Seunghwa Kang

@jnke2016 I thought more about implementing https://github.com/rapidsai/cugraph/issues/3446#issuecomment-1499649664; especially the steps 6, 7, and 8. After step 6, sort the (edge source, edge destination, triangle count) triplets using edge destination as...

@jnke2016 Please ping me if you have any questions about the comments.

@naimnv Is this PR ready-for-review?

What's the minimum scale (i.e. # GPUs) to reproduce this? Can you reproduce this with 2 GPUs?

You mean this is a heisenbug? Sounds worse but let me try to reproduce this first.

How often can you reproduce this? (Say run test_egonet_mg.py 10 times, how many times you see at least one failure?) I am running this on my local system with 2...

Never mind, I reproduced this.

This PR won't be merged.

Added quick fixes for the FPE issue in systems with more than 8 GPUs and the KatzCentralityDynamic compile error.

I see, and this is not a high priority task at all. It seems like cuco gets updated to take thrust::tuple (instead of requiring thrust::pair), and now I just need...