• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.181-182
• /
• 2015

모바일 기기의 보급률과 성능이 급속도로 성장하면서 모바일 기기에서의 비디오 소비 또한 크게 증가하였다. 하지만, 전력과 공간을 줄이기 위해 설계된 모바일 플랫폼은 데스크톱 플랫폼과 비교하여 성능의 한계가 존재한다. 따라서 대용량 비디오 처리를 위해 SIMD 아키텍쳐를 이용하는 임베디드 GPU를 활용하여 이와 같은 한계를 극복하기 위한 고속화 연구가 많이 진행되고 있다. 저장된 데이터를 활용하는 영상처리는 GPU 뿐만 아니라 CPU가 반드시 함께 이용되어야 하며, 모바일 환경에서의 이기종 컴퓨팅 시스템은 프로세서 사이의 낮은 전송속도와 이로 인한 대기시간, 모바일 운영체제가 지원하는 데이터 형태의 필수적인 사용 등의 구조적 단점이 존재한다. 본 논문에서는 임베디드 GPU를 활용한 영상처리 고속화를 위해 임베디드 CPU측에서 병렬처리를 이용하여 앞서 설명한 단점들을 극복하고 실험결과로 모바일 이기종 컴퓨팅 구조에서 임베디드 CPU 활용이 전체적인 연산 효율을 증가시키는 결과를 보였다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.488-495
• /
• 2009

This paper presents a fast feature extraction method for autonomous mobile robots utilizing parallel processing and based on OpenMP, SSE (Streaming SIMD Extension) and CUDA programming. In the first step on CPU version, the algorithms and codes are optimized and then implemented by parallel processing. The parallel algorithms are debugged to maintain the same level of performance and the process for extracting key points and obtaining dominant orientation with respect to key points is parallelized. After extraction, a parallel descriptor via SSE instructions is constructed. And the GPU version also implemented by parallel processing using CUDA based on the SIFT. The GPU-Parallel descriptor achieves an acceleration up to five times compared with the CPU-Parallel descriptor, but it shows the lower performance than CPU version. CPU version also speed-up the four and half times compared with the original SIFT while maintaining robust performance.

• Journal of Broadcast Engineering
• /
• v.18 no.3
• /
• pp.362-371
• /
• 2013

This paper presents a framework of real-time augmented reality on 3-D mobile display with stereo camera tracking. In the framework, camera poses are jointly estimated with the geometric relationship between stereoscopic images, which is based on model-based tracking. With the estimated camera poses, the virtual contents are correctly augmented on stereoscopic images through image rectification. For real-time performance, stereo camera tracking and image rectification are efficiently performed using multiple threads. Image rectification and color conversion are accelerated with a GPU processing. The proposed framework is tested and demonstrated on a commercial smartphone, which is equipped with a stereoscopic camera and a parallax barrier 3-D display.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.4
• /
• pp.416-422
• /
• 2019

This paper proposes a GPU-based modeling and rendering of 3D clouds using procedural functions. The formation of clouds is based on modified noise function made with fbm(Fractional Brownian Motion). Those noise values turn into densities of droplets of liquid water, which is a critical parameter for forming the three different types of clouds. At the rendering stage, the algorithm applies the ray marching technique to decide the colors of cloud using density values obtained from the noise function. In this process, all lighting attenuation and scattering are calculated by physically based manner. Once we have the clouds, they are blended on the sky, which is also rendered physically. We also make the clouds moving in the sky by the wind force. All algorithms are implemented and tested on GPU using GLSL.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.253-259
• /
• 2009

In this paper, we propose a novel architecture of a general graphics shader processor without a dedicated hardware. Recently, mobile devices require the high performance graphics processor as well as the small size, low power. The proposed shader processor is a GP-GPU(General-Purpose computing on Graphics Processing Units) to execute the whole OpenGL ES 2.0 graphics pipeline by using shader instructions. It does not require the separate dedicate H/W such as rasterization on this fully programmable capability. The fully programmable 3D graphics shader processor can reduce much of the graphics hardware. The chip size of the designed shader processor is reduced 60% less than the sizes of previous processors.

• Journal of KIISE
• /
• v.44 no.6
• /
• pp.573-580
• /
• 2017

Despite the recent remarkable advances in the computing power of mobile devices, the heat and battery problems still restrict their performances, particularly compared to PCs. Therefore, in the application of the ray-tracing technique for high-quality rendering, the consideration of a method that traces only the secondary rays while the effects of the primary rays are generated through rasterization-based OpenGL ES rendering is worthwhile. Given that most of the rendering time is for the secondary-ray processing in such a method, a new volume-grid technique for dynamic scenes that enhances the tracing performance of the secondary rays with a low coherence is proposed here. The proposed method attempts to model all of the possible spatial secondary rays in a fixed number of sampling rays, thereby alleviating the visitation problem regarding all of the cells along the ray in a uniform grid. Also, a hybrid rendering pipeline that speeds up the overall rendering performance by exploiting the mobile-device CPU and GPU is presented.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.6
• /
• pp.325-334
• /
• 2016

Recently, Open Computing Language (OpenCL) has been proposed to provide a framework that supports heterogeneous computing platforms. By using an OpenCL framework, digital communication systems can support various protocols in a unified computing environment to achieve both high portability and high performance. This article introduces a parallel software decoder of Low Density Parity Check (LDPC) codes for China Multimedia Mobile Broadcasting (CMMB) on a heterogeneous platform. Each step of LDPC decoding has different parallelization characteristics. In this paper, steps suitable for task-level parallelization are executed on the CPU, and steps suitable for data-level parallelization are processed by the GPU. To improve the performance of the proposed OpenCL kernels for LDPC decoding operations, explicit thread scheduling, loop-unrolling, and effective data transfer techniques are applied. The proposed LDPC decoder achieves high performance by using heterogeneous multi-core processors on a unified computing framework.

• Electronics and Telecommunications Trends
• /
• v.35 no.3
• /
• pp.66-75
• /
• 2020

As the increasing expectations of a practical AI (Artificial Intelligence) service makes AI algorithms more complicated, an efficient processor to process AI algorithms is required. To meet this requirement, processors optimized for parallel processing, such as GPUs (Graphics Processing Units), have been widely employed. However, the GPU has a generalized structure for various applications, so it is not optimized for the AI algorithm. Therefore, research on the development of AI processors optimized for AI algorithm processing has been actively conducted. This paper briefly introduces an AI processor especially for inference acceleration, developed by the Electronics and Telecommunications Research Institute, South Korea., and other global vendors for mobile and server platforms. However, the GPU has a generalized structure for various applications, so it is not optimized for the AI algorithm. Therefore, research on the development of AI processors optimized for AI algorithm processing has been actively conducted.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.530-533
• /
• 2011

방사형 그라디언트 페인트(radial gradient paint)는 벡터 그래픽스(vector graphics)에서 적은 정보로 다양한 효과를 적용시킬 수 있는 방법이다. 기본적으로 이 방법은 곱하기, 나누기, 제곱근 등의 복잡한 연산이 필요하기 때문에 모바일 같은 저성능 환경에 적합하지 않았다. 하지만 최근 모바일 기기들은 SIMD 연산 지원 및 고성능의 GPU 탑재 등으로 성능이 향상됨에 따라 이러한 문제를 해결할 수 있게 되었다. 본 논문은 ARM의 SIMD연산인 NEON을 이용하여 최대 2.6배의 성능을 가속시켰으며 GPU의 쉐이더를 이용하여 4.9배의 성능을 가속하였다.