RAPID-Graph: 递归所有对最短路径利用内存处理技术实现图的动态规划
RAPID-Graph: Recursive All-Pairs Shortest Paths Using Processing-in-Memory for Dynamic Programming on Graphs
AI总结:
RAPID-Graph通过内存处理技术实现图的动态规划,利用递归分区和并行处理,在大规模图分析中实现高速高效计算。
摘要:
所有对最短路径(APSP)仍然是大规模图分析的主要瓶颈,因为数据移动具有三次方复杂度,超出了传统内存层次结构的带宽。在本工作中,我们提出RAPID-Graph来解决这一挑战,通过一个联合设计的内存处理(PIM)系统,该系统集成了算法、架构和设备级的优化。在算法层面,我们引入了一个递归感知的分区器,通过将图分解为顶点瓷砖来实现精确的APSP计算,以减少数据依赖,使得Floyd-Warshall和Min-Plus内核能够在数字PIM阵列中完全原地执行。在架构和设备层面,我们设计了一个2.5D PIM堆栈,集成了两个相变内存计算芯片、一个逻辑芯片和高带宽暂存器内存,所有这些都在一个统一的先进封装中。外部非易失性存储堆栈用于持久化存储大型APSP结果。该设计实现了瓷砖级和单元级的并行处理,以维持高吞吐量。在245万个节点的OGBN-Products数据集上,RAPID-Graph比最先进的GPU集群快5.8倍,能效提高1186倍,同时比先前的PIM加速器在速度和能效上分别高出8.3倍和104倍。它进一步在NVIDIA H100 GPU上实现了高达42.8倍的速度提升和392倍的能效节省。
英文摘要:
All-pairs shortest paths (APSP) remains a major bottleneck for large-scale graph analytics, as data movement with cubic complexity overwhelms the bandwidth of conventional memory hierarchies. In this work, we propose RAPID-Graph to address this challenge through a co-designed processing-in-memory (PIM) system that integrates algorithm, architecture, and device-level optimizations. At the algorithm level, we introduce a recursion-aware partitioner that enables an exact APSP computation by decomposing graphs into vertex tiles to reduce data dependency, such that both Floyd-Warshall and Min-Plus kernels execute fully in-place within digital PIM arrays. At the architecture and device levels, we design a 2.5D PIM stack integrating two phase-change memory compute dies, a logic die, and high-bandwidth scratchpad memory within a unified advanced package. An external non-volatile storage stack stores large APSP results persistently. The design achieves both tile-level and unit-level parallel processing to sustain high throughput. On the 2.45M-node OGBN-Products dataset, RAPID-Graph is 5.8x faster and 1,186x more energy efficient than state-of-the-art GPU clusters, while exceeding prior PIM accelerators by 8.3x in speed and 104x in efficiency. It further delivers up to 42.8x speedup and 392x energy savings over an NVIDIA H100 GPU.
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。