Effective Jump-Pointer Prefetching for Linked Data Structures

Current techniques for prefetching linked data structures (LDS) exploit the work available in one loop iteration or recursive call to overlap pointer chasing latency. Jumppointers, which provide direct access to non-adjacent nodes, can be used for prefetching when loop and recursive procedure bodies are small and do not have sufficient work to overlap a long latency. This paper describes a framework for jump-pointer prefetching (JPP) that supports four prefetching idioms: queue, full, chain, and root jumping and three implementations: software-only, hardware-only, and a cooperative software/hardware technique. On a suite of pointer intensive programs, jumppointer prefetching reduces memory stall time by 72% for software, 83% for cooperative and 55% for hardware, producing speedups of 15%, 20% and 22% respectively.

• Type: Conference
• Year: 1999
• Where: ISCA
• Authors: Amir Roth, Gurindar S. Sohi
• Keywords: Hardware, ISCA 1999, Pointer Chasing Latency, Pointer Intensive Programs, Recursive Procedure Bodies