• Journal of Computing Science and Engineering
• /
• v.11 no.2
• /
• pp.69-77
• /
• 2017

Recent GPUs have adopted cache memory to benefit general-purpose GPU (GPGPU) programs. However, unlike CPU programs, GPGPU programs typically have considerably less temporal/spatial locality. Moreover, the L1 data cache is used by many threads that access a data size typically considerably larger than the L1 cache, making it critical to bypass L1 data cache intelligently to enhance GPU cache performance. In this paper, we examine GPU cache access behavior and propose a simple hardware-based GPU cache bypassing method that can be applied to GPU applications without recompiling programs. Moreover, we introduce a hybrid method that integrates static profiling information and hardware-based bypassing to further enhance performance. Our experimental results reveal that hardware-based cache bypassing can boost performance for most benchmarks, and the hybrid method can achieve performance comparable to state-of-the-art compiler-based bypassing with considerably less profiling cost.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.4
• /
• pp.326-334
• /
• 1991

We propose an optical Asynchronous Transfer Mode(ATM) switching system using free-space optics and an output buffer memory. The distributor system in the switching fabric was analyzed using the Huygens-Fresnel principle and lens transformation. For monochromatic illumination, a pattern similar to the Fourier transform of the input distribution was observed across the output plane. A spatially broadened intensity distribution across the the output plane can be expected when the system is illminated with a partially coherent, quasimonochromatic beam. Spatially coherent pulses as short as 100fs can propagate through the distributor without severe spatial broadening.

• Journal of Korea Multimedia Society
• /
• v.17 no.1
• /
• pp.1-7
• /
• 2014

Hippocampus is an important part of brain which is related with early memory storage and spatial navigation. By observing the anatomy of hippocampus, some brain diseases effecting human memory (e.g. Alzheimer, schizophrenia, etc.) can be diagnosed and predicted earlier. The diagnosis process is highly related with hippocampus segmentation. In this paper, hippocampus segmentation using Active Shape Model, which not only works based on image intensity, but also by using prior knowledge of hippocampus shape and intensity from the training images, is proposed. The results show that ASM is applicable in segmenting hippocampus from whole brain MR image. It also shows that adding more images in the training set results in better accuracy of hippocampus segmentation.

• ETRI Journal
• /
• v.28 no.6
• /
• pp.697-708
• /
• 2006

Various adaptive mesh refinement techniques are often employed in numerical simulations for increasing spatial and temporal resolution beyond the limits imposed by available CPU time and memory space. Recently, an octree-based adaptive mesh structure was successfully used in fluid animation to place more grid cells efficiently in visually interesting regions of fluids. In an attempt to optimize the use of computational resources further in fluid animation, this paper extends this adaptive technique by modifying the mesh refinement scheme so that the camera's viewing properties are dynamically exploited during the simulation. Based on a simple adaptive mesh structure, we show that the new meshing strategy can save a substantial amount of computation time and memory space by using a view-dependent adaptive approach. The experimental results reveal that the proposed technique provides a good compromise between the computational effort and the simulation's fidelity, and may be used quite effectively in 3D animation production.

• Molecules and Cells
• /
• v.28 no.6
• /
• pp.501-507
• /
• 2009

Fragile X syndrome (FXS) is caused by a lack of the fragile X mental retardation protein (FMRP) due to silencing of the Fmr1 gene. As an RNA binding protein, FMRP is thought to contribute to synaptic plasticity by regulating plasticity-related protein synthesis and other signaling pathways. Previous studies have mostly focused on the roles of FMRP within the hippocampus - a key structure for spatial memory. However, recent studies indicate that FMRP may have a more general contribution to brain functions, including synaptic plasticity and modulation within the prefrontal cortex. In this brief review, we will focus on recent studies reported in the prefrontal cortex, including the anterior cingulate cortex (ACC). We hypothesize that alterations in ACC-related plasticity and synaptic modulation may contribute to various forms of cognitive deficits associated with FXS.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.6 no.4
• /
• pp.252-256
• /
• 2006

A low-power ECC check bit generator is presented with competent DRAM implementation with minimal speed loss, area overhead and power consumption. The ECC used in the proposed scheme is a variant form of the minimum weight column code. The spatial and temporal correlations of input data are analyzed and the input paths of the check bit generator are ordered for the on-line adaptable power savings up to 24.4% in the benchmarked cases. The chip size overhead is estimated to be under 0.3% for a 80nm 1Gb DRAM implementation.

• BMB Reports
• /
• v.42 no.5
• /
• pp.239-244
• /
• 2009

New neurons are continually generated in the subgranular zone of the dentate gyrus and in the subventricular zone of the lateral ventricles of the adult brain. These neurons proliferate, differentiate, and become integrated into neuronal circuits, but how they are involved in brain function remains unknown. A deficit of adult hippocampal neurogenesis leads to defective spatial learning and memory, and the hippocampi in neuropsychiatric diseases show altered neurogenic patterns. Adult hippocampal neurogenesis is not only affected by external stimuli but also regulated by internal growth factors including BDNF, VEGF and IGF-1. These factors are implicated in a broad spectrum of pathophysiological changes in the human brain. Elucidation of the roles of such neurotropic factors should provide insight into how adult hippocampal neurogenesis is related to psychiatric disease and synaptic plasticity.

• School Mathematics
• /
• v.2 no.2
• /
• pp.489-508
• /
• 2000

With the increased use of computational technology, many educators question about spending large amount of class time for dealing with computational algorithms in elementary school math classroom at the expense of more holistic aspects of mathematics such as number sense, spatial sense, problem solving and data management. This paper introduce the new method for learning addition and subtraction so called ‘Mrs. Weill’s Hill’, which is believed as a suitable remedial method for children with mathematical learning disabilities, with perceptual problems, or with limited working memory capacities. This method provides children with external memory strategies by allowing them to solve the addition and subtraction problems in a stage by stage fashion with as many steps as they require. It also gives the child greater flexibility in the solution process and thus helps reduce anxiety.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4098-4116
• /
• 2020

Mobile devices such as smartphones are very attractive targets for augmented reality (AR) services, but their limited resources make it difficult to increase the number of objects to be recognized. When the recognition process is scaled to a large number of objects, it typically requires significant computation time and memory. Therefore, most large-scale mobile AR systems rely on a server to outsource recognition process to a high-performance PC, but this limits the scenarios available in the AR services. As a part of realizing large-scale standalone mobile AR, this paper presents a solution to the problem of accuracy, memory, and speed for large-scale object recognition. To this end, we design our own basic feature and realize spatial locality, selective feature extraction, rough pose estimation, and selective feature matching. Experiments are performed to verify the appropriateness of the proposed method for realizing large-scale standalone mobile AR in terms of efficiency and accuracy.

• Proceedings of the Optical Society of Korea Conference
• /
• 2003.02a
• /
• pp.72-73
• /
• 2003

In volume holographic memory (VHM), two-dimensional data array (i.e. data page) is used for the recording and the retrieving process with the aid of spatial light modulator (SLM) and CCD camera. Due to this two-dimensional parallel data processing, burst errors in this system also have two-dimensional characteristics in a data page domain. In this paper, we present a channel model of the burst noise and burst error for the VHM system using disk type recording media. (omitted)