Comparing
ct/tq-inv-direction-norms
(353a0ee
) withct/tq-docs
(f852d72
)-4%
- Improvement
- 1
- Regression
- 2
- Untouched
- 1234
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.No successful run was found on ct/tq-docs ( 14c7c24) during the generation of this report, so develop ( f852d72) was used instead as the comparison base. There might be some changes unrelated to this pull request in this report.
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
1237 total
new_alp_prim_test_between[f32, 32768]
encodings/fastlanes/benches/compute_between.rs::alp-16%
154 µs182.9 µs
new_alp_prim_test_between[f32, 16384]
encodings/fastlanes/benches/compute_between.rs::alp-12%
104.6 µs119.2 µs
chunked_varbinview_opt_canonical_into[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+20%
225.1 µs187.9 µs
cuda/runend/i32_runlen_1000[100M]
vortex-cuda/benches/runend_cuda.rs::benches::benchmark_runend::cuda+6%
915.7 µs863.8 µs
encode_varbinview[(10000, 8)]
vortex-array/benches/dict_compress.rs+4%
1.1 ms1 ms
chunked_dict_fsst_canonical_into[(1000, 100, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14 ms13.6 ms
chunked_dict_fsst_canonical_into[(1000, 10, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
13.9 ms13.6 ms
chunked_dict_fsst_into_canonical[(1000, 100, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14 ms13.7 ms
chunked_dict_fsst_canonical_into[(1000, 1000, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14.9 ms14.5 ms
chunked_dict_fsst_into_canonical[(1000, 1000, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+2%
14.9 ms14.6 ms
encode_varbin[(1000, 32)]
vortex-array/benches/dict_compress.rs+2%
171.2 µs167.5 µs
decode_primitives[f32, (1000, 512)]
vortex-array/benches/dict_compress.rs+2%
18.7 µs18.3 µs
encode_varbin[(1000, 8)]
vortex-array/benches/dict_compress.rs+2%
165.6 µs162.1 µs
new_bp_prim_test_between[i16, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+2%
49.6 µs48.7 µs
transpose_bmi2
encodings/fastlanes/benches/bit_transpose.rs::x86+2%
1.8 µs1.7 µs
untranspose_bmi2
encodings/fastlanes/benches/bit_transpose.rs::x86+2%
1.8 µs1.7 µs
take_map[(0.005, 1.0)]
vortex-array/benches/take_patches.rs+2%
1.1 ms1.1 ms
cuda/runend/i32_runlen_100000[100M]
vortex-cuda/benches/runend_cuda.rs::benches::benchmark_runend::cuda+1%
837.6 µs828.4 µs
chunked_opt_bool_into_canonical[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+1%
69.8 µs69.1 µs
take_indices[(1000, 16)]
encodings/runend/benches/run_end_compress.rs+1%
39.6 µs39.2 µs
take_map[(0.01, 0.5)]
vortex-array/benches/take_patches.rs+1%
609 µs604.2 µs
take_indices[(10000, 256)]
encodings/runend/benches/run_end_compress.rs+1%
56.1 µs55.6 µs
encode_varbinview[(10000, 4)]
vortex-array/benches/dict_compress.rs+1%
1 ms1 ms
chunked_varbinview_into_canonical[(10, 1000)]
vortex-array/benches/chunk_array_builder.rs+1%
1.9 ms1.9 ms
decode_primitives[f32, (10000, 512)]
vortex-array/benches/dict_compress.rs+1%
48.9 µs48.6 µs
Commits
Click on a commit to change the comparison rangeBase
develop
f852d72
-3.96%
Harden TurboQuant L2Norm fast path and document the crate
353a0ee
2 hours ago
by connortsui20