• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.142-148
• /
• 2023

In this paper, we identify performance issues in executing compute kernels from PolyBench, which includes compute kernels that are the core computational units of various data-intensive workloads, such as deep learning and data-intensive applications, on Processing-in-Memory (PIM) devices. Therefore, using our in-house simulator, we measured and compared the various performance metrics of workloads based on traditional out-of-order and in-order processors with Processing-in-Memory-based systems. As a result, the PIM-based system improves performance compared to other computing models due to the short-term data reuse characteristic of computational kernels from PolyBench. However, some kernels perform poorly in PIM-based systems without a multi-layer cache hierarchy due to some kernel's long-term data reuse characteristics. Hence, our evaluation and analysis results suggest that further research should consider dynamic and workload pattern adaptive approaches to overcome performance degradation from computational kernels with long-term data reuse characteristics and hidden data locality.

• Journal of Distribution Research
• /
• v.17 no.3
• /
• pp.93-113
• /
• 2012

Early conflict research in channel and organization area have focused on the definition of conflict construct, its cause, consequence and identified conflict resolution management. Recent studies about conflict, however, have explored new assumption of complexity, a multidimensional conflict construct, contextual conflict management strategies, positive and negative conflict/consequence, and the conflict resolution strategy. Although many literatures exists on channel conflict resolution, little research has been done about relationship learning and performance from conflict resolution perspective. This study explores how channel members can achieve a relationship learning, as a conflict resolution mechanism, which enhance co-created value in marketing channel relationship. Therefore we propose that conflict resolution strategies(collaborating behavior and avoiding behavior) influence channel performance(effectiveness and efficiency) through relationship learning processes(learning via information exchange, joint interpretation and coordination, relationship-specific knowledge memory), in view of buyer-seller relationship. The research model is shown at

• Proceedings of the Korea Environmental Mutagen Society Conference
• /
• 2004.05a
• /
• pp.74-75
• /
• 2004

• Natural Product Sciences
• /
• v.16 no.2
• /
• pp.93-98
• /
• 2010

The Chongmyung-tang (CMT) has been used as an oriental herbal medicine for the purpose of enhanced learning and memory. Recently, since fermentation may give a positive effect on pharmacological actions of herbal medicine, many studies are focused to find fermented medicinal herbs with improved bioactivity. In the present study, memory enhancing, antioxidant and reducing power activity of CMT and fermented CMT with Aspergillus oryzae (FCMT-A) or Saccharomyces cerevisiae (FCMT-S) were determined. To evaluate the memory enhancing activities of CMT, FCMT-A and FCMT-S, we performed passive avoidance test using scopolamine induced amnesia model. Administration of CMT, FCMT-A and FCMT-S showed a significant memory enhancing effect about 72.5, 78.3, 71.8% of the normal group respectively. CMT, FCMT-A and FCMT-S also exhibited strong $DPPH{\bullet}$, ${\bullet}{O_2}^-$, $NO^{\codt}$, $ABTS^{{\cdot}+}$ scavenging activities and reducing ower. It was also found that fermented CMT has slightly higher scavenging activities on $DPPH{\bullet}$, $ABTS^{{\cdot}+}$ radicals compared to CMT. These results revealed that CMT, FCMT-A and FCMT-S had memory enhancing and radical scavenging activities. In addition, the fermentation of CMT was more or less important for elevated memory enhancing and antioxidant activities of CMT.

• Journal of Digital Convergence
• /
• v.7 no.3
• /
• pp.49-60
• /
• 2009

The aim of this study was to develop a model for teaching-teaming by applying Ubiquitous at a learning experience field, in which connect characteristics of both ubiquitous application learning and experience teaming, making use of them. A literature survey of concepts was conducted, with the main areas to find out relationships between ubiquitous application learning and experience learning. Experience learning by applying ubiquitous learning methods maximizes its efficiency of experience learning in considering ubiquitous learning methods's characteristics of dynamic, interaction, sharing. Also it makes communications through positive participation and active interaction, and leads to a process of internal examination. The research data suggests that critical factors of experiencing learning applying ubiquitous are acquiring information and memory, information integration and exquisiteness, emotional and social activity, producing activity, help activity.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.456-462
• /
• 2008

The classification is that a new data is classified into one of given classes and is one of the most generally used data mining techniques. Memory-Based Reasoning (MBR) is a reasoning method for classification problem. MBR simply keeps many patterns which are represented by original vector form of features in memory without rules for reasoning, and uses a distance function to classify a test pattern. If training patterns grows in MBR, as well as size of memory great the calculation amount for reasoning much have. NGE, FPA, and RPA methods are well-known MBR algorithms, which are proven to show satisfactory performance, but those have serious problems for memory usage and lengthy computation. In this paper, we propose DPA (Dynamic Partition Averaging) algorithm. it chooses partition points by calculating GINI-Index in the entire pattern space, and partitions the entire pattern space dynamically. If classes that are included to a partition are unique, it generates a representative pattern from partition, unless partitions relevant partitions repeatedly by same method. The proposed method has been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory and FPA, and RPA.

• Animal cells and systems
• /
• v.8
• /
• pp.14-14
• /
• 2004

• The Korea Genome Conference
• /
• 2005.09a
• /
• pp.38-38
• /
• 2005

• Proceedings of the PSK Conference
• /
• 2005.11a
• /
• pp.235-235
• /
• 2005

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.4
• /
• pp.99-102
• /
• 2018

Caffe is a neural net learning software which is widely used in academic researches. The GPU memory capacity is one of the most important aspects of designing neural net architectures. For example, many object detection systems require to use less than 12GB to fit a single GPU. In this paper, we extended Caffe to allow to use more than 12GB GPU memory. To verify the effectiveness of the extended software, we executed some training experiments to determine the learning efficiency of the object detection neural net software using a PC with three GPUs.