• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.135-138
• /
• 2013

GPGPU(General Purpose Graphics Processing Unit) 병렬처리 시스템인 CUDA(Compute Unified Device Architecture)는 컴퓨터에서의 고속 연산 처리를 위해 많이 사용되어왔다. CUDA에서 연산 처리를 하기 위해서는 CUDA의 특성을 이해해야 한다. CUDA는 CPU(Central Processing Unit)가 처리하는 Host 영역과 GPU(Graphics Processing Unit)가 처리하는 영역인 Device 영역이 존재하며, 이 두 영역간의 데이터 복사를 통해 연산 처리를 진행한다. 이런 구조적인 특성상 메인 메모리에서 GPU 메모리로 입력 데이터를 전달해야 GPU를 이용해 연산을 처리할 수 있는 구조를 가지고 있다. 하지만 이러한 처리 구조로 인해 연산 시간과 별도로 메인 메모리와 GPU 메모리간의 데이터 복사시간이 존재하며, 추가적으로 발생하는 메모리 복사 시간으로 인해 오버헤드가 발생하게 된다. 본 논문에서는 실험을 통해 메모리 복사 시간, 연산의 반복 횟수 그리고 연산의 복잡성이 전체 성능에 어떤 영향을 미치는지 논하고자 한다.

• Computers and Concrete
• /
• v.18 no.5
• /
• pp.1019-1039
• /
• 2016

In this paper, a parallel algorithm of nonlinear dynamic analysis of three-dimensional (3D) reinforced concrete (RC) frame structures based on the platform of graphics processing unit (GPU) is proposed. Time integration is performed using Newmark method for nonlinear implicit dynamic analysis and parallelization strategies are presented. Correspondingly, a parallel Preconditioned Conjugate Gradients (PCG) solver on GPU is introduced for repeating solution of the equilibrium equations for each time step. The RC frames were simulated using fiber beam model to capture nonlinear behaviors of concrete and reinforcing bars. The parallel finite element program is developed utilizing Compute Unified Device Architecture (CUDA). The accuracy of the GPU-based parallel program including single precision and double precision was verified in comparison with ABAQUS. The numerical results demonstrated that the proposed algorithm can take full advantage of the parallel architecture of the GPU, and achieve the goal of speeding up the computation compared with CPU.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.4
• /
• pp.328-335
• /
• 2011

GPU (Graphics Processing Units) is consists of SIMD (Single Instruction Multiple Data) architecture and provides fast parallel processing. A GA (Genetic Algorithm), which requires large computations, is implemented in GPU using CUDA (Compute Unified Device Architecture). Three kinds of execution models are presented according to different combinations of processing modules in GPU. Comparison experiments between GPU models and CPU are tested for a couple of benchmark problems by variation of population sizes and complexity of problem sizes.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.1
• /
• pp.27-35
• /
• 2015

Increasing the number of GPU (Graphic Processor Unit) cores, the studies on High Performance Computing Platform using GPU have actively been made in recent. This trend has led to the development of GPGPU (General Purpose GPU) and CUDA (Compute Unified Device Architecture) Framework. In this paper, we explain the many benefits of the GPU based system, and propose the ICIDF(Identify Compute-Intensive Data set and Function) methodology to apply GPU technology to legacy military information system for performance improvement. To demonstrate the efficiency of this methodology, we applied this method to AES CPU based program obtained from the Internet web site. Simply changing the data structure made improved the performance of AES program. As a result, the performance of AES based GPU program is improved gradually up to 10 times. Depending on the developer's ability, additional performance improvement can be expected. The problem to be solved is heat issue, but this problem has been much improved by the development of the cooling technology.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.1
• /
• pp.90-100
• /
• 2011

We present a parallel bi-conjugate gradient (Bi-CG) matrix solver for large scale Bio-FET simulations based on recent graphics processing units (GPUs) which can realize a large-scale parallel processing with very low cost. The proposed method is focused on solving the Poisson equation in a parallel way, which requires massive computational resources in not only semiconductor simulation, but also other various fields including computational fluid dynamics and heat transfer simulations. As a result, our solver is around 30 times faster than those with traditional methods based on single core CPU systems in solving the Possion equation in a 3D FDM (Finite Difference Method) scheme. The proposed method is implemented and tested based on NVIDIA's CUDA (Compute Unified Device Architecture) environment which enables general purpose parallel processing in GPUs. Unlike other similar GPU-based approaches which apply usually 32-bit single-precision floating point arithmetics, we use 64-bit double-precision operations for better convergence. Applications on the CUDA platform are rather easy to implement but very hard to get optimized performances. In this regard, we also discuss the optimization strategy of the proposed method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.16 no.3
• /
• pp.83-89
• /
• 2015

Connected component labeling (CCL) is a mandatory step in image segmentation where objects are extracted and uniquely labeled. CCL is a computationally expensive operation and thus is often done in parallel processing framework to reduce execution time. Various parallel CCL methods have been proposed in the literature. Among them are NSZ label equivalence (NSZ-LE) method, modified 8 directional label selection (M8DLS) method, HYBRID1 method, and HYBRID2 method. Soh et al. showed that HYBRID2 outperforms the others and is the best so far. In this paper we propose a new hybrid parallel CCL algorithm termed as HYBRID3 that combines selective four directional label search (S4DLS) with label backtracking (LB). We show that the average percentage speedup of the proposed over M8DLS is around 60% more than that of HYBRID2 over M8DLS for various kinds of images.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.5
• /
• pp.1043-1061
• /
• 2013

Recent advances in computer technology introduce massive data and their analysis becomes important. The high performance computing is one of the most essential part in analysis of massive data. In this paper, we review the general purpose of the graphics processing unit and its application to parallel computing, which has been of great interest in statistics communities.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.3-6
• /
• 2013

반도체 공정에서 소자의 제조 비용 감소를 위해 제조 공정 검증을 위한 시뮬레이션을 수행하게 된다. 이 시뮬레이션은 반도체 소자 내부의 물리량 계산을 통해 반도체 소자 내부의 불순물의 거동을 해석하게 된다. 이를 위해 사용되는 알고리즘으로 3차원적 형상을 표현하는 물리적 미분 미분방정식을 계산하게 되는데, 정확한 계산을 위해 유한 차분 시간 영역법(이하 FDTD)과 같은 수치해석 기법을 이용한다. 실제적으로 반도체 공정의 시뮬레이션에서 FDTD연산의 실행 시간은 90% 이상을 소요하게 된다. 이러한 연산에서 더욱 빠른 성능을 확보하기 위해 본 논문에서는 기존의 CUDA(Compute Unified Device Architecture)로 구현된 FDTD알고리즘을 OpenMP를 통한 다중 GPU제어를 이용하여 연산 수행시간을 감소하고, 그 결과물을 통하여 성능 향상도를 측정한다.

• Korean Journal of Computational Design and Engineering
• /
• v.16 no.4
• /
• pp.285-291
• /
• 2011

A pose estimation process from medical images is calculating locations and orientations of objects obtained from Computed Tomography (CT) volume data utilizing X-ray images from two directions. In this process, digitally reconstructed radiograph (DRR) images of spatially transformed objects are generated and compared to X-ray images repeatedly until reasonable transformation matrices of the objects are found. The DRR generation and image comparison take majority of the total time for this pose estimation. In this paper, a fast DRR generation technique based on GPU parallel computing is introduced. A volume ray-casting algorithm is explained with brief vector operations and a parallelization technique of the algorithm using Compute Unified Device Architecture (CUDA) is discussed. This paper also presents the implementation results and time measurements comparing to those from pure-CPU implementation and open source toolkit.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.2
• /
• pp.44.1-44.1
• /
• 2015

We set up a project to make spectrometers for single dish observations of the Korean VLBI Network (KVN), a new future multi-beam receiver of the ASTE (Atacama Submillimeter Telescope Experiment), and the total power (TP) antennas of the Atacama Large Millimeter/submillimeter Array (ALMA). Traditionally, spectrometers based on ASIC (Application-Specific Integrated circuit) and FPGA (Field-Programmable Gate Array) have been used in radio astronomy. It is, however, that a Graphics Processing Unit (GPU) technology is now viable for spectrometers due to the rapid improvement of its performance. A high-resolution spectrometer should have the following functions: poly-phase filter, data-bit conversion, fast Fourier transform, and complex multiplication. We wrote a program based on CUDA (Compute Unified Device Architecture) for a GPU spectrometer. We measured its performance using two GPU cards, Titan X and K40m, from NVIDIA. A non-optimized GPU code can process a data stream of around 2 GHz bandwidth, which is enough for the KVN spectrometer and promising for the ASTE and ALMA TP spectrometers.