5 papers
GriNNder: Breaking the Memory Capacity Wall in Full-Graph GNN Training with Storage Offloading
Jaeyong Song, Seongyeon Park, Hongsun Jang +4
Full-graph training of graph neural networks (GNNs) is widely used as it enables direct validation of algorithmic improvements by preserving complete neighborhood information. Howe…
LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM
Junguk Hong, Changmin Shin, Sukjin Kim +6
Lookup tables (LUTs) have recently gained attention as an alternative compute mechanism that maps input operands to precomputed results, eliminating the need for arithmetic logic.…
FlexiWalker: Extensible GPU Framework for Efficient Dynamic Random Walks with Runtime Adaptation
Seongyeon Park, Jaeyong Song, Changmin Shin +3
Dynamic random walks are fundamental to various graph analysis applications, offering advantages by adapting to evolving graph properties. Their runtime-dependent transition probab…
PathWeaver: A High-Throughput Multi-GPU System for Graph-Based Approximate Nearest Neighbor Search
Sukjin Kim, Seongyeon Park, Si Ung Noh +4
Graph-based Approximate Nearest Neighbor Search (ANNS) is widely adopted in numerous applications, such as recommendation systems, natural language processing, and computer vision.…
PID-Comm: A Fast and Flexible Collective Communication Framework for Commodity Processing-in-DIMM Devices
Si Ung Noh, Junguk Hong, Chaemin Lim +5
Recent dual in-line memory modules (DIMMs) are starting to support processing-in-memory (PIM) by associating their memory banks with processing elements (PEs), allowing application…