교원프로필

김광선 사진
교원에 대한 정보를 나타내는 표입니다.
성명 김광선
소속 컴퓨터공학과
전화번호 054-279-2260
E-mail gangsun@postech.ac.kr
Homepage

학력

  • 2012.02 ~ 2016.08 한국과학기술원 (박사-컴퓨터 아키텍처)
  • 2010.02 ~ 2012.02 한국과학기술원 (석사-컴퓨터 아키텍처)
  • 2005.03 ~ 2010.02 포항공과대학교 (학사-전자전기공학)

주요경력

  • 2016.09 ~ 2018.10 : ARM,INC.

전문분야

  • 컴퓨터 구조
  • 병렬 컴퓨터
  • 메모리 시스템
  • 인터커넥션 네트워크

학술지

국제전문학술지

  • Design and Analysis of Hybrid Flow Control for Hierarchical Ring Network-on-Chip, IEEE TRANSACTIONS ON COMPUTERS, , 65, 480-494 (2016)
  • Low-Overhead Network-on-Chip Support for Location-Oblivious Task Placement, IEEE TRANSACTIONS ON COMPUTERS, , 63, 1487-1500 (2014)

국내전문학술지

일반학술지

학술회의논문

  • TCEP: Traffic Consolidation for Energy-Proportional High-Radix Networks, Proceedings of 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), 0, 0, - (2018)
  • Toward standardized near-data processing with unrestricted data placement for GPUs, International Conference for High Performance Computing, Networking, Storage and Analysis, 0, 0, - (2017)
  • History-Based Arbitration for Fairness in Processor-Interconnect of NUMA Servers, Proceedings of 2017 Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems, 0, 0, 765-777 (2017)
  • Contention-based congestion management in large-scale networks, Proceedings of 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), 0, 0, - (2016)
  • Accelerating linked-list traversal through near-data processing, Proceedings of 2016 International Conference on Parallel Architecture and Compilation Techniques (PACT), 0, 0, - (2016)
  • Automatically Exploiting Implicit Pipeline Parallelism from Multiple Dependent Kernels for GPUs, Proceedings of 2016 International Conference on Parallel Architecture and Compilation Techniques (PACT), 0, 0, - (2016)
  • Transparent offloading and mapping (TOM): enabling programmer-transparent near-data processing in GPU systems, Proceedings of 2016 43rd International Symposium on Computer Architecture, 0, 0, 204-216 (2016)
  • iPAWS: Instruction-issue pattern-based adaptive warp scheduling for GPGPUs, Proceedings of 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA), 0, 0, - (2016)
  • Overcoming far-end congestion in large-scale networks, Proceedings of 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), 0, 0, - (2015)
  • Multi-GPU System Design with Memory Networks , Proceedings of 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture, 0, 0, 484-495 (2014)
  • Transportation-network-inspired network-on-chip, Proceedings of 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA), 0, 0, - (2014)
  • Memory-centric system interconnect design with hybrid memory cubes, Proceedings of the 22nd international conference on Parallel architectures and compilation techniques, 0, 0, 145-156 (2013)
  • Scalable on-chip network in power constrained manycore processors, Proceedings of the 3rd International Green Computing Conference, 0, 0, - (2012)
  • FlexiBuffer: reducing leakage power in on-chip network routers, Proceedings of the 48th Design Automation Conference, 0, 0, 936-941 (2011)

학회발표

단행본

연구실적

  • 김광선_신규부임교수 기자재지원_1차(학과), 포항공과대학교 (2018-2019)
  • 김광선_신규부임교수 연구비지원_1차(학과), 포항공과대학교 (2018-2019)
  • 김광선_신규부임교수 기자재지원(2차_대학), 포항공과대학교 (2019-2020)
  • 김광선_신규부임교수 기자재지원(2차_학과), 포항공과대학교 (2019-2020)
  • 김광선_신규부임교수 연구비지원(2차_학과), 포항공과대학교 (2019-2020)
  • 고성능 연산 가속기를 위한 이기종 적층 메모리 설계 연구, 재단법인한국연구재단 (2019-2020)
  • 고성능 연산 가속기를 위한 이기종 적층 메모리 설계 연구, 재단법인한국연구재단 (2020-2021)
  • 김광선_신규부임교수 기자재지원(3차_대학), 포항공과대학교 (2020-2021)
  • 김광선_신규부임교수 연구비지원(3차_학과), 포항공과대학교 (2020-2021)
  • 김광선_신규부임교수 연구비지원(3차_대학), 포항공과대학교 (2020-2021)
  • 학생인건비통합관리과제, 포항공대산학협력단 (2020-2040)
  • 4.17734 이월과제, 재단법인한국연구재단 (2020-2021)
  • 대용량GPU워크로드를위한 COMPUTE EXPRESS LINK(CXL)기반 메모리 확장연구, 에스케이하이닉스 주식회사 (2020-2022)
  • 연구개발과제[2015년 신설], 포항공과대학교 (2020-2045)

IP