Yunsong Wang

Refactor CSV reader benchmarks with nvbench

1

## Description Closes #10941 This PR refactors the CSV reader benchmarks with nvbench and reduces the number of test cases by isolating data type, IO type, column selection, and row...

Refactor parquet writer benchmarks with nvbench

2

## Description Issue #10941 Example benchmark Results ## parquet_write_encode ### [0] Quadro RTX 8000 | data_type | cardinality | run_length | Samples | CPU Time | Noise | GPU Time...

Display bytes in base-ten format

1

Similar to #47 This PR updates the code thus numbers of bytes are displayed in base-ten format. i.e. B, MB, KB and GB.

Add distinct key inner join

6

## Description Contributes to #14948 This PR adds a public `cudf::distinct_hash_join` class that provides a fast code path for joins with distinct keys. Only distinct inner join is tackled in...

[BUG] Incorrect statistics for int96 timestamps in parquet

4

**Describe the bug** The statistics calculation is not working properly when dealing with int96 timestamp types. Adding statistics checks in `test_parquet_writer_int96_timestamps` will cause pytest failures. **Steps/Code to reproduce bug** At...

Use cuco::static_set in the hash-based groupby

1

## Description Depends on https://github.com/rapidsai/cudf/pull/14849 Contributes to #12261 This PR migrates hash groupby to use the new `cuco::static_set` data structure. ## Checklist - [x] I am familiar with the [Contributing...

**Is your feature request related to a problem? Please describe.** `cuco::static_map` and `cuco::static_multimap` are used to perform hash-based operations in libcudf. Depending on https://github.com/NVIDIA/cuCollections/issues/110, a lot of existing use cases...

Clean up nvtx macros

3

## Description This PR includes several cleanups for the cudf nvtx wrappers: - Removed the unused `NVTX3_FUNC_RANGE` macro - Fixed a typo in the doc - Added an example in...

## Description ## Checklist - [ ] I am familiar with the [Contributing Guidelines](https://github.com/rapidsai/cudf/blob/HEAD/CONTRIBUTING.md). - [ ] New or existing tests cover these changes. - [ ] The documentation is...