将神经网络转为逻辑流程，提升边缘设备上CPU的运行效率。
Late Breaking Results: Conversion of Neural Networks into Logic Flows for Edge Computing
- 把神经网络转为决策树，再压缩成if-else逻辑流执行
- 在模拟RISC-V CPU上延迟降低14.9%，精度无损
- 适合资源受限的边缘计算场景，尤其适用于无GPU的设备
神经网络已广泛应用于各类资源受限的边缘设备，这些设备通常依赖中央处理器（CPU）而非图形处理器（GPU），因功耗限制。现有研究仍聚焦于高效执行大量乘加（MAC）操作，但CPU本身不擅长大规模数学运算，更适合执行控制流逻辑（即计算机算法）。为提升神经网络在CPU上的计算效率，本文提出将其转换为逻辑流执行。具体而言，先将神经网络转化为等价决策树，从中选取具有常数叶节点的决策路径，并压缩为包含if-else结构和少量MAC操作的逻辑流。实验结果表明，在模拟RISC-V CPU上，延迟可降低高达14.9%，且无精度损失。代码开源：https://github.com/TUDa-HWAI/NN2Logic
原文摘要 · Abstract (English)
Neural networks have been successfully applied in various resource-constrained edge devices, where usually central processing units (CPUs) instead of graphics processing units exist due to limited power availability. State-of-the-art research still focuses on efficiently executing enormous numbers of multiply-accumulate (MAC) operations. However, CPUs themselves are not good at executing such mathematical operations on a large scale, since they are more suited to execute control flow logic, i.e., computer algorithms. To enhance the computation efficiency of neural networks on CPUs, in this paper, we propose to convert them into logic flows for execution. Specifically, neural networks are first converted into equivalent decision trees, from which decision paths with constant leaves are then selected and compressed into logic flows. Such logic flows consist of if and else structures and a reduced number of MAC operations. Experimental results demonstrate that the latency can be reduced by up to 14.9 % on a simulated RISC-V CPU without any accuracy degradation. The code is open source at https://github.com/TUDa-HWAI/NN2Logic
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。