Chih-Chen Yeh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chih-Chen Yeh has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Chia-Chun Wang
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
1 shared publication - Jun-Shen Wu
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
1 shared publication - Ren-Shuo Liu
Department of Electrical Engineering, National Tsing Hua University (NTHU), Hsinchu, Taiwan
1 shared publication - Wen-Chien Ting
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
1 shared publication - Yu-Chih Tsai
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
1 shared publication - Yun-Chen Lo
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
1 shared publication
Latest Publications
- 4 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 73 (9) , 2136-2149
ISSA: Architecting CNN Accelerators Using Input-Skippable, Set-Associative Computing-in-Memory
Among several emerging architectures, computing in memory (CIM), which features in-situ analog computation , is a potential solution to the data movement bottleneck of the Von Neumann architecture for artificial intelligence (AI). Interestingly, more strengths of CIM significantly different from in-situ analog computation are not widely known yet. In this work, we point out that mutually stationary vectors (MSVs) , which can be maximized by introducing associativity to CIM, are another inherent power unique to CIM. By MSVs, CIM exhibits significant freedom to dynamically vectorize the stored data (e.g., weights) to perform agile computation using the dynamically formed vectors. We have designed and realized an SA-CIM silicon prototype and corresponding architecture and acceleration schemes in the TSMC 28 nm process. More specifically, the contributions of this paper are fivefold: 1) We identify MSVs as new features that can be exploited to improve the current performance and energy challenges of the CIM-based hardware. 2) We propose SA-CIM to enhance MSVs (input-reordering flexibility) for skipping the zeros, small values, and sparse vectors. 3) We propose channel swapping to enhance the zero-skipping technique. 4) We propose a transposed systolic dataflow to efficiently conduct conv3×3 while being capable of exploiting input-skipping schemes. 5) We propose a design flow to search for optimal aggressive skipping scheme setups while satisfying the accuracy loss constraint. The proposed ISSA architecture improves the throughput by 1.91× to 2.97× speedup and the energy efficiency by 2.5× to 4.2×.
- 4 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 73 (9) , 2136-2149
ISSA: Architecting CNN Accelerators Using Input-Skippable, Set-Associative Computing-in-Memory
Among several emerging architectures, computing in memory (CIM), which features in-situ analog computation , is a potential solution to the data movement bottleneck of the Von Neumann architecture for artificial intelligence (AI). Interestingly, more strengths of CIM significantly different from in-situ analog computation are not widely known yet. In this work, we point out that mutually stationary vectors (MSVs) , which can be maximized by introducing associativity to CIM, are another inherent power unique to CIM. By MSVs, CIM exhibits significant freedom to dynamically vectorize the stored data (e.g., weights) to perform agile computation using the dynamically formed vectors. We have designed and realized an SA-CIM silicon prototype and corresponding architecture and acceleration schemes in the TSMC 28 nm process. More specifically, the contributions of this paper are fivefold: 1) We identify MSVs as new features that can be exploited to improve the current performance and energy challenges of the CIM-based hardware. 2) We propose SA-CIM to enhance MSVs (input-reordering flexibility) for skipping the zeros, small values, and sparse vectors. 3) We propose channel swapping to enhance the zero-skipping technique. 4) We propose a transposed systolic dataflow to efficiently conduct conv3×3 while being capable of exploiting input-skipping schemes. 5) We propose a design flow to search for optimal aggressive skipping scheme setups while satisfying the accuracy loss constraint. The proposed ISSA architecture improves the throughput by 1.91× to 2.97× speedup and the energy efficiency by 2.5× to 4.2×.