EUVIMEDEUVIMED entdecken
Crossref

A 28-nm 88.3-TFLOPS/W POSIT-Approximate-Calculation-Based Digital Computing-in-Memory Macro Incorporating Final-Cycle Fusion and Joint Skipping

Hao Wu, Yong Chen, Ming Li, Bingxin Zhang, Rui Zhang, Yiyang Yuan, Yiming Yang, Jinshan Yue, Xinghua Wang, Xiaoran Li, Feng Zhang

IEEE Journal of Solid-State Circuits · 2026-04 · 61 (4) · 1682-1696

DOI: 10.1109/jssc.2025.3590632 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal of Solid-State Circuits, 2026-04. Verfasst von Hao Wu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 29 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computing-in-memory (CiM) architecture is considered a technology that promises to alleviate the memory wall problem in artificial intelligence (AI) computing. Previous work on digital CiM macros has achieved significant energy efficiency advantages in supporting approximate calculations of traditional integer (INT)/floating point (FP) data. POSIT is an emerging FP number system. Its main characteristic is that it can approach a good tradeoff between data range and accuracy by flexibly adjusting the mantissa bit width. However, current digital CiM macros lack the ability to support approximate calculations of POSIT data. Given this, we propose a POSIT-approximate-calculation-based CiM macro. The three main contributions of our work are as follows: 1) we improve the original POSIT approximate calculation principle and design a calculation logic circuit based on unsigned Radix8+ final-cycle fusion (FCF); 2) we propose a macro-level approximate calculation control strategy to help the CiM macro find a compromise between calculation performance and calculation error; and 3) we design an activation mantissa alignment skipping (AMAS) unit, to help the hardware skip sparse activation bits when calculating POSIT multiplication. A prototype of the CiM macro was fabricated in a 28-nm complementary metal oxide semiconductor (CMOS) and scored a peak macro energy efficiency of 88.3 TFLOPS/W @ POSIT (8, 2) for a voltage supply of 0.55–1.1 V and an operating frequency of 70–280 MHz, a value $2.12{\times }$ higher than other state-of-the-art POSIT CiM macros.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Wu, H., Chen, Y., Li, M., Zhang, B., Zhang, R., Yuan, Y., Yang, Y., Yue, J., Wang, X., Li, X., & Zhang, F. (2026). A 28-nm 88.3-TFLOPS/W POSIT-Approximate-Calculation-Based Digital Computing-in-Memory Macro Incorporating Final-Cycle Fusion and Joint Skipping. IEEE Journal of Solid-State Circuits, 61(4), 1682-1696. https://doi.org/10.1109/jssc.2025.3590632

Vancouver

Wu H, Chen Y, Li M, Zhang B, Zhang R, Yuan Y, et al. A 28-nm 88.3-TFLOPS/W POSIT-Approximate-Calculation-Based Digital Computing-in-Memory Macro Incorporating Final-Cycle Fusion and Joint Skipping. IEEE Journal of Solid-State Circuits. 2026;61(4):1682-1696. doi:10.1109/jssc.2025.3590632

BibTeX
@article{Wu2026,
  author = {Wu, Hao and Chen, Yong and Li, Ming and Zhang, Bingxin and Zhang, Rui and Yuan, Yiyang and Yang, Yiming and Yue, Jinshan and Wang, Xinghua and Li, Xiaoran and Zhang, Feng},
  title = {A 28-nm 88.3-TFLOPS/W POSIT-Approximate-Calculation-Based Digital Computing-in-Memory Macro Incorporating Final-Cycle Fusion and Joint Skipping},
  journal = {IEEE Journal of Solid-State Circuits},
  year = {2026},
  volume = {61},
  number = {4},
  pages = {1682--1696},
  doi = {10.1109/jssc.2025.3590632}
}
Kostenlos starten →