전자통신동향분석 (Electronics and Telecommunications Trends)

한국전자통신연구원 (Electronics and Telecommunications Research Institute)
권호 표지
DOI QR코드

DOI QR Code

CCIX 연결망과 메모리 확장기술 동향

Trends of the CCIX Interconnect and Memory Expansion Technology

  • 김선영 (슈퍼컴퓨팅기술연구센터) ;
  • 안후영 (슈퍼컴퓨팅기술연구센터) ;
  • 전성익 (데이터중심컴퓨팅시스템연구실) ;
  • 박유미 (슈퍼컴퓨팅기술연구센터) ;
  • 한우종 (인공지능연구소)
  • 발행 : 2022.02.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

With the advent of the big data era, the memory capacity required for computing systems is rapidly increasing, especially in High Performance Computing systems. However, the number of DRAMs that can be used in a computing node is limited by the structural limitations of the hardware (for example, CPU specifications). Memory expansion technology has attracted attention as a means of overcoming this limitation. This technology expands the memory capacity by leveraging the external memory connected to the host system through hardware interface such as PCIe and CCIX. In this paper, we present an overview and describe the development trends of the memory expansion technology. We also provide detailed descriptions and use cases of the CCIX that provides higher bandwidth and lower latency than cases of the PCIe.

키워드

과제정보

본 연구 논문은 한국연구재단 슈퍼컴퓨터개발선도사업[2020M3H6A1084857, 초병렬 프로세서 기반 고집적 컴퓨팅 노드 및 시스템 개발] 및 한국전자통신연구원 내부연구과제(전략적선행투자사업)[21RS1100, 의료데이터 기반 인공지능 슈퍼컴퓨팅 기술 활성화 연구사업]의 일환으로 수행되었음.

참고문헌

  1. IDC, "Data age 2025: The evolution of data to life-critical," white paper, 2017.
  2. D. Zivanovic et al., "Main memory in HPC: Do we need more or could we live with less?," ACM Trans. Archit. Optim., vol. 14, no. 1, 2017, pp. 1-26. https://doi.org/10.1145/3023362
  3. Samsung Electronics, "Samsung unveils industry-first memory module incorporating new cxl interconnect standard," May 11, 2021, Available from: https://bit.ly/3uBo27J
  4. W. Kwon et al., "Gen-Z memory pool system architecture," in Proc. IEEE Int. Conf. Inf. Commun. Technol. Converg. (ICTC), (Jeju, South Korea), Oct. 2020.
  5. C. Hopkins, "The Machine seeks adventurous developers," June 8, 2017, Available from: https://www.hpe.com/us/en/insights/articles/new-computing-platform-seeks-adventurous-developers-1706.html [retrieved Dec. 13, 2021].
  6. Xilinx, "Versal: The first adaptive compute acceleration platform," white paper, 2020.
  7. CCIX Consortium, "CCIX base specification version 1.1," 2019.
  8. CXL Consortium, "CXL 2.0 specification," 2020.
  9. Gen-Z Consortium, "Gen-Z core specification 1.1," 2020.
  10. 김선영 외, "메모리 확장기술 동향," 대한전자공학회 추계학술대회, 2021. 11. 26.
  11. 김강호, "확장 메모리 풀 시스템 기술," Available from: https://itec.etri.re.kr/itec/sub02/sub02_01_1.do?t_id=1210-2021-00629#1
  12. CCIX Consortium, "SC20-CCIX 2.0: Transport agnostic interface in the intelligent accelerator era," Available from: https://www.youtube.com/watch?v=MUHgp3o35RA
  13. CCIX Consortium, "An introduction to CCIX," white paper, 2019.
  14. Persistent Memory Programming, Available from: https://pmem.io/
  15. CCIX and Real-World Application, Dec. 2019, available from: https://www.ccixconsortium.com/ccix-and-real-world-application/
  16. J. Defilippi, "Accelerating RedisEdge with CCIX," Arm TechCon, 2019.
  17. XilinxInc, Key-Value Store Acceleration with CCIX, Dec. 18, 2018, Available from: https://www.youtube.com/watch?v=drIu4vlubxE&list=PLRr5m7hDN9TLI3vuw1OqLbF7YcGi3UO9c&index=10
  18. M. Mittal, "Memory expansion and storag acceleration with CCIX Technology," in Proc. Int. Conf. High Perform. Comput., Netw., Storage, Anal. (SC19), (Denver, CO, USA), Nov. 2019.