Skip to main content

Table 1 Scaling over multiple cores

From: rapidGSEA: Speeding up gene set enrichment analysis on multi-core CPUs and CUDA-enabled GPUs

noHT 1 2 3 4 5 6 7 8 9 10
Runtime 224.11 116.06 83.93 65.11 53.56 45.21 39.31 34.87 31.74 28.94
Speedup 1.00 1.93 2.67 3.44 4.18 4.96 5.70 6.43 7.06 7.74
Efficiency 1.00 0.97 0.89 0.86 0.84 0.83 0.81 0.80 0.78 0.77
HT 1 2 3 4 5 6 7 8 9 10
Runtime 174.82 91.09 66.31 52.09 42.57 35.58 30.94 27.55 24.79 22.85
Speedup 1.28 2.46 3.38 4.30 5.26 6.30 7.24 8.13 9.04 9.81
Efficiency 1.28 1.23 1.13 1.08 1.05 1.05 1.03 1.02 1.00 0.98
  1. Runtime in seconds, speedup and parallelization efficiency using up to ten physical cores with disabled hyperthreading (noHT) and enabled hyperthreading (HT) for a fixed number of n=16,384 permutations on the Hallmark gene set collection