Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models rely on terabyte-scale embedding tables to learn user preferences over large bodies of contents. The reliance on a fixed embedding representation of embedding tables not only imposes significant memory capacity and bandwidth requirements but also limits the scope of compatible system solutions. This paper challenges the assumption of fixed embedding representations by showing how synergies between embedding representations and hardware platforms can lead to improvements in both algorithmic- and system performance. Based on our characterization of various embedding representations, we propose a hybrid embedding representation that achieves higher quality embeddings at the cost of increased memory and compute requirements. To address the system performance challenges of the hybrid representation, we propose MP-Rec -- a co-design technique that exploits heterogeneity and dynamic selection of embedding representations and underlying hardware platforms. On real system hardware, we demonstrate how matching custom accelerators, i.e., GPUs, TPUs, and IPUs, with compatible embedding representations can lead to 16.65x performance speedup. Additionally, in query-serving scenarios, MP-Rec achieves 2.49x and 3.76x higher correct prediction throughput and 0.19% and 0.22% better model quality on a CPU-GPU system for the Kaggle and Terabyte datasets, respectively.

翻译：深度学习推荐系统在多样化的尾部延迟目标和输入查询负载下提供个性化内容服务。为此，最先进的推荐模型依赖TB级嵌入表来学习用户对大量内容的偏好。这种对固定嵌入表示的依赖不仅带来了巨大的存储容量和带宽需求，也限制了兼容系统解决方案的适用范围。本文通过展示嵌入表示与硬件平台之间的协同效应如何能同时提升算法与系统性能，挑战了固定嵌入表示的假设。基于对多种嵌入表示的特征分析，我们提出了一种混合嵌入表示，该表示以更高的内存与计算需求为代价实现了更高质量的嵌入。为应对混合表示带来的系统性能挑战，我们提出了MP-Rec——一种利用嵌入表示与底层硬件平台的异构性及动态选择的协同设计技术。在真实系统硬件上，我们证明了将定制加速器（如GPU、TPU和IPU）与兼容的嵌入表示相匹配可实现16.65倍的性能加速。此外，在查询服务场景中，MP-Rec在Kaggle和Terabyte数据集上的CPU-GPU混合系统上分别实现了2.49倍和3.76倍的正确预测吞吐量提升，同时模型质量分别提升了0.19%和0.22%。