프로세서 노드 상황을 고려하는 저비용 파이프라인 브로드캐스트 하드웨어 엔진

Park, Jongsu 한국정보통신학회 2020 한국해양정보통신학회논문지 Vol.24 No.8

This paper presents a low cost hardware message passing engine of enhanced atomic pipelined broadcast based on processing node status. In this algorithm, the previous atomic pipelined broadcast algorithm is modified to reduce the waiting time until next broadcast communication. For this, the processor change the transmission order of processing nodes based on the nodes' communication channel. Also, the hardware message passing engine architecture of the proposed algorithm is modified to be adopted to multi-core processor. The synthesized logic area of the proposed hardware message passing engine was reduced by about 16%, compared by the pre-existing hardware message passing engine.

프로세서 노드 상황을 고려하는 효율적인 메시지 스캐터 및 개더 알고리즘

Park, Jongsu 한국정보통신학회 2022 한국해양정보통신학회논문지 Vol.26 No.4

To maximize performance in a high-performance multicore processor system. it is essential to enable effective data communication between processing cores. Data communication between processor nodes can be broadly classified into collective and point-to-point communications. Collective communication comprises scattering and gathering. This paper presents a efficient message scattering and gathering based on processing node status. In the proposed algorithms, the transmission order is changed according to the data size of the pre-existing communication, to reduce the waiting time required until the collective communications begin. From the simulation, the performances of the proposed message scattering and gathering algorithms were improved by approximately 71.41% and 69.84%.

Processing-Node Status-based Message Scattering and Gathering for Multi-processor Systems on Chip

Park, Jongsu The Korea Institute of Information and Commucation 2019 Journal of information and communication convergen Vol.17 No.4

This paper presents processing-node status-based message scattering and gathering algorithms for multi-processor systems on chip to reduce the communication time between processors. In the message-scattering part of the message-passing interface (MPI) scatter function, data transmissions are ordered according to the proposed linear algorithm, based on the processor status. The MPI hardware unit in the root processing node checks whether each processing node's status is 'free' or 'busy' when an MPI scatter message is received. Then, it first transfers the data to a 'free' processing node, thereby reducing the scattering completion time. In the message-gathering part of the MPI gather function, the data transmissions are ordered according to the proposed linear algorithm, and the gathering is performed. The root node receives data from the processing node that wants to transfer first, and reduces the completion time during the gathering. The experimental results show that the performance of the proposed algorithm increases at a greater rate as the number of processing nodes increases.

프로세서 노드 상황을 고려하는 저비용 파이프라인 브로드캐스트 하드웨어 엔진

Park, Jongsu 한국정보통신학회 2020 한국정보통신학회논문지 Vol.24 No.8

This paper presents a low cost hardware message passing engine of enhanced atomic pipelined broadcast based on processing node status. In this algorithm, the previous atomic pipelined broadcast algorithm is modified to reduce the waiting time until next broadcast communication. For this, the processor change the transmission order of processing nodes based on the nodes' communication channel. Also, the hardware message passing engine architecture of the proposed algorithm is modified to be adopted to multi-core processor. The synthesized logic area of the proposed hardware message passing engine was reduced by about 16%, compared by the pre-existing hardware message passing engine.

Provisioning of Subscriber-Level QoS Guarantees on Ethernet

Jongsu Park,Tae-Hyun Kwon,Won-Young Chung,Dae-Geun Park,Yong-Surk Lee 대한전자공학회 2007 ITC-CSCC :International Technical Conference on Ci Vol.2007 No.7

A novel subscriber-based quality-of-service provisioning scheme on Ethernet LANs is proposed. Our proposal can measure the bandwidths being used by subscribers by classifying Ethernet frames for the subscribers in real-time. Therefore, this scheme easily provides not only equal bandwidths for all subscribers, but also different bandwidths for each of the subscribers on Ethernet LANs.

Excellent Brightness with Shortening Lifetime of Textured Zn₂SiO₄:Mn²⁺Phosphor Films on Quartz Glass

Park, Jehong,Park, Kwangwon,Lee, Jaebum,Kim, Jongsu,Kim, Seongsin Margaret,Kung, Patrick IOP Publishing 2010 Japanese journal of applied physics Vol.49 No.r4

Hybrid Dynamic Branch Prediction to Reduce Destructive Aliasing

Park, Jongsu The Korea Institute of Information and Commucation 2019 한국정보통신학회논문지 Vol.23 No.12

This paper presents a prediction structure with a Hybrid Dynamic Branch Prediction (HDBP) scheme which decreases the number of stalls. In the application, a branch history register is dynamically adjusted to produce more unique index values of pattern history table (PHT). The number of stalls is also reduced by using the modified gshare predictor with a long history register folding scheme. The aliasing rate decreased to 44.1% and the miss prediction rate decreased to 19.06% on average compared with the gshare branch predictor, one of the most popular two-level branch predictors. Moreover, Compared with the gshare, an average improvement of 1.28% instructions per cycle (IPC) was achieved. Thus, with regard to the accuracy of branch prediction, the HDBP is remarkably useful in boosting the overall performance of the superscalar processor.

반도체 칩 기능 시험의 오류 디버깅 시 Single Long Scan Chain 활용 방안

박종수(Jongsu Park) ICT플랫폼학회 2023 ICT플랫폼학회 하계학술발표대회논문집 Vol.10 No.2

반도체 칩의 불량 여부를 판별하기 위하여 후공정 단계에서 웨이퍼 테스트를 수행한다. 이때 대표적으로 반도체 기능 시험과 스캔 시험이 수행된다. 스캔 시험은 제조상의 불량 여부 판별을 전문적으로 수행하기 위한 시험 방법으로써, ASIC 설계 단계에서 디지털 로직 중 D-플립플롭을 스캔 시험을 지원하는 D-플립플롭으로 모두 변경 후 반도체의 기능 동작 외 별도의 스캔 시프트 동작이 추가되어 시험이 가능해진다. 반도체 칩 내부의 모든 플립플롭은 이 스캔 시프트 동작에 참여하게 되며, 이 스캔 시프트 동작을 지원하기 위해 모든 플립플롭은 스캔 시프트 체인에 연결된다. 일반적으로 스캔 시프트 체인은 플립플롭 수백개에서 수천개 단위로 분할된다. 본 논문에서는 분할되어 있는 스캔 시프트 체인을 하나의 긴 시프트 체인으로 연결하여 기능 시험 시 디버깅에 활용할 수 있는 방안을 제안한다.

국제적 디지털 거래에서의 고정사업장 과세 문제

박종수(Park Jongsu),김신언(Kim Shineon) 한국세법학회 2015 조세법연구 Vol.21 No.3

기술발달과 더불어 디지털콘텐츠와 같은 권리와 전자적 용역을 웹서버 등의 가상공간을 통해 공급할 수 있게 되어 해당 국가에 고정사업장을 두지 않고도 사업 활동을 할 수 있게 되었다. 따라서 다국적기업이 고정사업장을 가지고 있지 않은 경우 소비지국에서 과세할 수 없는 점을 악용하는 사례도 발생하고 있다. 최근 OECD와 G20BEPS회의에서 디지털 경제에서 발생할 수 있는 조세회피문제와 그 해결방안을 검토한 것도 이러한 맥락에서이다. 국제적 디지털 거래의 특성상 서버와 같은 가상공간에 대한 과세권은 OECD의 고정사업장 개념에 따라 단순하게 물리적인 기반으로만 고정사업장을 정의할 수 없는 상황이 존재한다. 따라서 본 논문은 서버상의 웹사이트가 고정사업장의 구성요건을 충족시키는 국내에서 소비되는 재화와 용역임에도 불구하고 과세권을 행사하기 어려운 문제점과, 고정사업장을 구성하지 않는 예비적이고 보조적인 활동에 대하여 현행 판례와 국세청의 입장을 비교해서 이에 대한 보완점을 제시하고,국제적 디지털 거래에서 고정사업장의 개념변화에 맞는 입법의 필요성을 강조하였다. 최근 OECD는 가이드라인을 통해 비거주자인 외국사업자에 대하여 B2C거래에서 용역 및 무형자산을 공급하는 경우에 가장 효과적이고 효율적인 과세를 위한 접근방법이 사업자등록에 근거한 과세구조임을 제시하고 있다. 이러한 과세구조는 외국사업자에게 과세권을 갖는 국가에서 사업자등록과 신고·납부할 것을 요구하고 있다. 따라서 최근 신설된「부가가치세법」제53조의 2“전자적 용역을 공급하는 국외사업자의 용역공급과 사업자등록 등에 관한 특례” 규정도 그러한 의미에서「부가가치세법」상 외국사업자에게 부가가치세를 효과적으로 과세하기 위한 시도로 받아들일 수 있다. 그러나 신설규정에 의하여 사업장을 등록한 경우「법인세법」과「소득세법」상 고정사업장으로 오인할 수 있는 등 해석상의 문제점이 있음을 지적하고 이를 개선할 것을 주장하였다. This study is to investigate controversies surrounding digitalized products and services on a permanent establishment especially when it supplies products and services to foreign countries which do not have establishments in Korea. Generally, custom can legislate the burden of the tax on products when they are imported through cross-border. However, when they are changed into digitalized rights and services, the custom cannot recognize the transaction. Therefore, it is possible to use the products and services without paying tax through web server in a foreign country. Furthermore, the internet and relevant economy are increasing and the characteristics of transactions of digitalized contents are changeable and complicated in the modern society. Now, the traditional concept of permanent establishment cannot deal with these problems. OECD and G20 countries held Base Erosion and Profit Shifting Projects in 2014 to cope with these problems and suggested the solution to the tax challenges of the digital economy. The multinational corporations are trying to abuse the concept of the permanent establishments to avoid tax because the government cannot impose the burden of tax on foreign companies which do not have establishments in the country. If they use the internet server to supply the digitalized services and contents such as e-book, games, etc., many countries will take pains to classify the deals within their countries’ revenue power. This study will show the solutions to the problems which the new statute cannot overcome regarding the special issues and the available developments and inspect the precedent which is not compatible with the Revenue’s restatements and analysis in the field of web server. Recently, Korea Revenue legislated Article 53-2 in VAT called Special Provision for Electronic Services and Rights provided by foreign businesses simplified registration last December. It is anticipated to solve the logical contradiction of the reverse charge (self-assessment) and strengthen the destination principle of taxation. However, the statute has some problems which cause confusion when people interpret the concept of establishment in VAT compared with the permanent establishment in Corporation Tax and income Tax rules. Therefore, the government has to specify the details of the differences between the simplified registration and permanent establishment.

고려시대 남한강 유역의 불교사원 유적

박종수(Park Jongsu) 대한건축학회 2017 建築 Vol.61 No.9