def sl_mst_lifetime_gpu(dest, weight, fe, od, disconnect_weight = None, MAX_TPB = 256, stream = None): """ Input are device arrays. Inputs: dest, weight, fe : device arrays disconnect_weight : weight between unconnected vertices mst : list of edges in MST MAX_TPB : number of threads per block stream : CUDA stream to use TODO: - argmax is from cuBlas and only works with 32/64 floats. Make this work with any type. - """ if disconnect_weight is None: disconnect_weight = weight.max() if stream is None: myStream = cuda.stream() else: myStream = stream mst, n_edges = boruvka_minho_gpu(dest, weight, fe, od, MAX_TPB=MAX_TPB, stream=myStream, returnDevAry=True) # Allocate array for the mst weights. h_n_edges = int(n_edges.getitem(0, stream=myStream)) # edges to keep in MST mst_weights = cuda.device_array(h_n_edges, dtype=weight.dtype) # Get array with only the considered weights in the MST # and remove those edges in the MST edge list mstGrid = compute_cuda_grid_dim(h_n_edges, MAX_TPB) d_weight = cuda.to_device(weight, stream = myStream) getWeightsOfEdges_gpu[mstGrid, MAX_TPB, myStream](mst, n_edges, d_weight, mst_weights) # Sort the MST weights. There are no repeated edges at this # point since the output MST is like a directed graph. sorter = RadixSort(maxcount = mst_weights.size, dtype = mst_weights.dtype, stream = myStream) sortedWeightArgs = sorter.argsort(mst_weights) # Allocate array for the lifetimes. lifetimes = cuda.device_array(mst_weights.size - 1, dtype=mst_weights.dtype) compute_lifetimes_CUDA[mstGrid, MAX_TPB, myStream](mst_weights, lifetimes) maxer = Blas(stream) arg_max_lt = maxer.amax(lifetimes) max_lt = lifetimes.getitem(arg_max_lt) # this is the lifetime between edges with no connection and the weakest link #lt_threshold = disconnect_weight - max_lt lt_threshold = disconnect_weight - mst_weights.getitem(mst_weights.size - 1) # if the maximum lifetime is higher or equal than the lifetime threshold # cut the tree if max_lt >= lt_threshold: # from arg_max_lt onward all edges are discarded n_discarded = lifetimes.size - arg_max_lt + 1 # remove edges removeGrid = compute_cuda_grid_dim(n_discarded, MAX_TPB) removeEdges[removeGrid, MAX_TPB](edgeList, sortedArgs, n_discarded) # compute new amount of edges and update it new_n_edges = h_n_edges - n_discarded cuda.to_device(np.array([new_n_edges], dtype = n_edges.dtype), to = n_edges, stream = myStream) ngraph = getGraphFromEdges_gpu(dest, weight, fe, od, edges = mst, n_edges = n_edges, MAX_TPB = MAX_TPB, stream = myStream) ndest, nweight, nfe, nod = ngraph labels = connected_comps_gpu(ndest, nweight, nfe, nod, MAX_TPB = 512, stream = myStream) del ndest, nweight, nfe, nod, lifetimes return labels