DOI QR코드

DOI QR Code

인공지능 컴퓨팅 프로세서 반도체 동향과 ETRI의 자율주행 인공지능 프로세서

Trends in AI Computing Processor Semiconductors Including ETRI's Autonomous Driving AI Processor

  • 발행 : 2017.12.01

초록

Neural network based AI computing is a promising technology that reflects the recognition and decision operation of human beings. Early AI computing processors were composed of GPUs and CPUs; however, the dramatic increment of a floating point operation requires an energy efficient AI processor with a highly parallelized architecture. In this paper, we analyze the trends in processor architectures for AI computing. Some architectures are still composed using GPUs. However, they reduce the size of each processing unit by allowing a half precision operation, and raise the processing unit density. Other architectures concentrate on matrix multiplication, and require the construction of dedicated hardware for a fast vector operation. Finally, we propose our own inAB processor architecture and introduce domestic cutting-edge processor design capabilities.

키워드

참고문헌

  1. 황민규, "홍성주 SK하이닉스 부사장 "반도체 미세공정 한계...극자외선 노광장비 개발 도입 서둘러야"," Chosun Biz, 2017. 2. 8.
  2. J. Dongarra, "Report on the Sunway TaihuLight System," University of Tennessee, Tech Report UT-EECS-16-742, June 2016.
  3. H. Fu et al., "The Sunway TaihuLight Supercomputer: System and Applications," Sci. China Inform. Sci., vol. 59, July 2016.
  4. NVIDIA Corporation, "NVIDIA Tesla P100 Whitepaper," WP-08019-001_v01.1, 2016, pp. 1-45.
  5. N.P. Jouppi et al., "In-datacenter Performance Analysis of a Tensor Processing Unit," Int. Symp. Comput. Archit. (ISCA), Toronto, Canada, June 24-28, 2017, pp. 1-12.
  6. D. Moloney et al., "Myriad 2: Eye of the Computational Vision Storm," Hot Chips Symp., Cupertino, CA, USA, Aug. 10-12, 2014.
  7. Qualcomm Technologies, Inc., "Snapdragon 835 Mobile Platform Product Brief," www.qualcomm.com, 2016.
  8. M. Humrick, and R. Smith, "The Qualcomm Snapdragon 835 Performance Preview," Anandtech, 2017. 3. 22.
  9. D.S. Modha, "Introducing a Brain-inspired Computer," IBM Research, 2015.
  10. Y. Chen, T. Chen, Z. Xu, N. Sun, and O. Temam, "DianNao Family: Energy-Efficient Hardware Accelerators for Machine Learning," Commun. ACM, vol. 59, no. 11, Nov. 2016, pp. 105-112. https://doi.org/10.1145/2996864
  11. S. Liu et al., "Cambricon: An Instruction Set Architecture for Neural Networks," Int. Symp. Comput. Archit. (ISCA), Seoul, Rep. of Korea, June 18-22, 2016, pp. 393-405.