Add layered pco encoding stack: P1-P5 array implementations
#7926Comparing
claude/analyze-pco-schemes-91DAI
(7d44c51
) withdevelop
(7349cd6
)+20%
- Improvement
- 6
- Untouched
- 1210
- Archived
- 24
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.Benchmarks
1240 total
new_bp_prim_test_between[i64, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack+33%
236.7 µs177.9 µs
new_bp_prim_test_between[i64, 16384]
encodings/fastlanes/benches/compute_between.rs::bitpack+26%
144.4 µs115 µs
new_bp_prim_test_between[i32, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack+21%
169.9 µs141 µs
new_alp_prim_test_between[f64, 16384]
encodings/fastlanes/benches/compute_between.rs::alp+17%
148.8 µs126.8 µs
new_bp_prim_test_between[i32, 16384]
encodings/fastlanes/benches/compute_between.rs::bitpack+15%
109.1 µs94.7 µs
new_bp_prim_test_between[i16, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack+12%
134.1 µs120.1 µs
new_alp_prim_test_between[f32, 32768]
encodings/fastlanes/benches/compute_between.rs::alp+9%
169 µs155 µs
new_bp_prim_test_between[i16, 16384]
encodings/fastlanes/benches/compute_between.rs::bitpack+8%
90 µs82.9 µs
new_alp_prim_test_between[f32, 16384]
encodings/fastlanes/benches/compute_between.rs::alp+7%
112.7 µs105.6 µs
new_alp_prim_test_between[f64, 32768]
encodings/fastlanes/benches/compute_between.rs::alp+6%
252.1 µs237 µs
new_bp_prim_test_between[i64, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+6%
63.5 µs59.8 µs
new_alp_prim_test_between[f64, 2048]
encodings/fastlanes/benches/compute_between.rs::alp+6%
71.8 µs68 µs
cuda/for_bitpacked_6bw/dispatch_u32[100M]
vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda+5%
1.1 ms1 ms
cuda/dict_widen_u16_to_u32/dispatch_u32[100M]
vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda+5%
1,011.7 µs961.5 µs
cuda/dict_256vals_bp8bw_codes/dispatch_u32[100M]
vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda+5%
1.1 ms1.1 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
take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+3%
27.6 µs26.7 µs
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+3%
32.6 µs31.8 µs
new_bp_prim_test_between[i32, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+2%
53.8 µs52.9 µs
chunked_constant_i32_append_to_builder[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+1%
30.9 µs30.5 µs
cuda/dict/u64_values_u32_codes[100M]
vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict::cuda+1%
2.6 ms2.6 ms
encode_varbinview[(10000, 32)]
vortex-array/benches/dict_compress.rs+1%
1 ms1 ms
chunked_opt_bool_canonical_into[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+1%
56.8 µs56.4 µs
take_indices[(10000, 1024)]
encodings/runend/benches/run_end_compress.rs+1%
55.8 µs55.4 µs
chunked_opt_bool_into_canonical[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+1%
72.7 µs72.2 µs
Commits
Click on a commit to change the comparison rangeBase
develop
7349cd6
+20.36%
Add real-dataset benches to layered-pco-bench (P7)
7d44c51
2 days ago
by claude