• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.1651-1654
• /
• 2010

본 논문은 서버의 3D SW를 클라이언트에 서비스로 제공함에 있어서 실제 실행은 서버에서 이루어지지만 3D 렌더링과 결과 화면은 클라이언트의 GPU로 처리하여 표시하는 GPU 가상화 기반 3D 원격 렌더링 시스템을 설계하고 구현한 것이다. 3D 렌더링에 클라이언트의 GPU를 이용함으로써 클라이언트 수에 비례한 서버의 성능 저하 문제를 해결할 수 있으며, 클라이언트의 GPU 성능을 충분히 이용하면서 서버의 SW를 서비스 받을 수 있는 장점을 가진다.

• KNOM Review
• /
• v.23 no.1
• /
• pp.43-50
• /
• 2020

As General Purpose Graphics Processing Unit (GPGPU) recently plays an essential role in high-performance computing, several cloud service providers offer GPU service. Most cluster orchestration platforms in a cloud environment using containers allocate the integer number of GPU to jobs and do not allow a node shared with other jobs. In this case, resource utilization of a GPU node might be low if a job does not intensively require either many cores or large size of memory in GPU. GPU virtualization brings opportunities to realize kernel concurrency and share resources. However, performance may vary depending on characteristics of applications running concurrently and interference among them due to resource contention on a node. This paper proposes GPU container co-execution framework with multiple server creation and execution based on Kubernetes, container orchestration platform for measuring interference which may be occurred by sharing GPU resources. Performance changes according to scheduling policies were investigated by executing several jobs on GPU. The result shows that optimal scheduling is not possible only considering GPU memory and computing resource usage. Interference caused by co-execution among applications is measured using the framework.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.197-198
• /
• 2015

IT 기술의 진보적 발전에 따라 클라우드 컴퓨팅 분야 연구들이 활발히 진행되고 있다. 클라우드 컴퓨팅은 가상화 기술을 이용하여 크게 인프라, 플랫폼, 소프트웨어 관점으로 나뉘어 사용자에게 다양한 서비스를 제공한다. 가상화 기술 중에 Desktop Storage Virtualization (DSV)은 분산된 레거시 데스크탑으로 구성되어 있기 때문에 비가용 상태 시간별 클러스터링 및 사용자 요청에 따른 자동 확장이 매우 중요시된다. 본 논문에서는 GPU의 many-core를 이용하여 분산된 데스크탑의 성능 상태 분석 및 자동 확장을 위해 스레드별로 호스트를 매핑하고 병렬적으로 처리하는 Rapid Auto Scaling Mechanism (RASM)을 제안한다.

• Journal of Korea Game Society
• /
• v.14 no.5
• /
• pp.117-126
• /
• 2014

There are various kinds of applications if one can develop a remote execution system using for legacy 3D APIs. It can be used in implementing a cloud gaming service based on the real-time video streaming technology. Or, it can also be used in implementing a GPU virtualization for simultaneously rendering of many different 3D applications. The OpenGL API consists of independent global functions while the Direct3D API consists of Microsoft COM-based interfaces and their member functions, which makes the implementation of remote rendering system more difficult. The purpose of the paper is to show the applicability of the technology to any legacy 3D API by successfully designing and implementing a remote rendering system using the Direct3D API. It applies the implementation to a sample Direct3D application and also performs a few experimentations to show the technical feasibility.

• Broadcasting and Media Magazine
• /
• v.24 no.2
• /
• pp.32-38
• /
• 2019

컴퓨터 생성 홀로그래피(CGH)는 광파의 진행을 수치적으로 시뮬레이션하여 홀로그램 영상을 합성하는 연구분야이다. 실물 기반 홀로그램으로는 제작하기 어려운 다양한 가상 장면을 다룰 수 있으며 복잡한 광학계 구축 문제로부터 자유로운 장점 등으로 인하여 많은 연구가 진행되고 있다. 특히 대규모 병렬 처리가 가능한 범용 GPU의 발전은 CGH 실용화의 견인차가 되고 있다. 본 고에서는 CGH의 원리 소개와 함께 GPU에 기반한 CGH 고속화의 이슈 및 향후 전망을 살펴보고자 한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.1A
• /
• pp.57-63
• /
• 2012

In this paper, we propose a real-time view interpolation method using virtual viewpoint disparity estimation and convergence check. For the real-time process, we estimate a disparity map at the virtual viewpoint from stereo images using the belief propagation method. This method needs only one disparity map, compared to the conventional methods that need two disparity maps. In the view synthesis part, we warp pixels from the reference images to the virtual viewpoint image using the disparity map at the virtual viewpoint. For real-time acceleration, we utilize a high speed GPU parallel programming, called CUDA. As a result, we can interpolate virtual viewpoint images in real-time.

• Journal of KIISE:Software and Applications
• /
• v.37 no.8
• /
• pp.611-619
• /
• 2010

This paper presents an efficient modeling system of virtual pottery in which the user can deform a body of virtual clay with a haptic tool for E-learning. We propose a Circular Sector Element Method (CSEM) which represents the virtual pottery with a set of circular sector elements based on the cylindrical symmetry of pottery. Efficient algorithms for collision detection and response, interactions between adjacent elements, and GPU-based visual-haptic synchronization are designed and implemented for the CSEM. Empirical evaluation showed that the modeling system is computationally efficient with finer details and provides convincing model deformation and force feedback. The developed system, if combined with educational contents, is expected to be used as an effective E-learning platform for elementary school students.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.55-63
• /
• 2019

Recently, the GPU computing method has been utilized to improve the performance of the physics simulation field. In particular, in the case of a deformed object simulation requiring a large amount of computation, a GPU-based parallel processing algorithm is required to guarantee real-time performance. We have studied the parallel structure design method to improve the performance of the mass spring simulation method which is one of the methods of implementing the deformation object simulation. We used OpenGL's GLSL, a graphics library that allows direct access to the GPU, and implemented the GPGPU environment using an independent pipeline, the compute shader. In order to verify the effectiveness of the parallel structure design method, the mass - spring system was implemented based on CPU and GPU. Experimental results show that the proposed method improves computation speed by about 6,000% compared to the CPU Environment. It is expected that the lightweight simulation technology can be effectively applied to the augmented reality and the virtual reality field by using the design method proposed later in this research.

• Journal of Korea Game Society
• /
• v.11 no.6
• /
• pp.71-80
• /
• 2011

Recent terrain rendering applications such as 3D games and virtual reality, use GPU-based ray-casting method for rendering high-quality scenes in realtime. As the size of terrain dataset grows bigger, the rendering speed will be decreased by the increase of the number of texture samplings. To accelerate the conventional ray-casting, we propose an efficient ray casting method with subdivided bounding boxes which are based-on GPU quadtree traversal. The subdivision of the terrain's bounding box can reduce the empty spaces effectively. By performing the ray-casting with this compact bounding box, we can efficiently reduce computation with empty space skipping. Unlike the recent quadtree-based empty space skipping techniques which perform the tree traversal at each ray, our method traverses the tree only once per frame. Therefore, we can save much computational time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.11B
• /
• pp.1303-1310
• /
• 2009

Glassless 3D display requires multiple images taken from different viewpoints to show a scene. The simplest way to get multi-view image is using multiple camera that as number of views are requires. To do that, synchronize between cameras or compute and transmit lots of data comes critical problem. Thus, generating such a large number of viewpoint images effectively is emerging as a key technique in 3D video technology. Image-based view synthesis is an algorithm for generating various virtual viewpoint images using a limited number of views and depth maps. In this paper, because the virtual view image can be express as a transformed image from real view with some depth condition, we propose an algorithm to compute multi-view synthesis from two reference view images and their own depth-map by stepwise duplex forward mapping. And also, because the geometrical relationship between real view and virtual view is repetitively, we apply our algorithm into OpenGL Shading Language which is a programmable Graphic Process Unit that allow parallel processing to improve computation time. We demonstrate the effectiveness of our algorithm for fast view synthesis through a variety of experiments with real data.