[MichaHoffmann]

Scan level conjunct splitting cannot seperate predicates such as a > 1
OR (a = 1 and b > 4), because the disjunction must remain intact.
The struct reader previously skipped pruning for these multi-field
predicates, forcing scans to decode zones that column statistics could
rule out.

Summary

• Tracking Issue: #000

Changes

[joseph-isaacs]

Thanks for the contribution.

Does the conjunct partitioner not handle this in the ScanBuilder/exec_splits methods.

Can we try and unify this logic with other parts of the StructLayoutReader

[codspeed]

Merging this PR will regress 5 benchmarks

4 warnings, 1 note

⚠️ Walltime results may be unreliable

Some benchmarks used the Walltime instrument outside CodSpeed Macro Runners, which can make the results inconsistent.

Learn more about Macro Runners

See affected benchmarks

⚠️ Unable to measure the execution of 1 benchmark

This benchmark measured no execution time, so its result is not comparable and counts as unchanged. This usually happens when the compiler removes the code under test.

Prevent compiler optimizations

See affected benchmarks

⚠️ 19 benchmarks are dominated by system calls

System calls cannot be simulated consistently and are left out of the measure. The reported value understates the real cost. Switch to the Walltime instrument to measure them.

Learn more about system calls

See affected benchmarks

⚠️ Base and head ran on different runner types

Some benchmarks with significant performance changes were compared across different runner types, so the changes might not come from the code. Run base and head on the same runner type, or use CodSpeed Macro Runners for more stable results.

Learn more about Macro Runners

Open the report in CodSpeed to investigate

ℹ️ 40 benchmarks have no flamegraph

The flamegraph wasn't generated: the symbols of the profiling trace could not be resolved, because no information about the language frames was collected.

See affected benchmarks

⚡ 2 improved benchmarks
❌ 5 regressed benchmarks
✅ 2401 untouched benchmarks
⏩ 12 skipped benchmarks¹

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
❌	Walltime	threshold_neon[80]	3.4 µs	4.4 µs	-22.99%
❌	Walltime	filter_neon[8]	883 ns	1,089 ns	-18.92%
❌	Walltime	filter_neon[64]	1.7 µs	2 µs	-14.16%
❌	Walltime	bitpack_blocked_compress_avx2	6.8 µs	7.6 µs	-10.98%
❌	Walltime	filter_neon[80]	2.5 µs	2.7 µs	-10.26%
⚡	CPU Simulation	bench_compare_sliced_dict_primitive[(2000, 10000)]	67.6 µs	13.2 µs	×5.1
⚡	Walltime	starts_with_avx2[64, VarBin]	62.6 µs	56 µs	+11.85%

Tip

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

---

_{Comparing MichaHoffmann:compound-key-pruning (096e752) with develop (86d2845)}

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. ↩

[MichaHoffmann]

Thanks for the contribution.

Does the conjunct partitioner not handle this in the ScanBuilder/exec_splits methods.

Can we try and unify this logic with other parts of the StructLayoutReader

No it doesnt because the condition contains a disjunction! But the AI helped me to unify the logic a little and simplfiy the PR drastically!