perf[runend]: run_end_bool decompress#6229
Conversation
Merging this PR will degrade performance by 12.26%
Performance Changes
Comparing Footnotes
|
Benchmarks: TPC-H SF=1 on NVMESummary
Detailed Results Table
|
Benchmarks: FineWeb NVMeSummary
Detailed Results Table
|
Benchmarks: Random AccessSummary
Detailed Results Table
|
Benchmarks: TPC-H SF=1 on S3Summary
Detailed Results Table
|
Benchmarks: TPC-DS SF=1 on NVMESummary
Detailed Results Table
|
Benchmarks: TPC-H SF=10 on NVMESummary
Detailed Results Table
|
Benchmarks: FineWeb S3Summary
Detailed Results Table
|
Benchmarks: Statistical and Population GeneticsSummary
Detailed Results Table
|
Benchmarks: TPC-H SF=10 on S3Summary
Detailed Results Table
|
Benchmarks: Clickbench on NVMESummary
Detailed Results Table
|
Benchmarks: CompressionSummary
Detailed Results Table
|
robert3005
left a comment
There was a problem hiding this comment.
Love me some prefilling
|
This PR has been marked as stale because it has been open for 30 days with no activity. Please comment or remove the stale label if you wish to keep it active, otherwise it will be closed in 7 days |
ab1cffe to
3222cdc
Compare
robert3005
left a comment
There was a problem hiding this comment.
I think there's a bit too much llm leftover code here
… and fill_bits - Add `fill_bits` free function to vortex-buffer for efficient bit-range filling on raw `&mut [u8]` slices - Add `BitBufferMut::fill_range` method that delegates to `fill_bits` - Refactor `append_n` to delegate to `fill_range`, eliminating duplication - Replace private `fill_bits_true`/`fill_bits_false`/`flip_bits` helpers in decompress_bool.rs with `BitBufferMut::fill_range` - Simplify few-runs nullable path to use `append_n` directly - Replace `prefill_buffer` helper with `BitBufferMut::full` - Remove unused re-export of `runend_decode_bools` from compress.rs - Remove baseline benchmark code (decode_bool_nullable_develop) - Delete PERF_NOTES.md - Fix clippy is_multiple_of warnings in benchmarks Signed-off-by: Joseph Isaacs <joe@spiraldb.com> Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Benchmarks: PolarSignals ProfilingSummary
Detailed Results Table
|
cad9f85 to
6e8ef5c
Compare
Polar Signals Profiling ResultsLatest Run
Powered by Polar Signals Cloud |
speed up runend bool decompress