Add a registration mechanism to Aggregators - #30
Draft
devavret wants to merge 949 commits into
Draft
Conversation
…cudf Update cudf
- Disabled gpu anti join. - Disabled expression precompute
…-03-05 Update from Velox main (2025-03-05)
…ea-Project_more_ops2
Add debug utility function to print the cudf table
Streaming partial aggregation
Before that, the count result is incorrect. For companion aggregate function, the step of all the aggregates can be different, facebookincubator#12830 (comment), in this example, HashAggregate(keys=[], functions=[merge_count(l_quantity#80), partial_count(distinct l_partkey#77L)], output=[count#166L, count#169L]), so we cannot use a single step for HashAggregation ``` the step is SINGLE the kind is sum_merge_extract the step is SINGLE the kind is sum_merge_extract the step is SINGLE the kind is count_merge_extract add input 14count reduce stepSINGLE count input 0: {11933.739999999998, -4828.52, 8} 1: {13683.73, -100.96000000000026, 6} 2: {7070.17, 289.63, 8} 3: {13205.7, -952.0400000000004, 8} 4: {7017.68, 4809.41, 5} 5: {129.12, -27.13000000000001, 2} 6: {23060.460000000003, 6369.129999999999, 10} 7: {15549.43, -6224.07, 8} 8: {8111.89, -14071.19, 4} 9: {12510.16, -309.84000000000106, 8} 10: {4638.43, -7112.44, 5} 11: {9982.08, -4268.39, 7} 12: {11483.15, 2080.0799999999995, 8} 13: {1447.4599999999998, -20.260000000000105, 3} get the output 1 [14,139823.2,-24366.590000000004] Elapsed time: 4.389513118 seconds ```
…-2025-05-20 Update from Velox main (2025-05-20) to velox-cudf
feat(stats): add recordOutputStats to CudfLocalPartition
…acebookincubator#21) Due to a bug in `cudfAdapter`, when local partition node is followed by a non-cudf node, a `CudfToVelox` operator was **replacing** the `LocalExchange` at the beginning of the post partition pipeline. Before: ``` Operators before adapting for cuDF: count [4] Operator: ID 0: LocalExchange(0) Operator: ID 1: TopN[4] 1 Operator: ID 2: PartitionedOutput[5] 2 Operator: ID 3: CallbackSink[N/A] 3 Operators after adapting for cuDF: count [4] Operator: ID 0: CudfToVelox[3-to-velox] 0 <<<<======= LocalExchange removed! Operator: ID 1: TopN[4] 1 Operator: ID 2: PartitionedOutput[5] 2 Operator: ID 3: CallbackSink[N/A] 3 ``` After ``` Operators before adapting for cuDF: count [4] Operator: ID 0: LocalExchange(0) Operator: ID 1: TopN[4] 1 Operator: ID 2: PartitionedOutput[5] 2 Operator: ID 3: CallbackSink[N/A] 3 Operators after adapting for cuDF: count [5] Operator: ID 0: LocalExchange(0) Operator: ID 1: CudfToVelox[3-to-velox] 1 Operator: ID 2: TopN[4] 2 Operator: ID 3: PartitionedOutput[5] 3 Operator: ID 4: CallbackSink[N/A] 4 ```
- change null equality to UNEQUAL - handle empty input to build - disable right joins (because design should be different) - disable null aware anti join with filter (need to be implemented as per https://facebookincubator.github.io/velox/develop/anti-join.html ) - Null aware anti join without filter works, and also normal anti join with/without filter works null aware anti join NOT IN Subquery returns a row with a NULL: Empty result. Subquery returns no rows: All of left table. Subquery returns one or more rows and no row has a NULL: left unmatched, without nulls. anti join NOT EXISTS Subquery returns a row with a NULL: left unmatched, including nulls (UNEQUAL). Subquery returns no rows: All of left table. Subquery returns one or more rows and no row has a NULL: left unmatched, including nulls (UNEQUAL). The null behavior is verified with JoinFuzzer. (velox_join_fuzzer) --------- Co-authored-by: Karthikeyan Natarajan <karthikeyann@users.noreply.github.com>
This reverts commit 5fede81.
This reverts commit 344f9e7.
This reverts commit d2eebbd.
Restore ccache
…ream-28-05-2025 Merge velox-cudf branch from upstream 28 05 2025
…ith presto prefix
karthikeyann
force-pushed
the
velox-cudf
branch
from
September 10, 2026 01:18
eb60bff to
d7c312b
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This is an effort in trying to make a registration mechanism for cudf's aggregation operator's equivalent of aggregation functions. Currently it only allows for registration of aggs already supported by cudf but with different names like presto prefixes and spark companion functions.