claude/confident-hamilton-mZIEo - Branch - vortex-data/vortex

perf(fastlanes): fuse bit-packed compare into a transposed mask + untranspose

#8239Merged

Comparing

claude/confident-hamilton-mZIEo

(

bd3fbaa

) with

develop

(

583b003

)

+60%

Improvement: 239

Untouched: 1268

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

1507 total

chunked_into_canonical[(1000, 50, 8, 64)]

encodings/fsst/benches/fsst_compress.rs

6.7 ms6.7 ms

like_substr_low_match

encodings/fsst/benches/fsst_url_compare.rs

11.4 ms11.4 ms

case_when_fragmented[1000]

vortex-array/benches/expr/case_when_bench.rs

443.6 µs443.6 µs

compress_fsst[(1000, 64, 4)]

encodings/fsst/benches/fsst_compress.rs

495.9 µs495.9 µs

chunked_into_canonical[(10, 10000, 16, 4)]

encodings/fsst/benches/fsst_compress.rs

5.2 ms5.2 ms

train_compressor[(1000, 64, 8)]

encodings/fsst/benches/fsst_compress.rs

3.6 ms3.6 ms

chunked_dict_fsst_into_canonical[(1000, 1000, 100)]

encodings/fsst/benches/chunked_dict_fsst_builder.rs

14.2 ms14.2 ms

bitpacked_decompress_u32

vortex/benches/single_encoding_throughput.rs

262.2 µs262.2 µs

turboquant_decompress_dim128_4bit

vortex/benches/single_encoding_throughput.rs::turboquant_benches

5 ms5 ms

take_search[(0.005, 0.05)]

vortex-array/benches/take_patches.rs

132 µs132 µs

case_when_without_else[100000]

vortex-array/benches/expr/case_when_bench.rs

551.1 µs551.1 µs

sparse_is_constant

encodings/sparse/benches/sparse_pushdown.rs

251.3 µs251.3 µs

train_compressor[(10000, 64, 4)]

encodings/fsst/benches/fsst_compress.rs

3.5 ms3.5 ms

chunked_dict_fsst_into_canonical[(1000, 10, 10)]

encodings/fsst/benches/chunked_dict_fsst_builder.rs

1.4 ms1.4 ms

pushdown_compare[(1000, 16, 4)]

encodings/fsst/benches/fsst_compress.rs

140.6 µs140.6 µs

rebuild_naive

encodings/zstd/benches/listview_rebuild.rs

142.4 µs142.4 µs

extend_from_array_zctl[(1000, 8)]

vortex-array/benches/listview_builder_extend.rs

289.7 µs289.7 µs

pushdown_compare[(1000, 64, 8)]

encodings/fsst/benches/fsst_compress.rs

146.9 µs146.9 µs

canonicalize_sparse_list[(512, 7, 4)]

encodings/sparse/benches/sparse_canonical.rs

297.2 µs297.2 µs

bench_dict_mask[(0.9, 0.5)]

vortex-array/benches/dict_mask.rs

1.8 ms1.8 ms

compact[(16384, 10)]

vortex-array/benches/varbinview_compact.rs

2 ms2 ms

chunked_dict_fsst_canonical_into[(1000, 1000, 10)]

encodings/fsst/benches/chunked_dict_fsst_builder.rs

1.5 ms1.5 ms

take_filter_primitive_random_mask_sequential_indices[16384, 1000]

vortex-array/benches/take_filter.rs

166.9 µs166.9 µs

chunked_dict_primitive_into_canonical[u32, (1000, 10, 100)]

vortex-array/benches/chunked_dict_builder.rs

670.2 µs670.2 µs

chunked_dict_fsst_canonical_into[(1000, 1000, 100)]

encodings/fsst/benches/chunked_dict_fsst_builder.rs

13.8 ms13.8 ms

Commits

Click on a commit to change the comparison range

Base

develop

583b003

+46%

perf(fastlanes): fuse bit-packed compare into a transposed mask + untranspose

48da899

12 days ago

by claude

+17.53%

Merge branch 'develop' into claude/confident-hamilton-mZIEo

ab9c8d6

11 days ago

by joseph-isaacs

-4.72%

ci(wasm): pin in-development FastLanes in the excluded wasm-test workspace

08ed4a4

11 days ago

by claude

+5.42%

wip

816032b

11 days ago

by joseph-isaacs

-0.47%

wip

e4dd660

11 days ago

by joseph-isaacs

-65.08%

wip

211903c

11 days ago

by joseph-isaacs

+60.04%

wip

0649f03

11 days ago

by joseph-isaacs

+1.04%

wip

83c90b9

11 days ago

by joseph-isaacs

-1.41%

wip

4d50ff1

11 days ago

by joseph-isaacs

-58.4%

wip

c117649

11 days ago

by joseph-isaacs

+59.68%

wip

10e904c

11 days ago

by joseph-isaacs

+0.41%

Fix sliced_with_patches compare test to obtain a BitPacked via SliceKernel

c495055

11 days ago

by joseph-isaacs

-0.41%

Import SliceKernel instead of absolute path to satisfy clippy::absolute-paths

bd3fbaa

11 days ago

by joseph-isaacs

Home Terms Privacy Docs