fastlanes: streaming compare + between kernels for BitPacked
#8015Comparing
claude/fastlane-compare-kernel-7slGu
(ee44dd6
) withdevelop
(7b47788
)+32%
- Improvement
- 25
- Regression
- 5
- Untouched
- 1207
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
1237 total
new_alp_prim_test_between[f64, 16384]
encodings/fastlanes/benches/compute_between.rs::alp+14%
146.9 µs128.3 µs
new_bp_prim_test_between[i64, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack+14%
222.7 µs194.7 µs
new_bp_prim_test_between[i16, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+14%
48.9 µs42.8 µs
baseline_eq[16, 65536]
encodings/fastlanes/benches/bitpack_compare.rs+13%
259.4 µs229.9 µs
chunked_varbinview_into_canonical[(100, 100)]
vortex-array/benches/chunk_array_builder.rs+11%
358.4 µs323.5 µs
chunked_varbinview_opt_canonical_into[(100, 100)]
vortex-array/benches/chunk_array_builder.rs+9%
410.8 µs377.3 µs
cuda/runend/i32_runlen_100000[100M]
vortex-cuda/benches/runend_cuda.rs::benches::benchmark_runend::cuda+5%
872.4 µs829.4 µs
cuda/dict_64vals_bp6bw_codes_alp_for_bp6bw_f32_values/dispatch_f32[100M]
vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda+5%
1.1 ms1 ms
cuda/alp_for_bp_6bw_f32/dispatch_f32[100M]
vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda+5%
1.1 ms1.1 ms
chunked_bool_canonical_into[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+3%
45 µs43.6 µs
chunked_dict_fsst_into_canonical[(1000, 100, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14 ms13.6 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_canonical_into[(1000, 1000, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14.9 ms14.5 ms
push_n_vortex_buffer[u16, 128]
vortex-buffer/benches/vortex_buffer.rs+2%
1.6 µs1.6 µs
map_each[Buffer<i32>, 128]
vortex-buffer/benches/vortex_buffer.rs+2%
1.9 µs1.8 µs
push_n_vortex_buffer[u64, 128]
vortex-buffer/benches/vortex_buffer.rs+2%
1.9 µs1.9 µs
untranspose_scalar
encodings/fastlanes/benches/bit_transpose.rs+1%
2.4 µs2.3 µs
push_n_vortex_buffer[u16, 1024]
vortex-buffer/benches/vortex_buffer.rs+1%
3.2 µs3.2 µs
map_each[Buffer<i32>, 1024]
vortex-buffer/benches/vortex_buffer.rs+1%
3.6 µs3.6 µs
canonicalize_compare[(1000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+1%
130.5 µs129.5 µs
bench_compare_sliced_dict_primitive[(2000, 10000)]
vortex-array/benches/dict_compare.rs+1%
91.1 µs90.5 µs
push_n_vortex_buffer[u16, 2048]
vortex-buffer/benches/vortex_buffer.rs+1%
4.5 µs4.5 µs
bench_compare_sliced_dict_varbinview[(1000, 10000)]
vortex-array/benches/dict_compare.rs+1%
119.9 µs119.2 µs
decompress_alp[f64, (1000, 0.01, 1.0)]
encodings/alp/benches/alp_compress.rs+1%
15.9 µs15.8 µs
Commits
Click on a commit to change the comparison rangeBase
develop
7b47788
+32.36%
fastlanes: streaming compare + between kernels for BitPacked
ee44dd6
2 days ago
by claude