谁需要DRAM？我们有光纤
Who Needs DRAM? We Have Fiber
浏览论文内容
中文总结 AI 辅助
针对生成式AI对高性能内存需求及超大规模数据中心扩张带来的DRAM压力，提出光纤内存架构，通过考虑光纤物理特性的架构设计及相关技术应用，可消除冗余存储并大幅降低权重传输能量。
中文摘要 AI 辅助
DRAM可用性和合同定价面临的压力不断上升，这反映了生成式人工智能对高性能内存的巨大需求。超大规模数据中心的扩张加剧了这种压力，其消耗了全球DRAM产量的很大一部分。在这项工作中，我们提出了一种新架构：光纤内存，它重新设想了光纤在超大规模数据中心中的作用，将其部署为用于不可变数据（如大语言模型权重）的有源循环延迟线内存。我们提出了一种数据并行光学广播延迟线内存架构，该架构考虑了光纤的物理特性。通过纳入空分复用多芯光纤、无源光学分接和放大接口、共封装光学器件和区域全光再生，我们的案例研究评估表明，与传统HBM3e配置相比，光纤内存可以消除10000个AI加速器中的冗余权重存储，并将权重传输能量降低70%以上。
英文摘要
The rising pressure on DRAM availability and contract pricing reflects generative AI's massive high-performance memory requirements. This pressure is heavily compounded by hyperscale data center expansion, which now consumes a significant portion of global DRAM output. In this work, we propose a new architecture: Fiber Memory, which reimagines the role of optical fiber in a hyperscale data center, deploying it as an active, recirculating delay-line memory for immutable data, such as large language model weights. We present a data-parallel optical broadcast delay-line memory architecture that accounts for fiber's physical realities. By incorporating space-division multiplexed multi-core fibers, passive optical tap-and-amplify interfaces, co-packaged optics, and regional all-optical regeneration, our case study evaluation suggests that Fiber Memory can eliminate redundant weight storage across 10,000 AI accelerators and reduce weight-delivery energy by over 70% compared to traditional HBM3e configurations.
