Skip to main content

Table 3 Performance comparison of Lock-Based Read–Write, Atomic IO and STM SIR implementations with varying grid sizes on 4 cores

From: A tale of lock-free agents: towards Software Transactional Memory in parallel Agent-Based Simulation

Grid sizeLock-Based Read–WriteAtomic IOSTM
101 × 101 (10,201)139.0 (0.15)91.1 (0.14)96.5 (0.27)
151 × 151 (22,801)314.0 (0.67)204.0 (0.36)212.0 (0.16)
201 × 201 (40,401)559.0 (1.22)360.0 (0.61)382.0 (0.85)
251 × 251 (63,001)861.0 (0.62)571.0 (0.71)608.0 (1.20)
  1. Best performance indicated in italic
  2. Timings in seconds (lower is better), standard deviation in parentheses