Integrating GPUs into serverless computing platforms is crucial for improving efficiency. However, existing solutions for GPU-enabled serverless computing platforms face two significant problems due to coarse-grained GPU management: long setup time and low function throughput. To address these issues, we propose SAGE, a GPU serverless framework with fast setup and high throughput. First, based on the data knowability of GPU function ahead of actual execution, SAGE first devises the parallelized function setup mechanism, which parallelizes the data preparation and context creation. In this way, SAGE achieves fast setup of GPU function invocations.Second, SAGE further proposes the sharing-based memory management mechanism, which shares the read-only memory and context memory across multiple invocations of the same function. The memory sharing mechanism avoids repeated data preparation and then unnecessary data-loading contention. As a consequence, the function throughput could be improved. Our experimental results show that SAGE reduces function duration by 11.3X and improves function density by 1.22X compared to the state-of-the-art serverless platform.

翻译：将GPU集成到无服务器计算平台对于提升效率至关重要。然而，现有面向GPU的无服务器计算方案因粗粒度GPU管理而面临两大难题：部署耗时长且函数吞吐量低。针对上述问题，本文提出SAGE——一个兼具快速部署与高吞吐特性的GPU无服务器框架。首先，基于GPU函数在实际执行前数据可知的特性，SAGE设计了并行化函数部署机制，将数据准备与上下文创建并行化处理，从而实现了GPU函数调用的快速部署。其次，SAGE进一步提出基于共享的内存管理机制，通过同一函数多次调用间的只读内存与上下文内存共享，避免重复数据准备及由此引发的不必要数据加载竞争，从而提升函数吞吐量。实验结果表明，与当前最先进的无服务器平台相比，SAGE可将函数执行时间缩短11.3倍，函数密度提升1.22倍。