• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.3
• /
• pp.11-19
• /
• 2023

Recently with the rapid advancement of artificial intelligence (AI) technologies such as Chat GPT, AI semiconductors have become important. AI technologies require the ability to process large volumes of data quickly, as they perform tasks such as big data processing, deep learning, and algorithms. However, AI semiconductors encounter challenges with excessive power consumption and data bottlenecks during the processing of large-scale data. Thus, the latest packaging technologies are required for AI semiconductor computations. In this study, the authors have described packaging technologies applicable to AI semiconductors, including interposers, Through-Silicon-Via (TSV), bumping, Chiplet, and hybrid bonding. These technologies are expected to contribute to enhance the power efficiency and processing speed of AI semiconductors.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.36-44
• /
• 2024

Recently, large-scale artificial intelligence (AI) such as ChatGPT have been developed, and as AI is used across various industrial fields, attention is focused on AI chips (semiconductors). AI chips refer to chips designed for calculations for AI algorithms, and many companies at domestic and abroad, such as NVIDIA, Tesla, and ETRI, are developing AI chips. In this paper, we survey research trends on nine types of AI chips. Currently, many attempts have been made to improve the computational performance of most AI chips, and semiconductors for specific purposes are also being designed. In order to compare various AI semiconductors, each chip is analyzed in terms of operation unit, speed, power, and energy efficiency. We introduce currently existing optimization methodologies for AI computation. Based on this, future research directions for AI semiconductors are presented in this paper.

• Electronics and Telecommunications Trends
• /
• v.39 no.2
• /
• pp.66-76
• /
• 2024

Artificial-intelligence (AI) semiconductors are crucial for securing national core competitiveness, including dominating the AI and data ecosystem and succeeding in the Digital New Deal. When examining the macroenvironment, the global division of labor in the semiconductor industry has weakened owing to the technological competition between the United States and China. Major countries are aiming to build the entire semiconductor ecosystem around their territories. As a result, these countries are formulating policy goals tailored to their realities and actively pursuing key policies such as research and development, securing manufacturing bases, workforce development, and financial support. These policies also focus on intercountry cooperation and bold government policy support, which is deemed essential. To secure core competitiveness in AI semiconductors, South Korea needs to examine the policy directions of major countries and actively formulate and implement policies for this semiconductor industry.

• Electronics and Telecommunications Trends
• /
• v.38 no.5
• /
• pp.1-11
• /
• 2023

The emergence of generative hyperscale artificial intelligence (AI) has enabled new services, such as image-generating AI and conversational AI based on large language models. Such services likely lead to the influx of numerous users, who cannot be handled using conventional AI models. Furthermore, the exponential increase in training data, computations, and high user demand of AI models has led to intensive hardware resource consumption, highlighting the need to develop domain-specific semiconductors for hyperscale AI. In this technical report, we describe development trends in technologies for hyperscale AI processors pursued by domestic and foreign semiconductor companies, such as NVIDIA, Graphcore, Tesla, Google, Meta, SAPEON, FuriosaAI, and Rebellions.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.382-384
• /
• 2021

AI (Artificial Intelligence)기술이 상용화되면서 최근 기업들은 AI 모델의 기능을 서비스화하여 제공하고 있다. 하지만 최근 이러한 서비스를 이용하여 기업이 자본을 투자해 학습시킨 AI 모델을 탈취하는 공격이 등장하여 위협이 되고 있다. 본 논문은 최근 연구되고 있는 이러한 모델 탈취 공격들에 대해 공격자의 정보를 기준으로 분류하여 서술한다. 또한 본 논문에서는 모델 탈취 공격에 대응하기 위해 다양한 관점에서 시도되는 방어 기법들에 대해 서술한다.

• Electronics and Telecommunications Trends
• /
• v.37 no.1
• /
• pp.53-62
• /
• 2022

With increasing size of transformer-based neural networks, a light-weight algorithm and efficient AI accelerator has been developed to train these huge networks in practical design time. In this article, we present a survey of state-of-the-art research on the low-precision computational algorithms especially for floating-point formats and their hardware accelerator. We describe the trends by focusing on the work of two leading research groups-IBM and Seoul National University-which have deep knowledge in both AI algorithm and hardware architecture. For the low-precision algorithm, we summarize two efficient floating-point formats (hybrid FP8 and radix-4 FP4) with accuracy-preserving algorithms for training on the main research stream. Moreover, we describe the AI processor architecture supporting the low-bit mixed precision computing unit including the integer engine.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.235-246
• /
• 2023

In the rapid technological development of artificial intelligence (AI), electric vehicles, and robots based the fourth industrial revolution, semiconductors determine the core performance, and semiconductor competitiveness is directly related to national competitiveness. However, the Korean semiconductor industry has continuously weakened its competitiveness in the system semiconductor field, excluding memory semiconductors, so in this study, a new smart contract basedblockchain business model to engage the global market, which is the most urgent need for the growth of Korean fabless system semiconductor industry in recession. F-SBM (Fabless-Smart contract based Blockchain Model) proposed. In this study, through the new F-SBM, it was verified how to engage new customers for fabless firms through smart contract based consortium blockchain regarding technology, economy, and reliability items of fabless. This model has great significance in improving the high entry barriers to engaging new customers for the long-cherished desire of the Korean fabless system semiconductor industry and deriving new growth solutions.

• Proceedings of the Korean Society Of Semiconductor Equipment Technology
• /
• 2005.09a
• /
• pp.89-92
• /
• 2005

The AIN/AI thin films were prepared at various conditions, such as $N_2$ gas flow rate [$N_2(N_2+Ar)$] from 0.6 to 0.9, a substrate temperature ranging from room temperature to $300^{\circ}C$ and working pressure 1mTorr. We estimated crystallographic characteristics and c-axis preferred orientations of AIN/AI thin films as function of AI electrode surface roughness. The optimal processing conditions for AI electrode were found at substrate temperature of $300^{\circ}C$ sputtering power of 100W and a working pressure of 2mTorr. In these conditions, we obtained the c-axis preferred orientation of $AIN/AI/SiO_2/Si$ thin film about 4 degree.

• Electronics and Telecommunications Trends
• /
• v.38 no.5
• /
• pp.12-22
• /
• 2023

The development of neural networks is evolving towards the adoption of transformer structures with attention modules. Hence, active research focused on extending the concept of lightweight neural network algorithms and hardware acceleration is being conducted for the transition from conventional convolutional neural networks to transformer-based networks. We present a survey of state-of-the-art research on lightweight neural network algorithms and hardware architectures to reduce memory usage and accelerate both inference and training. To describe the corresponding trends, we review recent studies on token pruning, quantization, and architecture tuning for the vision transformer. In addition, we present a hardware architecture that incorporates lightweight algorithms into artificial intelligence processors to accelerate processing.

• Electronics and Telecommunications Trends
• /
• v.35 no.7
• /
• pp.13-22
• /
• 2020

There is no denying that computing power has been a crucial driving force behind the development of artificial intelligence today. In addition, artificial intelligence (AI) semiconductors and computing systems are perceived to have promising industrial value in the market along with rapid technological advances. Therefore, success in this field is also meaningful to the nation's growth and competitiveness. In this context, ETRI's AI strategy proposes implementation directions and tasks with the aim of strengthening the technological competitiveness of AI semiconductors and computing systems. The paper contains a brief background of ETRI's AI Strategy #2, research and development trends, and key tasks in four major areas: 1) AI processors, 2) AI computing systems, 3) neuromorphic computing, and 4) quantum computing.