refactor[fsst]: take VarBinView directly, decide offset width upfront
#7900Comparing
mp/fsst-compress-refactor
(3dec60f
) withdevelop
(2699169
)+7%
- Improvement
- 3
- Regression
- 1
- Untouched
- 1247
- New
- 2
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.Different runtime environments detected
Some benchmarks with significant performance changes were compared across different runtime environments, which may affect the accuracy of the results. Learn more about regression causes.Benchmarks
1253 total
chunked_varbinview_opt_canonical_into[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs-17%
187.4 µs224.8 µs
eq_pushdown_low_match
encodings/fsst/benches/fsst_url_compare.rs+19%
1,152.5 µs970 µs
eq_pushdown_high_match
encodings/fsst/benches/fsst_url_compare.rs+17%
1.2 ms1.1 ms
chunked_varbinview_canonical_into[(100, 100)]
vortex-array/benches/chunk_array_builder.rs+13%
307.8 µs273.1 µs
eq_pushdown_high_match_view
encodings/fsst/benches/fsst_url_compare.rsN/A
N/A1.1 ms
eq_pushdown_low_match_view
encodings/fsst/benches/fsst_url_compare.rsN/A
N/A969.1 µs
train_compressor[(10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+8%
3.3 ms3.1 ms
train_compressor[(10000, 64, 4)]
encodings/fsst/benches/fsst_compress.rs+7%
3.5 ms3.3 ms
fsst_prefix[email]
encodings/fsst/benches/fsst_like.rs+7%
2.8 ms2.6 ms
train_compressor[(10000, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+7%
3.5 ms3.3 ms
fsst_prefix[path]
encodings/fsst/benches/fsst_like.rs+7%
2.8 ms2.6 ms
fsst_prefix[urls]
encodings/fsst/benches/fsst_like.rs+7%
3 ms2.8 ms
train_compressor[(10000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+7%
3.8 ms3.5 ms
train_compressor[(10000, 16, 8)]
encodings/fsst/benches/fsst_compress.rs+6%
4 ms3.8 ms
train_compressor[(10000, 64, 8)]
encodings/fsst/benches/fsst_compress.rs+6%
4 ms3.8 ms
fsst_prefix[json]
encodings/fsst/benches/fsst_like.rs+5%
3.5 ms3.3 ms
compress_fsst[(10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+5%
1.5 ms1.5 ms
compress_fsst[(1000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+5%
178.9 µs171.1 µs
compress_fsst[(1000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+5%
190.1 µs181.9 µs
compress_fsst[(10000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+4%
1.6 ms1.5 ms
pushdown_compare[(10000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+4%
423.8 µs405.7 µs
pushdown_compare[(10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+4%
417.8 µs400 µs
pushdown_compare[(10000, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+4%
417.7 µs400.1 µs
pushdown_compare[(10000, 64, 4)]
encodings/fsst/benches/fsst_compress.rs+4%
417.2 µs399.8 µs
fsst_prefix[rare]
encodings/fsst/benches/fsst_like.rs+4%
4.4 ms4.2 ms
Commits
Click on a commit to change the comparison rangeBase
develop
2699169
+18.64%
refactor[fsst]: take VarBinView directly, decide offset width upfront
f110e06
26 days ago
by mprammer0%
Merge branch 'develop' into mp/fsst-compress-refactor
a2891ec
26 days ago
by mprammer-0.84%
use mask.true_count()
f40189e
24 days ago
by mprammer+0.09%
Take ArrayRef in fsst_compress and dispatch on encoding internally
27c96a2
18 days ago
by mprammer-10.94%
Merge branch 'develop' into mp/fsst-compress-refactor
3dec60f
13 days ago
by mprammer