[robert3005]

The filter of bit-packed, sequence and run-end arrays, run-end decoding
and constant byte views allocated their output buffers from the global
allocator. Allocate them through the allocator of the execution context
instead, so a session can choose where decoded buffers come from.

[codspeed]

Merging this PR will degrade performance by 10.71%

⚠️ 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)]

⚠️ 23 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

• decompress[u16, (4000, 256)]
• decompress[u32, (1000, 256)]
• compress_fsst[(500, 16, 8)]
• random_i128[0.01]
• bench_compare_sliced_dict_primitive[(3333, 10000)]
• filter_run_end[len=4096_run=16_density=0.1]
• test_scan_filter[int_float]
• chunked_dict_primitive_canonical_into[u64, (1000, 1000, 10)]
• test_scan_filter[int_str_float]
• chunked_dict_primitive_canonical_into[f64, (1000, 1000, 10)]
• …and 13 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_str]
• test_repeated_scan[int]
• test_scan_filter[int]
• test_repeated_scan_scalar_at[int]
• test_repeated_scan_scalar_at[int_str_float]
• test_scan[int_float]
• test_scan_scalar_at[int]
• test_scan_filter[int_float]
• test_scan_filter_to_arrow_array[int_str_float]
• test_repeated_scan_filter[int_str]
• …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

⚡ 4 improved benchmarks
❌ 10 regressed benchmarks
✅ 2394 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[8]	1.5 µs	2.5 µs	-39.66%
❌	WallTime	filter_neon[8]	871 ns	1,214 ns	-28.25%
❌	WallTime	threshold_neon[64]	2.7 µs	3.8 µs	-27.71%
❌	WallTime	threshold_neon[80]	3.7 µs	4.6 µs	-19.29%
❌	WallTime	filter_neon[64]	1.7 µs	2.1 µs	-15.85%
❌	WallTime	filter_neon[80]	2.5 µs	2.9 µs	-13.96%
❌	WallTime	bitpack_blocked_compress_avx2	6.7 µs	7.6 µs	-11.32%
❌	WallTime	starts_with_avx512[64, VarBin]	52.9 µs	59.6 µs	-11.25%
❌	Simulation	take[routing/grouped_chunks/primitive/nonnull/chunks=32/indices=1000]	385 µs	428.9 µs	-10.24%
❌	Simulation	decompress[u8, (1000, 256)]	28.1 µs	31.2 µs	-10.06%
⚡	Simulation	chunked_opt_bool_canonical_into[(1000, 10)]	65.4 µs	55.5 µs	+17.81%
⚡ ℹ️	Simulation	test_repeated_scan_scalar_at[int_str]	481.3 µs	409.8 µs	+17.44%
⚡	WallTime	threshold_avx2[80]	3 µs	2.6 µs	+14.54%
⚡	WallTime	starts_with_avx2[64, VarBin]	60.4 µs	54.4 µs	+11.18%

Tip

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

---

_{Comparing rk/kernel-allocator (200cb9f) with develop (61ff28d)}

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. ↩