• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1332-1338
• /
• 2015

Recently, growing attention has been paid to multi-GPU rendering to support real-time high-quality rendering at high resolution. In order to attain high performance in real-time multi-GPU rendering, great care needs to be taken to reduce the overhead of data transfer among GPUs and frame composition. This paper presents a novel multi-GPU algorithm that greatly enhances split frame rendering with implicit query-based synchronization. In order to support implicit synchronization in frame composition, we further present a message queue-based scheduling algorithm. We carried out an experiment to evaluate our algorithm, and found that our algorithm improved rendering performance up to 200% more than previously existing algorithms.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.11
• /
• pp.853-858
• /
• 2006

In this paper, we propose a practical method for hardware-accelerated rendering of the depth image-based representation(DIBR) of 3D graphic object using graphic processing unit(GPU). The proposed method overcomes the drawbacks of the conventional rendering, i.e. it is slow since it is hardly assisted by graphics hardware and surface lighting is static. Utilizing the new features of modem GPU and programmable shader support, we develop an efficient hardware-accelerating rendering algorithm of depth image-based 3D object. Surface rendering in response of varying illumination is performed inside the vertex shader while adaptive point splatting is performed inside the fragment shader. Experimental results show that the rendering speed increases considerably compared with the software-based rendering and the conventional OpenGL-based rendering method.

• ETRI Journal
• /
• v.42 no.4
• /
• pp.608-618
• /
• 2020

We present a novel GPU-based ray-casting algorithm for volume rendering of unstructured grid data. Our volume rendering system uses a ray-casting method that guarantees accurate rendering results. We also employ the per-pixel intersection list concept in the Bunyk algorithm to guarantee an accurate result for non-convex meshes. For efficient memory access for the lists on the GPU, we represent the intersection lists for all faces as an array with our novel construction algorithm. With the intersection lists, we perform ray-casting on a GPU, and a GPU thread handles each ray. To increase ray-coherency in a thread block and improve memory access efficiency, we extend a prior image-tile-based work distribution method to fit modern GPU architectures. We also show that a prior approach using a per-thread local buffer to reduce redundant computation is not appropriate for modern GPU architectures. Instead, we take an on-demand calculation strategy that achieves better performance even though it allows duplicate computations. We applied our method to three unstructured grid datasets with different characteristics. With a GPU, our method achieved up to 36.5 times higher performance for the ray-casting process and 19.7 times higher performance for the whole volume rendering process compared with the Bunyk algorithm using a CPU core. Also, our approach showed up to 8.2 times higher performance than a GPU-based cell projection method while generating more accurate rendering results. These results demonstrate the efficiency and accuracy of our method.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.3
• /
• pp.27-33
• /
• 2009

In terrain visualization, the quadtree is the most frequently used data structure for progressive mesh generation. The quadtree provides an efficient level-of-detail selection and view frustum culling. However, most applications using quadtrees are performed by the CPU, since the hierarchical data structure cannot be manipulated in a programmable rendering pipeline. For this reason, quadtree-based methods show lower performance and higher dependancy of CPU in comparison to GPU-based methods. We present a quadtree-based terrain-rendering method for GPU execution that uses vertex multiplication. It offers higher performance than previous CPU-based quadtree methods, without loss of image quality.

• Journal of Korea Game Society
• /
• v.7 no.3
• /
• pp.59-66
• /
• 2007

Ray tracing is one of the classical global illumination methods to generate a photo-realistic rendering image with various lighting effects such as reflection and refraction. However, there are some restrictions on real-time applications because of its computation load. In order to overcome these limitations, many researches of the ray tracing based on GPU (Graphics Processing Unit) have been presented up to now. In this paper, we implement the ray tracing algorithm by J. Purcell and combine it with two methods in order to improve the rendering performance for interactive applications. First, intersection points of the primary ray are determined efficiently using rasterization on graphics hardware. We then construct the acceleration structure of 3D objects to improve the rendering performance. There are few researches on a detail analysis of improved performance by these considerations in ray tracing rendering. We compare the rendering system with environment mapping based on GPU and implement the wireless remote rendering system. This system is useful for interactive applications such as the realtime composition, augmented reality and virtual reality.

• Journal of Korea Game Society
• /
• v.12 no.2
• /
• pp.53-62
• /
• 2012

Visualizing a volume dataset with ray-casting which of visualization methods provides high quality image. However it spends too much time for rendering because the size of volume data are huge. Recently, various researches have been proposed to accelerate GPU-based volume rendering to solve these problems. In this paper, we propose an efficient GPU-based empty space skipping to accelerate volume ray-casting using octree traversal. This method creates min-max octree and searches empty space using vertex splitting. It minimizes the bounding polyhedron by eliminating empty space found in the octree traveral step. The rendering results of our method are identical to those of previous GPU-based volume ray-casting, with the advantage of faster run-time because of using minimized bounding polyhedron.

• Journal of Korea Game Society
• /
• v.8 no.3
• /
• pp.61-68
• /
• 2008

Quadtree-based terrain visualization methods have been used in a lot of applications. However, because most procedures are performed on the CPU, the rendering speed is slow in comparison to methods using GPU. In this paper, we present a quadtree-based terrain visualization method working on the GPU with specially designed data structure, error-texture and LOD-texture, and block-based acceleration method. In preprocessing step, we calculate errors in world space and store them to error-texture. In rendering step, we examine projected errors of error-texture and choose the detail level, then store the projected errors to LOD-texture. View frustum culling is performed as block unit using the values of error-texture and LOD-texture. This method reduces CPU load and performs time consuming jobs such as LOD selection and view frustum culling.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.12
• /
• pp.1165-1176
• /
• 2010

In order to realistically visualize such participating media as cloud, smoke, and gas, the light transport process must be physically simulated inside the media. While it is known that this process is well described physically through the volume rendering equation, it usually takes a great deal of computation time for obtaining high-precision solutions. Recently, GPU-based, fast rendering methods have been proposed for the realistic simulation of participating media, however, there still remain several problems to be resolved. In this article, we describe our rendering techniques applied to enhance the performances and features of our GPU-assisted participating media renderer, and analyze how such efforts have actually improved the renderer. The presented techniques will be effectively used in volume renderers for creating various digital contents in the special effects industries.

• Journal of the HCI Society of Korea
• /
• v.1 no.1
• /
• pp.45-52
• /
• 2006

This paper presents an image-space algorithm to real-time collision detection, which is run completely by GPU. For a single object or for multiple objects with no collision, the front and back faces appear alternately along the view direction. However, such alternation is violated when objects collide. Based on these observations, the algorithm propose the depth peeling method which renders the minimal surface of objects, not whole surface, to find colliding. The Depth peeling method utilizes the state-of-the-art functionalities of GPU such as framebuffer object, vertexbuffer object, and occlusion query. Combining these functions, multi-pass rendering and context switch can be done with low overhead. Therefore proposed approach has less rendering times and rendering overhead than previous image-space collision detection. The algorithm can handle deformable objects and complex objects, and its precision is governed by the resolution of the render-target-texture. The experimental results show the feasibility of GPU-based collision detection and its performance gain in real-time applications such as 3D games.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.3
• /
• pp.17-26
• /
• 2015

In this paper, we explain a volume rendering system for client-server environment. A single GPU-equipped PC works as a server which is based on the ideas that only a few concurrent users use a volume rendering system in a small hospital. As the clients, we used Android mobile devices such as smart phones. User events are transformed to rendering requests by the client application. When the server receives a rendering request, it renders the volume using the GPU. The rendered image is compressed to JPEG or PNG format so that we can save network bandwidth and reduce transfer time. In addition, we perform an event pruning method while a user is dragging the touch to enhance latency. The server compensates the pruning by interpolating the touch positions. As the result, real-time volume rendering is possible for 5 concurrent users on single GPU-equipped commodity hardware.