用搜索方法生成省电的GPU核函数，兼顾低功耗与低延迟。
Automating Energy-Efficient GPU Kernel Generation: A Fast Search-Based Compilation Approach
- 在编译阶段引入能耗评估，通过搜索生成节能核函数。
- 相比现有方法，最高降低21.69%能耗，延迟几乎不变。
- 自适应更新能耗模型，减少实测次数，加速搜索过程。
深度神经网络（DNN）已广泛应用于多个领域，但其在GPU上的部署常导致显著的能耗问题。现有降低GPU能耗的方法或依赖特定硬件，或受限于工作负载。本文从GPU核函数层面出发，提出一种新型基于搜索的编译方法，将能耗效率纳入搜索过程以生成节能核函数。为加速能耗评估，我们基于核函数的高层特征构建了精确的能耗模型，并引入动态更新策略，减少对设备端能耗测量的需求，从而加快搜索速度。实验表明，该方法可使生成的GPU核函数能耗最高降低21.69%，同时保持低延迟。
原文摘要 · Abstract (English)
Deep Neural Networks (DNNs) have revolutionized various fields, but their deployment on GPUs often leads to significant energy consumption. Unlike existing methods for reducing GPU energy consumption, which are either hardware-inflexible or limited by workload constraints, this paper addresses the problem at the GPU kernel level. We propose a novel search-based compilation method to generate energy-efficient GPU kernels by incorporating energy efficiency into the search process. To accelerate the energy evaluation process, we develop an accurate energy cost model based on high-level kernel features. Furthermore, we introduce a dynamic updating strategy for the energy cost model, reducing the need for on-device energy measurements and accelerating the search process. Our evaluation demonstrates that the proposed approach can generate GPU kernels with up to 21.69% reduced energy consumption while maintaining low latency.
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。