Skip to main content

Table 6 Performance comparison of Sequential, Lock-Based, TVar and TArray Sugarscape implementations under varying cores with 50 × 50 environment and 500 initial agents

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

Cores

Sequential

Lock-Based

TVar

TArray

1

25.2 (0.36)

21.0 (0.12)

21.1 (0.25)

42.0 (2.20)

2

20.0 (0.12)

22.2 (0.21)

24.5 (1.07)

3

21.9 (0.19)

23.6 (0.12)

19.7 (1.05)

4

24.0 (0.17)

25.2 (0.16)

18.9 (0.58)

5

26.7 (0.17)

31.0 (0.24)

20.3 (0.87)

6

29.3 (0.57)

35.2 (0.12)

21.2 (1.49)

7

30.0 (0.12)

38.7 (0.42)

21.0 (0.41)

8

31.2 (0.29)

49.0 (0.41)

21.1 (0.64)

  1. Best performance indicated in italic
  2. Timings in seconds (lower is better), standard deviation in parentheses