EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Enabling Efficient Vector Processing: A Heterogeneous Vector Architecture with in-SRAM Computing

Ruoxi Wang, Zhang Dunbo, Shangshang Yao, Lang Qingjie, Junyi Zhu, Li Shen

ACM Transactions on Architecture and Code Optimization · 2026-06-30 · 23 (2) · 1-18

DOI: 10.1145/3817062 ↗

At a glance

Journal article in ACM Transactions on Architecture and Code Optimization, published online on 2026-06-26. Written by Ruoxi Wang and 5 co-authors. 19 references. The full text is freely available (open access, CC BY 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The growing demand for high-performance, energy-efficient execution of data-parallel workloads has driven the resurgence of vector processors, yet their expanding instruction sets exacerbate the area-performance tradeoff of vector processing units (VPUs). Processing-in-memory (PIM) technique offers a promising path to mitigate this tradeoff by offloading vector operations near data. However, integrating the computing-capable SRAM (C-SRAM) with conventional VPUs introduces significant architectural challenges, including inefficient coordination between heterogeneous devices, the lack of a unified hardware/software interface, and underutilized parallelism within the C-SRAM arrays due to unoptimized data handling. To address these challenges, this article proposes a heterogeneous VPU (HVPU) that seamlessly integrates a standard VPU inside a vector processor with a C-SRAM for more efficient vector processing. HVPU introduces a standardized interface between the processor frontend and the C-SRAM, enabling instruction dispatch, dynamic hazard resolution, and concurrent execution. Furthermore, it employs multiple independent PIM blocks coupled with dual controlling pipelines inside the C-SRAM for further performance improvement. This design facilitates pipelined data loading and computing, effectively hiding memory latency and fully unlocking the parallel potential of C-SRAM. The system is supported by a user-friendly and generic programming model featuring a two-layer extended ISA system and a vector batch pipelining mechanism. Experimental results show that our HVPU-enhanced processor achieves significant speedups of 5.11× to 39.0× over the Xuantie-910 baseline on vector benchmarks, respectively, while reducing energy consumption by 75% on average. Meanwhile, it outperforms state-of-the-art PIM accelerators by 1.33× to 1.97× on the same benchmarks, with minimal area overhead. This demonstrates that our architectural co-design effectively alleviates the area-performance tradeoff in vector processors and offers a scalable heterogeneous architecture template for efficient vector processing.

Cite

APA

Wang, R., Dunbo, Z., Yao, S., Qingjie, L., Zhu, J., & Shen, L. (2026). Enabling Efficient Vector Processing: A Heterogeneous Vector Architecture with in-SRAM Computing. ACM Transactions on Architecture and Code Optimization, 23(2), 1-18. https://doi.org/10.1145/3817062

Vancouver

Wang R, Dunbo Z, Yao S, Qingjie L, Zhu J, Shen L. Enabling Efficient Vector Processing: A Heterogeneous Vector Architecture with in-SRAM Computing. ACM Transactions on Architecture and Code Optimization. 2026;23(2):1-18. doi:10.1145/3817062

BibTeX
@article{Wang2026,
  author = {Wang, Ruoxi and Dunbo, Zhang and Yao, Shangshang and Qingjie, Lang and Zhu, Junyi and Shen, Li},
  title = {Enabling Efficient Vector Processing: A Heterogeneous Vector Architecture with in-SRAM Computing},
  journal = {ACM Transactions on Architecture and Code Optimization},
  year = {2026},
  volume = {23},
  number = {2},
  pages = {1--18},
  doi = {10.1145/3817062}
}
Start for free →