Buffer Prospector: Discovering and Exploiting Untapped Buffer Resources in Many-Core DNN Accelerators

In large-scale DNN inference accelerators, the many-core architecture has emerged as a predominant design, with layer-pipeline (LP) mapping being a mainstream mapping approach. However, our experimental findings and theoretical justifications uncover a hardware-independent and prevalent flaw in empl...

Full description

Saved in:
Bibliographic Details
Published in:2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors: Wei, Yuchen, Cai, Jingwei, Gao, Mingyu, Peng, Sen, Wu, Zuotong, Shi, Guiming, Ma, Kaisheng
Format: Conference Proceeding
Language:English
Published: IEEE 22.06.2025
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In large-scale DNN inference accelerators, the many-core architecture has emerged as a predominant design, with layer-pipeline (LP) mapping being a mainstream mapping approach. However, our experimental findings and theoretical justifications uncover a hardware-independent and prevalent flaw in employing layer-pipeline mapping on many-core accelerators: a significant underutilization of buffer space across numerous cores, indicating substantial potential for optimization. Building on this discovery, we develop a universal and efficient buffer allocation strategy, BufferProspector, which includes a Buffer Requirement Calculator and Buffer Allocator, to capitalize on these unused buffers, addressing the timing mismatch challenge inherent in LP mapping. Compared to the state-of-the-art (SOTA) open-source LP mapping framework Tangram, BufferProspector averages a simultaneous increase in energy efficiency and performance by 1.44× and 2.26×, respectively. Moreover, we conduct some case studies on architecture and mapping. BufferProspector will be open-sourced.
DOI:10.1109/DAC63849.2025.11132440