Fig. 10
From: Fast noisy long read alignment with multi-level parallelism
The strong and weak scalability of ParaHAT. a Strong scalability of ParaHAT on real and simulated H. sapiens datasets. The runtime of the program decreases proportionally with the number of computing nodes. b Weak scalability of ParaHAT on real and simulated datasets. At 128 computing nodes, only the smaller datasets E. coli-sim and S. cerevisiae-sim show a decline, with the peak weak scalability metric reaching up to 0.99