PIFS-Rec：面向大规模推荐系统推理的架构内交换机处理
PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferences
AI总结：
本文提出PIFS-Rec，一种基于CXL架构内交换机处理的方案，通过交换机下行端口实现近数据处理，有效解决DLRM推理的内存与带宽瓶颈，延迟比Pond低3.89倍，性能比BEACON高2.03倍。
摘要：
深度学习推荐模型（DLRM）在当今数据中心日益普及，消耗了大部分AI推理周期。由于嵌入表中的大向量规模和并发访问，DLRM的性能受可用带宽影响极大。为在现有方案上取得实质性改进，亟需针对DLRM优化的新方法，特别是在CXL等新兴互连技术背景下。本研究深入探索CXL系统，实现了一种架构内交换机处理（PIFS）方案，以加速DLRM并优化其内存与带宽可扩展性。我们对运行于CXL就绪系统的工业级DLRM工作负载进行了深入特征分析，识别出现有CXL系统的主要瓶颈。因此，我们提出PIFS-Rec，一种基于PIFS的方案，通过架构交换机的下行端口实现近数据处理。PIFS-Rec的延迟比工业标准CXL系统Pond低3.89倍，且性能优于最先进方案BEACON 2.03倍。
英文摘要：
Deep Learning Recommendation Models (DLRMs) have become increasingly popular and prevalent in today's datacenters, consuming most of the AI inference cycles. The performance of DLRMs is heavily influenced by available bandwidth due to their large vector sizes in embedding tables and concurrent accesses. To achieve substantial improvements over existing solutions, novel approaches towards DLRM optimization are needed, especially, in the context of emerging interconnect technologies like CXL. This study delves into exploring CXL-enabled systems, implementing a process-in-fabric-switch (PIFS) solution to accelerate DLRMs while optimizing their memory and bandwidth scalability. We present an in-depth characterization of industry-scale DLRM workloads running on CXL-ready systems, identifying the predominant bottlenecks in existing CXL systems. We, therefore, propose PIFS-Rec, a PIFS-based scheme that implements near-data processing through downstream ports of the fabric switch. PIFS-Rec achieves a latency that is 3.89x lower than Pond, an industry-standard CXL-based system, and also outperforms BEACON, a state-of-the-art scheme, by 2.03x.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
