-
Notifications
You must be signed in to change notification settings - Fork 4k
Open
Description
Reporter: Neal Richardson / @nealrichardson
Related issues:
- [C++][Compute] Implement TopK/BottomK (is a parent of)
- [C++][Compute] Wrap grouped aggregation in an ExecNode (is a parent of)
- [C++][Compute] Provide a registry for ExecNode implementations (is a parent of)
- TPC-H Data Generator Node (is a parent of)
- [C++][Compute] Add support for imperfect grouping for use in radix partitioning (is a parent of)
- [C++][Compute] Use generic hash-aggregate for DictionaryArrays (is a parent of)
- [C++][Compute] GroupBy: add unittests for individual components of hash group by (is a parent of)
- [C++][Compute] GroupBy: add parallelism to hash group by (is a parent of)
- [C++][Compute] GroupBy: support more than 2^32 groups (is a parent of)
- [C++][Compute] Make GroupBy optimizations work on Big Endian architecture (is a parent of)
- [C++][Compute] Support tagging ExecBatches with arbitrary extra information (is a parent of)
- [C++] Add StopToken to ExecNode (is a parent of)
- [C++][Compute] Add Find method to Grouper (is a parent of)
- [C++][Compute] Add residual predicate support to new (Swiss) hash join (is a parent of)
- [C++][Compute] Add dictionary support to new (Swiss) hash join (is a parent of)
- [C++][Acero] Add Window Functions exec node (is a parent of)
- [C++] Take kernel can't handle ChunkedArrays that don't fit in an Array (is a parent of)
- [C++][Compute] Implement many-to-many inner hash join (is a parent of)
- [C++][Compute] Hash Join support for dictionary (is a parent of)
- [C++] Measure microperformance associated with ExecBatchIterator (is a parent of)
- [C++][Compute] Add ExecNode hierarchy (is a parent of)
- [C++][Dataset][Compute] Refactor Dataset scans to use an ExecNode graph (is a parent of)
- [C++][Dataset][Compute] Replace UnionDataset with Union ExecNode (is a parent of)
- [C++][Compute] Improve performance of the hash table used in GroupIdentifier (is a parent of)
- [C++][Compute] GroupBy: improve performance by encoding keys in row format only when they are inserted into hash table (is a parent of)
- [C++][Compute] Implement count_distinct/distinct hash aggregate kernels (is a parent of)
- [C++][Compute] Document ExecNode, ExecPlan (is a parent of)
- [C++][Dataset][Compute] Substitute ExecPlan impl for dataset scans (is a parent of)
- [C++][Compute] Add ExecNode for semi and anti-semi join (is a parent of)
- [C++][Compute] Add ScalarAggregateNode (is a parent of)
- [C++][Compute] Join: add set membership test method to the grouper (is a parent of)
- [C++][Compute] Add OrderByNode for ordering of rows in an ExecPlan (is a parent of)
- [C++][Compute][Dataset] Add dataset::WriteNode for writing rows from an ExecPlan to disk (is a parent of)
- [C++][Compute] Replace ExecNode::InputReceived with ::MakeTask (is a parent of)
- [C++][Compute] Hash Join performance improvement (is a parent of)
- [C++][Compute] Introduce Bloom filters to hash join (is a parent of)
- [C++][Compute] Implement Bloom filter pushdown between hash joins (is a parent of)
- [C++][Compute] Implement outer join with support for residual predicates (is a parent of)
Note: This issue was originally created as ARROW-12633. Please see the migration documentation for further details.