Skip to main content

Improving the Efficiency of In-Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode for Lossless Neural Network Inference

Publication ,  Conference
Zheng, Q; Li, Z; Ku, J; Wang, Y; Taylor, B; Fan, D; Chen, Y
Published in: Proceedings - Design Automation Conference
November 7, 2024

Analog in-memory-computing (IMC) is an attractive technique with a higher energy efficiency to process machine learning workloads. However, the analog computing scheme suffers from large interface circuit overhead. In this work, we propose a macro with a hybrid analog-digital mode computation to reduce the precision requirement of the interface circuit. Considering the distribution of the multiplication and accumulation (MAC) value, we propose a nonlinear transfer function of the computing circuits by only accurately computing low MAC value in the analog domain with a digital mode to deal with the high MAC value with smaller possibility. Silicon measurement results show that the proposed macro could achieve 160 GOPS/mm2 area efficiency and 25.5 TOPS/W for 8b/8b matrix computation. The architectural-level evaluation for real workloads shows that the proposed macro can achieve up to 2.92× higher energy efficiency than conventional analog IMC designs.

Duke Scholars

Published In

Proceedings - Design Automation Conference

DOI

ISSN

0738-100X

Publication Date

November 7, 2024
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zheng, Q., Li, Z., Ku, J., Wang, Y., Taylor, B., Fan, D., & Chen, Y. (2024). Improving the Efficiency of In-Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode for Lossless Neural Network Inference. In Proceedings - Design Automation Conference. https://doi.org/10.1145/3649329.3658472
Zheng, Q., Z. Li, J. Ku, Y. Wang, B. Taylor, D. Fan, and Y. Chen. “Improving the Efficiency of In-Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode for Lossless Neural Network Inference.” In Proceedings - Design Automation Conference, 2024. https://doi.org/10.1145/3649329.3658472.
Zheng Q, Li Z, Ku J, Wang Y, Taylor B, Fan D, et al. Improving the Efficiency of In-Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode for Lossless Neural Network Inference. In: Proceedings - Design Automation Conference. 2024.
Zheng, Q., et al. “Improving the Efficiency of In-Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode for Lossless Neural Network Inference.” Proceedings - Design Automation Conference, 2024. Scopus, doi:10.1145/3649329.3658472.
Zheng Q, Li Z, Ku J, Wang Y, Taylor B, Fan D, Chen Y. Improving the Efficiency of In-Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode for Lossless Neural Network Inference. Proceedings - Design Automation Conference. 2024.

Published In

Proceedings - Design Automation Conference

DOI

ISSN

0738-100X

Publication Date

November 7, 2024