[논문]Z-PIM: A Sparsity-Aware Processing-in-Memory Architecture With Fully Variable Weight Bit-Precision for Energy-Efficient Deep Neural Networks

Kim, Ji-Hoon; Lee, Juhyoung; Lee, Jinsu; Heo, Jaehoon; Kim, Joo-Young

doi:10.1109/jssc.2020.3039206

[해외논문] Z-PIM: A Sparsity-Aware Processing-in-Memory Architecture With Fully Variable Weight Bit-Precision for Energy-Efficient Deep Neural Networks

IEEE journal of solid-state circuits, v.56 no.4, 2021년, pp.1093 - 1104

Kim, Ji-Hoon (Korea Advanced Institute of Science and Technology, Daejeon, South Korea) , Lee, Juhyoung (Korea Advanced Institute of Science and Technology, Daejeon, South Korea) , Lee, Jinsu (Korea Advanced Institute of Science and Technology, Daejeon, South Korea) , Heo, Jaehoon (Korea Advanced Institute of Science and Technology, Daejeon, South Korea) , Kim, Joo-Young (Korea Advanced Institute of Science and Technology, Daejeon, South Korea)

Abstract ▼ AI-Helper

We present an energy-efficient processing-in-memory (PIM) architecture named Z-PIM that supports both sparsity handling and fully variable bit-precision in weight data for energy-efficient deep neural networks. Z-PIM adopts the bit-serial arithmetic that performs a multiplication bit-by-bit through multiple cycles to reduce the complexity of the operation in a single cycle and to provide flexibility in bit-precision. To this end, it employs a zero-skipping convolution SRAM, which performs in-memory AND operations based on custom 8T-SRAM cells and channel-wise accumulations, and a diagonal accumulation SRAM that performs bit- and spatial-wise accumulation on the channel-wise accumulation results using diagonal logic and adders to produce the final convolution outputs. We propose the hierarchical bitline structure for energy-efficient weight bit pre-charging and computational readout by reducing the parasitic capacitances of the bitlines. Its charge reuse scheme reduces the switching rate by 95.42% for the convolution layers of VGG-16 model. In addition, Z-PIM’s channel-wise data mapping enables sparsity handling by skip-reading the input channels with zero weight. Its read-operation pipelining enabled by a read-sequence scheduling improves the throughput by 66.1%. The Z-PIM chip is fabricated in a 65-nm CMOS process on a 7.568-mm2 die, while it consumes average 5.294-mW power at 1.0-V voltage and 200-MHz frequency. It achieves 0.31–49.12-TOPS/W energy efficiency for convolution operations as the weight sparsity and bit-precision vary from 0.1 to 0.9 and 1 to 16 bit, respectively. For the figure of merit considering input bit-width, weight bit-width, and energy efficiency, the Z-PIM shows more than 2.1 times improvement over the state-of-the-art PIM implementations.

참고문헌 (22)

10.1109/ISSCC.2019.8662302
Han, Song, Liu, Xingyu, Mao, Huizi, Pu, Jing, Pedram, Ardavan, Horowitz, Mark A., Dally, William J.. EIE : efficient inference engine on compressed deep neural network. Computer architecture news, vol.44, no.3, 243-254.

상세보기
10.1109/ISSCC19947.2020.9062989
Wulf, Wm. A., McKee, Sally A.. Hitting the memory wall : implications of the obvious. Computer architecture news, vol.23, no.1, 20-24.

상세보기
Wang, Jingcheng, Wang, Xiaowei, Eckert, Charles, Subramaniyan, Arun, Das, Reetuparna, Blaauw, David, Sylvester, Dennis. A 28-nm Compute SRAM With Bit-Serial Logic/Arithmetic Operations for Programmable In-Memory Vector Computing. IEEE journal of solid-state circuits, vol.55, no.1, 76-86.

상세보기
Zhang, Jintao, Wang, Zhuo, Verma, Naveen. In-Memory Computation of a Machine-Learning Classifier in a Standard 6T SRAM Array. IEEE journal of solid-state circuits, vol.52, no.4, 915-924.

상세보기
Si, Xin, Liu, Rui, Yu, Shimeng, Liu, Ren-Shuo, Hsieh, Chih-Cheng, Tang, Kea-Tiong, Li, Qiang, Chang, Meng-Fan, Chen, Jia-Jing, Tu, Yung-Ning, Huang, Wei-Hsing, Wang, Jing-Hong, Chiu, Yen-Cheng, Wei, Wei-Chen, Wu, Ssu-Yen, Sun, Xiaoyu. A Twin-8T SRAM Computation-in-Memory Unit-Macro for Multibit CNN-Based AI Edge Processors. IEEE journal of solid-state circuits, vol.55, no.1, 189-202.

상세보기
Biswas, Avishek, Chandrakasan, Anantha P.. CONV-SRAM: An Energy-Efficient SRAM With In-Memory Dot-Product Computation for Low-Power Convolutional Neural Networks. IEEE journal of solid-state circuits, vol.54, no.1, 217-230.

상세보기
10.1109/ISSCC.2019.8662435
Proc Adv Neural Inf Process Syst (NIPS) ImageNet classification with deep convolutional neural networks krizhevsky 2012 1
Pierson, Harry A., Gashler, Michael S.. Deep learning in robotics: a review of recent research. Advanced robotics : the international journal of the Robotics Society of Japan, vol.31, no.16, 821-835.

상세보기
Goldberg, Yoav. Neural Network Methods for Natural Language Processing. Synthesis lectures on human language technologies, vol.10, no.1, 1-309.

상세보기
Chen, Yu-Hsin, Krishna, Tushar, Emer, Joel S., Sze, Vivienne. Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks. IEEE journal of solid-state circuits, vol.52, no.1, 127-138.

상세보기
10.1145/3079856.3080246
Lee, Jinmook, Kim, Changhyeon, Kang, Sanghoon, Shin, Dongjoo, Kim, Sangyeob, Yoo, Hoi-Jun. UNPU: An Energy-Efficient Deep Neural Network Accelerator With Fully Variable Weight Bit Precision. IEEE journal of solid-state circuits, vol.54, no.1, 173-185.

상세보기
Yuan, Zhe, Liu, Yongpan, Yue, Jinshan, Yang, Yixiong, Wang, Jingyu, Feng, Xiaoyu, Zhao, Jian, Li, Xueqing, Yang, Huazhong. STICKER: An Energy-Efficient Multi-Sparsity Compatible Accelerator for Convolutional Neural Networks in 65-nm CMOS. IEEE journal of solid-state circuits, vol.55, no.2, 465-477.

상세보기
Hinton, G., Li Deng, Dong Yu, Dahl, G. E., Mohamed, A., Jaitly, N., Senior, Andrew, Vanhoucke, V., Nguyen, P., Sainath, T. N., Kingsbury, B.. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE signal processing magazine, vol.29, no.6, 82-97.

상세보기
Proc Int Conf Learn Represent (ICLR) Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding han 2016 1
10.1109/CVPR.2012.6248110
10.1109/CVPR.2015.7298594
Proc Symp VLSI Circuits A 31.2 pJ/disparity$^{\cdot}$ pixel stereo matching processor with stereo SRAM for mobile UI application lee 2017 158
Proc ImageNet Large Scale Vis Recognition Challenge (ILSVRC) Very deep convolutional networks for large-scale image recognition simonyan 2015 1

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 URL 링크

DOI : 10.1109/JSSC.2020.3039206
IEEE : 저널 > 논문

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증