Dyn-Bitpool: A Two-sided Sparse CIM Accelerator Featuring a Balanced Workload Scheme and High CIM Macro Utilization
Xujiang Xiang, Zhiheng Yue, Yuxuan Li, Liuxin Lv, Shaojun Wei, Yang Hu, Shouyi Yin
Abstract
Computing-in-memory (CIM), a promising computing paradigm, has demonstrated great energy-efficiency by integrating computing units into memory. However, previous research on CIM has rarely utilized sparsity in activation and weight concurrently. Moreover, new challenges arise when harnessing sparsity in both activation and weight (two-sided sparsity), such as unbalanced workload and low hardware substrate utilization.
Ask Lune
Ask anything. The answer shows its sources.
Lune reads the papers around it, then shows you the passages behind every answer.
Related papers
- Dual-side Sparse Tensor CoreYang Wang, Chen Zhang, Zhiqiang Xie, Cong Guo et al.ISCA 2021 · 109 citations
- Morphable CIM: Improving Operation Intensity and Depthwise Capability for SRAM-CIM ArchitectureYun-Chen Lo, Ren-Shuo LiuDAC 2023 · 13 citations
- CAP: A General Purpose Computation-in-memory with Content Addressable Processing ParadigmZhiheng Yue, Shaojun Wei, Yang Hu, Shouyi YinDAC 2024 · 1 citation
- A Two-way SRAM Array based Accelerator for Deep Neural Network On-chip TrainingHongwu Jiang, Shanshi Huang, Xiaochen Peng, Jian-Wei Su et al.DAC 2020 · 39 citations
- TAIM: ternary activation in-memory computing hardware with 6T SRAM arrayNameun Kang, Hyungjun Kim, Hyunmyung Oh, Jae-Joon KimDAC 2022 · 4 citations
