[yiquanzhou]

Summary

• Tracking Issue: vortex-datafusion: comparisons on RunEndEncoded<Dictionary> string columns are no longer pushed down #10634

For ree_dict = 'x' on a RunEndEncoded<_, Dictionary<_, Utf8>> column, DataFusion's comparison coercion produces CAST(ree_dict AS Dictionary(UInt32, Utf8)) = 'x'. Since #9785 the converter rejects that cast, so the filter runs in DataFusion instead of the scan. Results stay correct, but pushdown is lost. Both Arrow types map to Vortex Utf8, so Vortex has nothing to cast.

Changes

supported_cast becomes classify_cast, which either drops a cast, keeps it as a Vortex cast, or leaves it in DataFusion:

• Drop (the converted child is returned unchanged) when the Arrow cast cannot fail and the Vortex dtype is unchanged:

  • identity casts;
  • REE<Int16 | Int32, Dict<K, V>> → Dict<K, V>.

  Arrow expands runs with take on Int32 indices, and take on a dictionary only gathers keys. A dropped cast no longer blocks pushdown under AND/OR or in IN lists.

• Keep numeric widening, as before.

• Leave in DataFusion everything else, including:

  • Int64 run ends (Arrow's indices may wrap);
  • REE<_, V> → V when expanding values can fail (for example, Utf8/Binary offset overflow);
  • Dict<K, V> → V (out of scope; see below);
  • dictionary key changes;
  • V → Dict<K, V>;
  • LargeUtf8 → Utf8.

Tests:

• The issue's repro (coerce, simplify, plan) for =, OR and IN, asserting no cast node remains.
• Accepted and rejected casts.
• Vortex vs. DataFusion evaluation on an REE batch with nulls and unreferenced dictionary values.
• A .vortex scan vs. MemTable test that also asserts the filter is accepted by the scan when pushdown is enabled.

Follow-up scope

Dict<K, V> → V is deliberately out of scope for this PR. Arrow decodes a dictionary by gathering one value per key. For offset-based values such as Utf8 or Binary, the decoded output can exceed the offset limit and the cast can fail. A follow-up can allow specific value types only after checking that the Arrow cast cannot fail, preserves values and nulls, and leaves the expected Vortex dtype. For now, all dictionary-to-value casts stay in DataFusion.

Known limitation: an unsimplified predicate still casts the literal (Utf8 → Dict), which remains unsupported.

AI assistance

Disclosed per the AI policy: the investigation, code and tests were drafted with Claude (Claude Code) and reviewed by me.

[codspeed]

Merging this PR will regress 9 benchmarks

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

⚠️ 1 benchmark measured no execution time

Nothing ran under measurement, usually because the compiler removed the code under test. This result is not comparable, so it counts as unchanged.

Preventing compiler optimizations

• bench_compare_primitive[(10000, 2)]

⚠️ 16 benchmarks spent significant time in system calls

System calls cannot be consistently instrumented, so they are not included in the measure, which understates the real cost. Please switch to the Walltime instrument to accurately measure system calls.

Measurement and system calls

• random_i128[0.01]
• test_scan_filter[int]
• take_indices[(10000, 4096)]
• decode_primitives[i64, (1000, 8)]
• compress_fsst[(500, 16, 4)]
• filter_run_end[len=4096_run=16_density=0.1]
• test_scan_filter[int_float]
• decompress[u16, (4000, 256)]
• test_scan[int_str]
• test_scan_filter[int_str_float]
• …and 6 more

ℹ️ 40 benchmarks have no flame graph

The flamegraph could not be generated because we failed to resolve the symbols in the profiling trace. This happens when we fail to harvest information about language frames.

• test_repeated_scan_scalar_at[int]
• test_scan_filter_to_arrow_array[int_float]
• test_scan_scalar_at[int_float]
• test_repeated_scan_filter[int]
• test_repeated_scan_filter[int_float]
• test_scan_filter_to_arrow_array[int]
• test_scan_filter[int]
• test_repeated_scan_scalar_at[int_str_float]
• test_repeated_scan_to_arrow_array[int]
• test_scan_scalar_at[int_str_float]
• …and 30 more

⚠️ Different runtime environments detected

Some benchmarks with significant performance changes were compared across different runtime environments,
which may affect the accuracy of the results.

Open the report in CodSpeed to investigate

⚡ 17 improved benchmarks
❌ 9 regressed benchmarks
✅ 2382 untouched benchmarks
⏩ 12 skipped benchmarks¹

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
❌	WallTime	mul_u64_nonnull_neon	20.5 µs	39 µs	-47.49%
❌	WallTime	filter_neon[8]	909 ns	1,549 ns	-41.32%
❌	WallTime	filter_neon[64]	1.8 µs	2.9 µs	-39.45%
❌	WallTime	threshold_neon[8]	1.4 µs	2.4 µs	-39.25%
❌	WallTime	filter_neon[80]	2.5 µs	3.5 µs	-28.41%
❌	Simulation	density_sweep_dense_runs[0.001]	44.5 µs	61.4 µs	-27.55%
❌	WallTime	threshold_neon[64]	2.7 µs	3.6 µs	-25.75%
❌	WallTime	threshold_neon[80]	3.5 µs	4.5 µs	-20.79%
❌	WallTime	starts_with_avx512[64, VarBin]	53.3 µs	59.3 µs	-10.17%
⚡	Simulation	column_x_constant	580.9 µs	153.5 µs	×3.8
⚡	Simulation	column_x_column	168.6 µs	107.9 µs	+56.26%
⚡	Simulation	nullable_columns	183.2 µs	124.7 µs	+46.99%
⚡ ℹ️	Simulation	test_repeated_scan_scalar_at[int]	354.3 µs	245.4 µs	+44.39%
⚡ ⚠️	Simulation	random_i128[0.01]	6.4 µs	5.4 µs	+16.79%
⚡ ℹ️	Simulation	test_scan_filter_to_arrow_array[int_float]	4.1 ms	3.5 ms	+15.59%
⚡ ℹ️	Simulation	test_scan_scalar_at[int_float]	1,079.2 µs	956.9 µs	+12.78%
⚡	WallTime	bitpack_blocked_compress_avx2	7.7 µs	6.8 µs	+12.6%
⚡ ℹ️	Simulation	test_repeated_scan_filter[int]	2.8 ms	2.5 ms	+12.46%
⚡	Simulation	eight_points	642.6 µs	571.7 µs	+12.4%
⚡ ℹ️	Simulation	test_repeated_scan_filter[int_float]	3.8 ms	3.4 ms	+11.83%
...	...	...	...	...	...

ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.

Tip

Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.

---

_{Comparing yiquanzhou:fix/ree-dict-cast-pushdown (b6191f9) with develop (f990a5d)²}

Footnotes

1. 12 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

2. No successful run was found on develop (c48457b) during the generation of this report, so f990a5d was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩