Diskann Benchmarking Wrapper

[tarang-jain]

Brings DiskANN into cuvs-bench

• Build and search in-memory DiskANN index
• Build and search SSD DiskANN index
• Build a cuvs Vamana index on GPU and serialize it in DiskANN format. Search on CPU using in-memory DiskANN search API.

[achirkin]

Thanks for the PR, it's nice to see the list of supported algorithms growing.

I feel unsettled though about adding new functionality to the common benchmark.hpp header just for one algorithm - this looks unsustainable. I see you probably want to avoid having the user to specify the path to the index file / dataset manually, but I think adding the new functionality in such an ad-hoc way is not a solution.
I think, the easiest solution could be just to pass both paths as algo parameters.
Maybe you can automate this in the python layer of the benchmark. Alternatively, I think it's acceptable to modify the parse_build_param api to give it access to the full json config file; that way, you could get the path to the dataset and fill-in the algo parameters inside that function.

[achirkin]

Looks like this algorithm does not use the CUDA stream during search. If this is true, please add the uses_stream() override to disable GPU timing to avoid extra sync overheads and make the benchmark results more fair.

[tarang-jain]

The GPU build requires the stream, whereas the search is done on CPU. So we would still need the stream for the build part. So we would still have to set uses_stream() to true for the whole algorithm (which is the default)? I believe we are currently doing it the same way in CAGRA + HNSWLIB.