fix(fsst): adaptive i32→i64 codes_offsets promotion
#7851Comparing
mp/fsst-i32-overflow-adaptive
(9e2bcdc
) withdevelop
(ff12040
)-25%
- Improvement
- 2
- Regression
- 6
- Untouched
- 1200
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
1208 total
new_bp_prim_test_between[i64, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack-25%
178.3 µs237.6 µs
new_bp_prim_test_between[i64, 16384]
encodings/fastlanes/benches/compute_between.rs::bitpack-21%
115.5 µs145.4 µs
new_bp_prim_test_between[i32, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack-17%
141.2 µs170.8 µs
new_alp_prim_test_between[f64, 16384]
encodings/fastlanes/benches/compute_between.rs::alp-15%
127.3 µs149.8 µs
new_bp_prim_test_between[i32, 16384]
encodings/fastlanes/benches/compute_between.rs::bitpack-14%
94.9 µs110 µs
new_bp_prim_test_between[i16, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack-11%
120.6 µs135.1 µs
take_map[(0.1, 0.5)]
vortex-array/benches/take_patches.rs+12%
1,111.5 µs988.1 µs
take_map[(0.1, 1.0)]
vortex-array/benches/take_patches.rs+12%
1.8 ms1.6 ms
null_count_run_end[(10000, 1024, 0.01)]
encodings/runend/benches/run_end_null_count.rs+5%
3.4 µs3.3 µs
null_count_run_end[(10000, 256, 0.01)]
encodings/runend/benches/run_end_null_count.rs+5%
3.4 µs3.3 µs
null_count_run_end[(100000, 1024, 0.01)]
encodings/runend/benches/run_end_null_count.rs+5%
3.4 µs3.3 µs
take_map[(0.1, 0.1)]
vortex-array/benches/take_patches.rs+5%
476 µs453.1 µs
take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+4%
27.6 µs26.6 µs
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+3%
32.7 µs31.6 µs
pack_return_dtype[1000]
vortex-array/benches/expr/large_struct_pack.rs+2%
647.3 µs632.7 µs
pack_return_dtype[2000]
vortex-array/benches/expr/large_struct_pack.rs+2%
1.3 ms1.3 ms
pack_return_dtype[100]
vortex-array/benches/expr/large_struct_pack.rs+2%
68.7 µs67.2 µs
pack_return_dtype[500]
vortex-array/benches/expr/large_struct_pack.rs+2%
324.3 µs317.6 µs
compact[(16384, 90)]
vortex-array/benches/varbinview_compact.rs+2%
1.9 ms1.8 ms
compact[(4096, 90)]
vortex-array/benches/varbinview_compact.rs+2%
491.8 µs482.5 µs
chunked_dict_primitive_canonical_into[u32, (1000, 10, 100)]
vortex-array/benches/chunked_dict_builder.rs+2%
716 µs702.6 µs
decompress[u16, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+2%
18.9 µs18.5 µs
compact[(16384, 10)]
vortex-array/benches/varbinview_compact.rs+2%
2 ms1.9 ms
chunked_dict_primitive_canonical_into[u32, (1000, 100, 100)]
vortex-array/benches/chunked_dict_builder.rs+2%
731.4 µs718.5 µs
decompress[u8, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+2%
16.7 µs16.4 µs
Commits
Click on a commit to change the comparison rangeBase
develop
ff12040
-24.95%
fix(fsst): adaptive i32→i64 codes_offsets promotion (#7833)
9e2bcdc
19 hours ago
by mprammer