perf(fastlanes): fuse bit-packed compare into a transposed mask + untranspose
#8239Comparing
claude/confident-hamilton-mZIEo
(211903c
) withdevelop
(4e6e9ed
)-1%
- Improvement
- 1
- Regression
- 2
- Untouched
- 1504
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.Benchmarks
1507 total
chunked_varbinview_canonical_into[(100, 100)]
vortex-array/benches/chunk_array_builder.rs-11%
269.9 µs304.9 µs
baseline_lt[16, 65536]
encodings/fastlanes/benches/bitpack_compare.rs-11%
216.1 µs244.1 µs
chunked_varbinview_canonical_into[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+23%
197.1 µs160.7 µs
compare[1]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i8+7%
163.2 µs152.5 µs
compare[2]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i8+7%
164.9 µs154.2 µs
compare[3]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i8+7%
171.6 µs160.8 µs
compare[1]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i16+7%
165.9 µs155.5 µs
compare[1]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::u8+7%
170.5 µs159.9 µs
compare[2]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::u8+7%
171.9 µs161.3 µs
compare[4]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i8+7%
174.6 µs163.8 µs
compare[2]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i16+7%
167.7 µs157.4 µs
compare[1]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i32+6%
169 µs158.8 µs
compare[2]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i32+6%
170.5 µs160.2 µs
fast_eq_out_of_range[4, 65536]
encodings/fastlanes/benches/bitpack_compare.rs+6%
173.7 µs163.3 µs
compare[3]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::u8+6%
178.5 µs167.8 µs
compare[5]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i8+6%
180.1 µs169.3 µs
compare[3]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i32+6%
173.2 µs162.9 µs
compare[3]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i16+6%
174 µs163.7 µs
compare[1]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::u16+6%
172.7 µs162.5 µs
compare[4]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i32+6%
174.5 µs164.2 µs
compare[1]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i64+6%
179 µs168.5 µs
compare[4]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::u8+6%
181.5 µs170.9 µs
compare[4]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i16+6%
177.2 µs166.9 µs
compare[6]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i8+6%
183.9 µs173.2 µs
compare[5]
encodings/fastlanes/benches/bitpack_compare_sweep.rs::i32+6%
177.5 µs167.3 µs
Commits
Click on a commit to change the comparison rangeBase
develop
4e6e9ed
+46%
perf(fastlanes): fuse bit-packed compare into a transposed mask + untranspose
48da899
21 hours ago
by claude+17.53%
Merge branch 'develop' into claude/confident-hamilton-mZIEo
ab9c8d6
4 hours ago
by joseph-isaacs-4.72%
ci(wasm): pin in-development FastLanes in the excluded wasm-test workspace
08ed4a4
3 hours ago
by claude+5.42%
wip
816032b
58 minutes ago
by joseph-isaacs-0.47%
wip
e4dd660
53 minutes ago
by joseph-isaacs-65.08%
wip
211903c
46 minutes ago
by joseph-isaacs