• Title, Summary, Keyword: 병렬컴퓨팅

Search Result 418, Processing Time 0.035 seconds

A Kernel Module to Support High-Performance Intra-Node Communication for Multi-Core Systems (멀티 코어 시스템을 위한 고속 노드내 통신 지원 모듈)

  • Jin, Hyun-Wook;Kang, Hyun-Goo;Kim, Jong-Soon
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.34 no.9
    • /
    • pp.407-415
    • /
    • 2007
  • In parallel cluster computing systems, the efficiency of communication between computing nodes is one of important factors that decide overall system performance. Accordingly, many researchers have studied on high-performance inter-node communication. The recently launched multi-core processor, however. increases the importance of intra-node communication as well because the more the number of cores in a node, the more the number of parallel processes running in the same node. Though there have been studies on intra-node communications, these have limited considerations on the state-of-the-art systems. In this paper, we propose a Linux kernel module that minimizes the number of data copy by exploiting the memory mapping mechanism for high-performance intra-node communication. The proposed kernel module supports the Linux kernel version 2.6. The performance measurements over a multi-core system present that the proposed kernel module can achieve lower latency up to 62% and higher throughput up to 144% than an existing kernel module approach. In addition, the measurements reveal that the performance of intra-node communication can vary significantly based on whether the cores that run the communication processes are belong to the same processor package (i.e., sharing the L2 cache).

Design And Implementation Real-Time Load Balancing Using TMO Replica Of LTMOS In Distributed Environment (분산 환경에서 LTMOS의 TMO 리플리카를 이용한 실시간 로드 밸런싱의 설계 및 구현)

  • Joo Koonho;Lim Bosub;Heu Shin;Kim Jungguk
    • Proceedings of the Korean Information Science Society Conference
    • /
    • /
    • pp.829-831
    • /
    • 2005
  • 실시간 시스템이란 시간적인 제한을 가지고 작업 수행 결과의 정확도가 보장되는 시스템으로 경성 실시간 시스템과 연성 실시간 시스템으로 분류된다. 최근 분산 실시간 분야에서 새로운 패러다임으로써 폭넓게 활용되기 시작한 실시간 객체 모델인 TMO는 Kane Kim과 Kopetz에 의해 처음 제안되었다. TMO 모델은 경성 또는 연성 실시간 응용과 병렬 컴퓨팅 응용 프로그램에서 사용 될 수 있으며, 시스템의 기능적인 면과 시간 조건 수행 모두를 명확히 정의할 수 있다. TMO의 네트워크로 구성되는 실시간 분산 환경에서의 실행을 위해 몇 개의 TMO 실행 엔진이 개발 되었는데, 그 중에서 LTMOS라는 리눅스 기반의 연성 실시간 미들웨어 엔진이 한국외대 RTDCS lab.에서 개발되었다. 하지만 LTMOS의 실시간 시스템 수행 중 작업량의 과부하로 인한 deadline 위반이나, 시스템간의 분산 IPC 통신에 있어서 Channel Traffic이 빈번한 경우 실시간 시스템을 유지할 수 없다는 문제점들을 갖고 있다. 이러한 문제점들을 해결하고 조금 더 효율적인 실시간 시스템을 유지하기 위해서, TMO 프로그램의 resource 정보를 담고 있는 ODS(Object Data Store)만을 다른 노드에 있는 자신의 TMO 프로그램 Replica로 이주해서 실시간 로드 밸런싱을 구현하는 기법을 사용하였다. 이에 본 논문에서는 TMO 프로그램들의 deadline 위반 및 Channel Traffic 부하를 감지할 수 있는 Node Monitor와 최적의 노드를 선별할 수 있는 Migration Manager를 새롭게 추가하였고, 쓰레드들의 스케줄러인 WRMT에 이주 작업을 하기 위한 부가적인 기능을 구현하였다. 2D 이미지의 관측점을 줄여 계산량을 대폭 감소시키는 장점을 갖는다.것으로 조사되었으며 40대 이상의 연령층은 점심비용으로 더 많은 지출을 하고 있는 것으로 나타났다. 4) 끼니별 한식에 대한 선호도는 아침식사의 경우가 가장 높았으며, 이는 40대와 50대에서 높게 나타났다. 점심 식사로 가장 선호되는 음식은 중식, 일식이었으며 저녁 식사에서 가장 선호되는 메뉴는 전 연령층에서 일식, 분식류 이었으며, 한식에 대한 선택 정도는 전 연령층에서 매우 낮게 나타났다. 5) 각 연령층에서 선호하는 한식에 대한 조사에서는 된장찌개가 전 연령층에서 가장 높은 선호도를 나타내었고, 김치는 40대 이상의 선호도가 30대보다 높게 나타났으며, 흥미롭게도 30세 이하의 선호도는 30대보다 높게 나타났다. 그 외에도 떡과 죽에 대한 선호도는 전 연령층에서 낮게 조사되었다. 장아찌류의 선호도는 전 연령대에서 낮았으며 특히 30세 이하에서 매우 낮게 조사되었다. 한식의 맛에 대한 만족도 조사에서는 연령이 올라갈수록 한식의 맛에 대한 만족도는 낮아지고 있었으나, 한식의 맛에 대한 만족도가 높을수록 양과 가격에 대한 만족도는 높은 경향을 나타내었다. 전반적으로 한식에 대한 선호도는 식사 때와 식사 목적에 따라 연령대 별로 다르게 나타나고 있으나, 선호도는 성별이나 세대에 관계없이 폭 넓은 선호도를 반영하고 있으며, 이는 대학생들을 대상으로 하는 연구 등에서도 나타난바 같다. 주 5일 근무제의 확산과 초 중 고생들의 토요일 휴무와 더불어 여행과 엔터테인먼트산업은 더욱 더 발전을 거듭하고 있으며, 외식은 여행과 여가 활동의 필수적인 요소로써 그 역할을 일조하고 있다. 이와 같은 여가시간의 증가는 독신자들에게는 좀더 많은 여유시간을 가족을

  • PDF

Simulation of YUV-Aware Instructions for High-Performance, Low-Power Embedded Video Processors (고성능, 저전력 임베디드 비디오 프로세서를 위한 YUV 인식 명령어의 시뮬레이션)

  • Kim, Cheol-Hong;Kim, Jong-Myon
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.13 no.5
    • /
    • pp.252-259
    • /
    • 2007
  • With the rapid development of multimedia applications and wireless communication networks, consumer demand for video-over-wireless capability on mobile computing systems is growing rapidly. In this regard, this paper introduces YUV-aware instructions that enhance the performance and efficiency in the processing of color image and video. Traditional multimedia extensions (e.g., MMX, SSE, VIS, and AltiVec) depend solely on generic subword parallelism whereas the proposed YUV-aware instructions support parallel operations on two-packed 16-bit YUV (6-bit Y, 5-bits U, V) values in a 32-bit datapath architecture, providing greater concurrency and efficiency for color image and video processing. Moreover, the ability to reduce data format size reduces system cost. Experiment results on a representative dynamically scheduled embedded superscalar processor show that YUV-aware instructions achieve an average speedup of 3.9x over the baseline superscalar performance. This is in contrast to MMX (a representative Intel#s multimedia extension), which achieves a speedup of only 2.1x over the same baseline superscalar processor. In addition, YUV-aware instructions outperform MMX instructions in energy reduction (75.8% reduction with YUV-aware instructions, but only 54.8% reduction with MMX instructions over the baseline).

PreSPI: Protein-Protein Interaction Prediction Service System (PreSPI: 단백질 상호작용 예측 서비스 시스템)

  • Han Dong-Soo;Kim Hong-Soog;Jang Woo-Hyuk;Lee Sung-Doke
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.11 no.6
    • /
    • pp.503-513
    • /
    • 2005
  • With the recognition of the importance of computational approach for protein-protein interaction prediction, many techniques have been developed to computationally predict protein-protein interactions. However, few techniques are actually implemented and announced in service form for general users to readily access and use the techniques. In this paper, we design and implement a protein interaction prediction service system based on the domain combination based protein-protein interaction prediction technique, which is known to show superior accuracy to other conventional computational protein-protein interaction prediction methods. In the prediction accuracy test of the method, high sensitivity($77\%$) and specificity($95\%$) are achieved for test protein pairs containing common domains with teaming sets of proteins in a Yeast. The stability of the method is also manifested through the testing over DIP CORE, HMS-PCI, and TAP data. Performance, openness and flexibility are the major design goals and they are achieved by adopting parallel execution techniques, web Services standards, and layered architecture respectively. In this paper, several representative user interfaces of the system are also introduced with comprehensive usage guides.

A Study on the Digital Filter Design using Software for Analysis of Observation Data in Radio Astronomy (전파천문 관측데이터 분석을 위해 소프트웨어를 이용한 디지털필터 설계에 관한 연구)

  • Yeom, Jae-Hwan;Oh, Se-Jin;Roh, Duk-Gyoo;Oh, Chung-Sik;Jung, Dong-Kyu;Shin, Jae-Sik;Kim, Hyo-Ryoung;Hwang, Ju-Yeon
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.16 no.4
    • /
    • pp.175-181
    • /
    • 2015
  • In this paper, we propose a design method for a digital filter using software in order to analyze the radio astronomy observation data. Recently the analysis method for radio astronomy observing system is transferring from hardware to software by developing of state-of-the-art of computer system. The existing hardware system is not able to easily change the specification because it is implemented to meet special requirements and it takes a high cost and time. In case of software, however, it has an advantage to implement with small cost if open software is used, and flexibly changes to satisfy the desired specification. But, in order to analyze the massive data like radio astronomy with software, the good performance system is needed for computer. Therefore, this paper proposes a digital filter design method using software with the same performance as that of digital filter implemented with hardware in observation system which is operated by the KVN(Korean VLBI Network). To design a digital filter, the proposed method is performed with standard C language and the simulation is conducted with GNU(GNU's Not Unix) Octave and investigated to show its effectiveness. In addition, for the high speed operation of the designed digital filter, the SSE(Streaming SIMD Extensions) library is adopted for available parallel operation. By the proposed digital filter, the digital filtering is performed for the wide band observation data in the KVN observation mode, the filtering result of narrow band observation has no ripple inside of stop band, and confirmed the effectiveness of the proposed method.

A Hardware Implementation of the Underlying Field Arithmetic Processor based on Optimized Unit Operation Components for Elliptic Curve Cryptosystems (타원곡선을 암호시스템에 사용되는 최적단위 연산항을 기반으로 한 기저체 연산기의 하드웨어 구현)

  • Jo, Seong-Je;Kwon, Yong-Jin
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.8 no.1
    • /
    • pp.88-95
    • /
    • 2002
  • In recent years, the security of hardware and software systems is one of the most essential factor of our safe network community. As elliptic Curve Cryptosystems proposed by N. Koblitz and V. Miller independently in 1985, require fewer bits for the same security as the existing cryptosystems, for example RSA, there is a net reduction in cost size, and time. In this thesis, we propose an efficient hardware architecture of underlying field arithmetic processor for Elliptic Curve Cryptosystems, and a very useful method for implementing the architecture, especially multiplicative inverse operator over GF$GF (2^m)$ onto FPGA and futhermore VLSI, where the method is based on optimized unit operation components. We optimize the arithmetic processor for speed so that it has a resonable number of gates to implement. The proposed architecture could be applied to any finite field $F_{2m}$. According to the simulation result, though the number of gates are increased by a factor of 8.8, the multiplication speed We optimize the arithmetic processor for speed so that it has a resonable number of gates to implement. The proposed architecture could be applied to any finite field $F_{2m}$. According to the simulation result, though the number of gates are increased by a factor of 8.8, the multiplication speed and inversion speed has been improved 150 times, 480 times respectively compared with the thesis presented by Sarwono Sutikno et al. [7]. The designed underlying arithmetic processor can be also applied for implementing other crypto-processor and various finite field applications.

Real-time Color Recognition Based on Graphic Hardware Acceleration (그래픽 하드웨어 가속을 이용한 실시간 색상 인식)

  • Kim, Ku-Jin;Yoon, Ji-Young;Choi, Yoo-Joo
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.14 no.1
    • /
    • pp.1-12
    • /
    • 2008
  • In this paper, we present a real-time algorithm for recognizing the vehicle color from the indoor and outdoor vehicle images based on GPU (Graphics Processing Unit) acceleration. In the preprocessing step, we construct feature victors from the sample vehicle images with different colors. Then, we combine the feature vectors for each color and store them as a reference texture that would be used in the GPU. Given an input vehicle image, the CPU constructs its feature Hector, and then the GPU compares it with the sample feature vectors in the reference texture. The similarities between the input feature vector and the sample feature vectors for each color are measured, and then the result is transferred to the CPU to recognize the vehicle color. The output colors are categorized into seven colors that include three achromatic colors: black, silver, and white and four chromatic colors: red, yellow, blue, and green. We construct feature vectors by using the histograms which consist of hue-saturation pairs and hue-intensity pairs. The weight factor is given to the saturation values. Our algorithm shows 94.67% of successful color recognition rate, by using a large number of sample images captured in various environments, by generating feature vectors that distinguish different colors, and by utilizing an appropriate likelihood function. We also accelerate the speed of color recognition by utilizing the parallel computation functionality in the GPU. In the experiments, we constructed a reference texture from 7,168 sample images, where 1,024 images were used for each color. The average time for generating a feature vector is 0.509ms for the $150{\times}113$ resolution image. After the feature vector is constructed, the execution time for GPU-based color recognition is 2.316ms in average, and this is 5.47 times faster than the case when the algorithm is executed in the CPU. Our experiments were limited to the vehicle images only, but our algorithm can be extended to the input images of the general objects.

Transfer Learning using Multiple ConvNet Layers Activation Features with Principal Component Analysis for Image Classification (전이학습 기반 다중 컨볼류션 신경망 레이어의 활성화 특징과 주성분 분석을 이용한 이미지 분류 방법)

  • Byambajav, Batkhuu;Alikhanov, Jumabek;Fang, Yang;Ko, Seunghyun;Jo, Geun Sik
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.1
    • /
    • pp.205-225
    • /
    • 2018
  • Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.