aduffy/lazy-project - Branch - vortex-data/vortex

fix: make StructReader lazy

#6143

Comparing

aduffy/lazy-project

(

7740da2

) with

develop

(

a66a58d

)

-20%

Improvement: 12

Regression: 7

Untouched: 1246

Skipped: 1219

Archived: 75

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

2559 total

into_canonical_non_nullable[(10000, 1, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-20%

33 µs41.1 µs

into_canonical_non_nullable[(10000, 1, 0.01)]

encodings/fastlanes/benches/canonicalize_bench.rs

-17%

39.2 µs47.1 µs

into_canonical_nullable[(10000, 10, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-15%

456 µs536.8 µs

into_canonical_nullable[(10000, 100, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-14%

4.3 ms5 ms

into_canonical_non_nullable[(10000, 1, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

-13%

55.3 µs63.7 µs

canonical_into_nullable[(10000, 100, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-13%

4.3 ms4.9 ms

into_canonical_nullable[(10000, 100, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

-12%

6.1 ms6.9 ms

canonical_into_non_nullable[(10000, 10, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

+43%

278.9 µs195.6 µs

into_canonical_non_nullable[(10000, 10, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

+42%

283.5 µs200.2 µs

canonical_into_non_nullable[(10000, 1, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

+40%

36.2 µs25.8 µs

canonical_into_non_nullable[(10000, 10, 0.01)]

encodings/fastlanes/benches/canonicalize_bench.rs

+37%

306 µs222.7 µs

into_canonical_non_nullable[(10000, 10, 0.01)]

encodings/fastlanes/benches/canonicalize_bench.rs

+36%

310.4 µs227.8 µs

canonical_into_non_nullable[(10000, 1, 0.01)]

encodings/fastlanes/benches/canonicalize_bench.rs

+27%

41.1 µs32.3 µs

canonical_into_non_nullable[(10000, 10, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

+23%

471.6 µs382.2 µs

into_canonical_non_nullable[(10000, 10, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

+23%

472.8 µs383.7 µs

u8_FoR[10M]

vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u8

+19%

8 µs6.8 µs

canonical_into_non_nullable[(10000, 1, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

+19%

57 µs48.1 µs

u64_values_u8_codes[10M]

vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict_cuda::Dict_cuda_u64_u8

+18%

260.3 µs221.5 µs

into_canonical_nullable[(10000, 10, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

+14%

716.9 µs627.6 µs

set_indices_arrow_buffer[128]

vortex-buffer/benches/vortex_bitbuffer.rs

+5%

1.2 µs1.2 µs

into_canonical_non_nullable[(10000, 1000, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

+3%

26.9 ms26.1 ms

true_count_arrow_buffer[128]

vortex-buffer/benches/vortex_bitbuffer.rs

+3%

1 µs1 µs

new_bp_prim_test_between[i64, 2048]

encodings/fastlanes/benches/compute_between.rs::bitpack

+2%

42.3 µs41.3 µs

patched_take_10_contiguous

encodings/fastlanes/benches/bitpacking_take.rs

+2%

30 µs29.3 µs

new_raw_prim_test_between[i64, 2048]

encodings/fastlanes/benches/compute_between.rs::primitive

+2%

27.2 µs26.8 µs

Commits

Click on a commit to change the comparison range

Base

develop

a66a58d

-29.63%

fix: make StructReader lazy

0b9b0f6

1 day ago

by a10y

+9.97%

add tests

7740da2

1 day ago

by a10y

Home Terms Privacy Docs