time 0.027 seconds

Analysis of Programming Techniques for Creating Optimized CUDA Software (최적화된 CUDA 소프트웨어 제작을 위한 프로그래밍 기법 분석)

  • Kim, Sung-Soo;Kim, Dong-Heon;Woo, Sang-Kyu;Ihm, In-Sung
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.16 no.7
    • /
    • pp.775-787
    • /
    • 2010
  • Unlike general-purpose CPUs, the GPUs have been specialized as many-core streaming processors, and are frequently replacing the CPUs in an increasing range of computations thanks to their outstanding parallel computing capacity. In order to respond to such trend, NVIDIA has recently issued a new parallel computing architecture called CUDA(Compute Unified Device Architecture), offering a flexible GPU programming environment for GPGPU(General Purpose GPU) computing. In general, when programmers use the CUDA API, they should clearly understand many aspects of GPU's computing architecture to produce efficient parallel software. In this article, we explain several optimization techniques for CUDA programming that we have verified through a lot of experiment and trial and error, and review how those techniques affect the performance of code execution. In particular, we use a specific problem as an example to analyze several elements that affect performances, such as effective accesses to hierarchical memory system, processor occupancy, and latency hiding. In conclusion, we present several directions that may be utilized effectively in CUDA-based parallel programming.

A Comparative Study on Louis L Kahn's Architectural Philosophy and Kabbalah based on Psychoanalysis (정신분석학에 의한 루이스 칸의 건축철학과 카발라와의 비교 연구)

  • Choi, Hyo-Sik
    • Journal of architectural history
    • /
    • v.18 no.2
    • /
    • pp.85-105
    • /
    • 2009
  • This study set out to compare and analyze the influences Kabbalah, which was Louis I. Kahn's faith as a Jew, on his architecture based on Freud's psychoanalysis that had many exchanges with modernism and contemporary architecture and theories. The specific goals of the study were to shed light to Kahn's presence in contemporary architecture anew and establish the methodology of using psychoanalysis in building new theories of architectural planning. When the theories of psychoanalysis were introduced for comparison and analysis purposes, Kahn tried to differentiate his buildings by placing a function or symbolic central space at the heart of a building even though he did adopt a characteristic of modernism architecture, which was placing a core at the centre of plan, for a while. Such a tendency of his was based on Jung's opinions rather than Freud's and affected by Ecole des Beaux-Art. The analysis results also indicate that he conceived "Served Space & Servant Space," "architecture of connection" and "silence and light" that made up the essence of his architectural theory from the relationships between Ayin-Sof, Kabbalah's absolute god, and Sefiroth. It's also very likely that his often use of triangles and circles in his architecture was affected by the Tree of Sefiroth diagram of Kabbalah. His tendency is well reflected in Salk Institute and Philips Exeter Academy Library, where he placed a laboratory or courtyard at the center where a core was supposed to be, created a corridor or courtyard space between those central spaces and the core, and connected them one another with to perceive the being of Ayin-Sof into an architectural space, which is well proven with Mikveh Israel Synagogue where he directly applied the Tree of Sefiroth diagram. The synagogue also contained a hollow column that served as an important concept in his late architecture. The hollow column was also the result of him applying the concept of Sefiroth of the place where Ayin-Sof Was reduced in Kabbalah.

  • PDF

Seismic Performance of Low-rise Piloti RC Buildings with Concentric Core (중심코어를 가지는 저층 철근콘크리트 필로티 건물의 내진성능)

  • Yoon, Tae-Ho
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.25 no.4_2
    • /
    • pp.611-619
    • /
    • 2022
  • In this study, the seismic performance of low - rise piloti buildings with concentric core (shear wall) position is analysed and reviewed based on KDS 41. The prototype is selected among the constructed low - rise piloti buildings with concentric core designed based on KBC 2005 which was used for many low - rise piloti buildings construction. The seismic performance of the building shows plastic behavior in X-direction and elastic behavior in Y-direction. The inter-story drift is lager than that of concentric core case and is under the maximum allowed drift ratio. The displacement ratio of first story is much lager the that of upper stories, and the frame structure in the first story is evaluated as vulnerable to lateral force. Therefore, low - rise piloti buildings with concentric core need the diminishment of lateral displacement and reinforcement of lateral resistance capacity in seismic design and seismic retrofit.

A Study on GPGPU Performance Improvement Technique on GCN Architecture Using OpenCL API (GCN 아키텍쳐 상에서의 OpenCL을 이용한 GPGPU 성능향상 기법 연구)

  • Woo, DongHee;Kim, YoonHo
    • The Journal of Society for e-Business Studies
    • /
    • v.23 no.1
    • /
    • pp.37-45
    • /
    • 2018
  • The current system upon which a variety of programs are in operation has continuously expanded its domain from conventional single-core and multi-core system to many-core and heterogeneous system. However, existing researches have focused mostly on parallelizing programs based CUDA framework and rarely on AMD based GCN-GPU optimization. In light of the aforementioned problems, our study focuses on the optimization techniques of the GCN architecture in a GPGPU environment and achieves a performance improvement. Specifically, by using performance techniques we propose, we have reduced more then 30% of the computation time of matrix multiplication and convolution algorithm in GPGPU. Also, we increase the kernel throughput by more then 40%.

Design Proposals of Public Architecture for Sustainable Development in Kwangju Old City (광주도심지역의 지속가능한 개발을 위한 공공건축 설계프로젝트)

  • 손승광
    • Proceeding of Spring/Autumn Annual Conference of KHA
    • /
    • 2002.11a
    • /
    • pp.79-84
    • /
    • 2002
  • Many people think, in common that An expansion toward outer city is a development, and it can be a general trends in a new development in a growing city. But We can see many case which moving of a public building are considerate as a core element to promote the new development towards outer city, and that is a negative element of slum in central area and community making. There are many aspects to pursue sustainable urban structure of in a city, and public building is a very important element to manage deteriorate central area from social slum in a old town. In this presentation, three project, Local Authority office of Chonnam province, Kwangju Station, and Hyper Urbanity, and it shows sustainable concept of the public building as a core in a city development. The effect of the projects are expected sustainable development and community in terms of social, cultural and historical aspects.

  • PDF

Electrospray technique for preparation of core-shell materials : A mini-review

  • Tran, Vinh Van;Lee, Young-Chul
    • Particle and aerosol research
    • /
    • v.14 no.3
    • /
    • pp.49-63
    • /
    • 2018
  • During the last decade, electrospray (ES) techniques have been used as potential methods for preparing of core-shell materials. Depending on the architecture of nozzle and design of devices, the ES techniques includes monoaxial, coaxial, multiple coaxial nozzle ES and microfluidic ES devices. ES operates based on a basic principle, in which a spray of monodisperse droplets is formed by dispensing an electrically conductive liquid through a capillary charged to a sufficiently high potential. In review of many recent research papers, we take a closer look at ES techniques and their applications for fabrication of core-shell materials. Several advantages of ES technique compared with other methods were emphasized and it may be regarded as a potential tool for fabrication of core-shell materials current and near future.

Research on prefabricated concrete beam-column joint with high strength bolt-end plate

  • Shufeng, Li;Di, Zhao;Qingning, Li;Huajing, Zhao;Jiaolei, Zhang;Dawei, Yuan
    • Structural Engineering and Mechanics
    • /
    • v.74 no.3
    • /
    • pp.395-406
    • /
    • 2020
  • Many prefabricated concrete frame joints have been proposed, and most of them showed good seismic performance. However, there are still some limitations in the proposed fabricated joints. For example, for prefabricated prestressed concrete joints, prefabricated beams and prefabricated columns are assembled as a whole by the pre-stressed steel bar and steel strand in the beams, which brings some troubles to the construction, and the reinforcement in the core area of the joints is complex, and the mechanical mechanism is not clear. Based on the current research results, a new type of fabricated joint of prestressed concrete beams and confined concrete columns is proposed. To study the seismic performance of the joint, the quasi-static test is carried out. The test results show that the nodes exhibit good ductility and energy dissipation. According to the experimental fitting method and the "fixed point pointing" law, the resilience model of this kind of nodes is established, and compared with the experimental results, the two agree well, which can provides a certain reference for elasto-plastic seismic response analysis of this type of structure. Besides, based on the analysis of the factors affecting the shear capacity of the node core area, the formula of shear capacity of the core area of the node is proposed, and the theoretical values of the formula are consistent with the experimental value.

Vulnerability analysis on the ARMv7 Thumb Architecture (ARMv7 Thumb Architecture 취약성 분석)

  • Kim, Si-Wan;Seong, Ki-Taek
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.21 no.5
    • /
    • pp.1003-1008
    • /
    • 2017
  • The Internet of Things has attracted considerable research attention in recent years. In order for the new IoT technology to be widely used, the reliability and protection of information is required. IoT systems are very vulnerable to physical security due to their easy accessibility. Along with the development of SoC technology, many operating systems have been developed and many new operating systems have been introduced. In this paper, we describe the vulnerability analysis results for operating systems running on the ARMv7 Thumb Architecture hardware platform. For the recently introduced "Windows 10 IoT Core" operating system, I implemented the Zero-Day Attack by implanting the penetration code developed through the research into a specific IoT system. The virus detection test for the resulting penetration code was validated by referral to the "virustotal" site.

Multimedia Extension Instructions and Optimal Many-core Processor Architecture Exploration for Portable Ultrasonic Image Processing (휴대용 초음파 영상처리를 위한 멀티미디어 확장 명령어 및 최적의 매니코어 프로세서 구조 탐색)

  • Kang, Sung-Mo;Kim, Jong-Myon
    • Journal of the Korea Society of Computer and Information
    • /
    • v.17 no.8
    • /
    • pp.1-10
    • /
    • 2012
  • This paper proposes design space exploration methodology of many-core processors including multimedia specific instructions to support high-performance and low power ultrasound imaging for portable devices. To explore the impact of multimedia instructions, we compare programs using multimedia instructions and baseline programs with a same many-core processor in terms of execution time, energy efficiency, and area efficiency. Experimental results using a $256{\times}256$ ultrasound image indicate that programs using multimedia instructions achieve 3.16 times of execution time, 8.13 times of energy efficiency, and 3.16 times of area efficiency over the baseline programs, respectively. Likewise, programs using multimedia instructions outperform the baseline programs using a $240{\times}320$ image (2.16 times of execution time, 4.04 times of energy efficiency, 2.16 times of area efficiency) as well as using a $240{\times}400$ image (2.25 times of execution time, 4.34 times of energy efficiency, 2.25 times of area efficiency). In addition, we explore optimal PE architecture of many-core processors including multimedia instructions by varying the number of PEs and memory size.

Design Space Exploration of Many-Core Processor for High-Speed Cluster Estimation (고속의 클러스터 추정을 위한 매니코어 프로세서의 디자인 공간 탐색)

  • Seo, Jun-Sang;Kim, Cheol-Hong;Kim, Jong-Myon
    • Journal of the Korea Society of Computer and Information
    • /
    • v.19 no.10
    • /
    • pp.1-12
    • /
    • 2014
  • This paper implements and improves the performance of high computational subtractive clustering algorithm using a single instruction, multiple data (SIMD) based many-core processor. In addition, this paper implements five different processing element (PE) architectures (PEs=16, 64, 256, 1,024, 4,096) to select an optimal PE architecture for the subtractive clustering algorithm by estimating execution time and energy efficiency. Experimental results using two different medical images and three different resolutions ($128{\times}128$, $256{\times}256$, $512{\times}512$) show that PEs=4,096 achieves the highest performance and energy efficiency for all the cases.