Sparse deep neural networks (DNNs) have the potential to deliver compelling performance and energy efficiency without significant accuracy loss. However, their benefits can quickly diminish if their training is oblivious to the target hardware. For example, fewer critical connections can have a significant overhead if they translate into long-distance communication on the target hardware. Therefore, hardware-aware sparse training is needed to leverage the full potential of sparse DNNs. To this end, we propose a novel and comprehensive communication-aware sparse DNN optimization framework for tile-based in-memory computing (IMC) architectures. The proposed technique, CANNON first maps the DNN layers onto the tiles of the target architecture. Then, it replaces the fully connected and convolutional layers with communication-aware sparse connections. After that, CANNON optimizes the communication cost with minimal impact on the DNN accuracy. Extensive experimental evaluations with a wide range of DNNs and datasets show up to 3.0× lower communication energy, 3.1× lower communication latency, and 6.8× lower energy-delay product compared to state-of-the-art pruning approaches with a negligible impact on the classification accuracy on IMC-based machine learning accelerators.

中文翻译：

---

CANNON：通信感知稀疏神经网络优化

稀疏深度神经网络 (DNN) 有潜力提供令人信服的性能和能源效率，而不会显着损失准确性。然而，如果他们的培训忽视了目标硬件，那么他们的优势可能会很快消失。例如，如果关键连接较少转化为目标硬件上的长距离通信，则它们可能会产生显着的开销。因此，需要硬件感知的稀疏训练来充分利用稀疏 DNN 的潜力。为此，我们提出了一种新颖且全面的通信感知稀疏 DNN 优化框架，用于基于图块的内存计算 (IMC) 架构。所提出的技术 CANNON 首先将 DNN 层映射到目标架构的图块上。然后，它用通信感知的稀疏连接替换全连接层和卷积层。之后，CANNON 优化了通信成本，同时对 DNN 精度的影响最小。对各种 DNN 和数据集进行的广泛实验评估表明，与最先进的剪枝方法相比，通信能量降低了 3.0 倍，通信延迟降低了 3.1 倍，能量延迟乘积降低了 6.8 倍，对性能的影响可以忽略不计。基于 IMC 的机器学习加速器的分类准确性。