Fig. 2
From: A GPU-based algorithm for fast node label learning in large and unbalanced biomolecular networks
CPU/GPU schema of the PARCOSNET parallelization. Multiple CPU threads are launched in parallel each one solving the AFP problem for a given class/protein function. The GPU thread blocks, each composed of several CUDA threads, first solve the coloring problem for the graph and then concurrently process all neurons of a given color, for all colors in sequence. A further fine-grained level of parallelism is finally introduced by assigning to each neuron a thread block to perform the neuron level local computations