Daniel Jünger
Daniel Jünger
Could this potentially land in v1.9.0?
@wmaxey could this be a candidate for v1.9.0? Also related: #163
Has there been any progress on this issue? I am planning to implement an HLL-backed version of `cuco::util::approx_distinct_count`, which can potentially be used in cudf.
@bdice Good idea. Let me read through the relevant papers first. I guess the crucial part I have to wrap my head around is how to represent the counters and...
FYI `cuco::distinct_count_estimator` (NVIDIA/cuCollections#429) has been merged so we can start implementing and exposing this feature in cudf.
🙅 Something's not right: ``` nvbench_compare.py dev_baseline.json invoke_one.json ['dev_baseline.json', 'invoke_one.json'] # static_set_contains_unique_occupancy ## [0] NVIDIA H100 PCIe | Key | Distribution | Occupancy | Ref Time | Ref Noise |...
That's expected on a
Will be available once rapidsai/rapids-cmake#399 is resolved
now ready for review
Quick update: I managed to resolve the merge conflicts and, in the process, refactored parts of the benchmark suite. I'll re-run all of the benchmarks tonight to make sure they...