通过优化权重布局，显著降低存算一体芯片的寄生电阻影响。
MDM: Manhattan Distance Mapping of DNN Weights for Parasitic-Resistance-Resilient Memristive Crossbars
- 按曼哈顿距离重排权重，将活跃单元移至受寄生电阻影响小的区域。
- 在ImageNet-1k上使非理想因子降低46%，ResNet准确率提升3.6%。
- 适合追求高能效的存算一体神经网络加速器设计者。
曼哈顿距离映射（MDM）是一种针对存内计算交叉阵列的后训练权重映射技术，可缓解寄生电阻（PR）非理想性对深度神经网络（DNN）性能的影响。由于PR限制了交叉阵列效率，通常将DNN矩阵划分到小型交叉阵列块中执行，每块独立运行需数字同步，导致速度提升受限。现有方案要么并行部署多个小阵列，要么串行复用少数阵列，均增加模数转换、延迟、输入输出压力和芯片面积。MDM通过优化活跃存储单元的位置来缓解此问题，利用比特级结构稀疏性，将激活信号从密度较高的低位侧输入，并根据曼哈顿距离重排行顺序，使活跃单元向受PR影响较小的区域迁移，从而降低非理想因子（NF）。在ImageNet-1k数据集上的DNN模型测试表明，该方法最高可降低NF达46%，在模拟失真下平均提升准确率3.6%。整体上提供了一种轻量、空间感知的扩展存算一体加速器的解决方案。
原文摘要 · Abstract (English)
Manhattan Distance Mapping (MDM) is a post-training deep neural network (DNN) weight mapping technique for memristive bit-sliced compute-in-memory (CIM) crossbars that reduces parasitic resistance (PR) nonidealities. PR limits crossbar efficiency by mapping DNN matrices into small crossbar tiles, reducing CIM-based speedup. Each crossbar executes one tile, requiring digital synchronization before the next layer. At this granularity, designers either deploy many small crossbars in parallel or reuse a few sequentially-both increasing analog-to-digital conversions, latency, I/O pressure, and chip area. MDM alleviates PR effects by optimizing active-memristor placement. Exploiting bit-level structured sparsity, it feeds activations from the denser low-order side and reorders rows according to the Manhattan distance, relocating active cells toward regions less affected by PR and thus lowering the nonideality factor (NF). Applied to DNN models on ImageNet-1k, MDM reduces NF by up to 46% and improves accuracy under analog distortion by an average of 3.6% in ResNets. Overall, it provides a lightweight, spatially informed method for scaling CIM DNN accelerators.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。