ad/new-launch-kernel-fn - Branch - vortex-data/vortex

chore: custom kernel launcher API to remove macro

#6112

Comparing

ad/new-launch-kernel-fn

(

5cd76db

) with

develop

(

238d063

)

-30%

Improvement: 3

Regression: 15

Untouched: 1256

Skipped: 1254

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

2528 total

u64_FoR[10K]

vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u64

-30%

9.7 µs13.8 µs

canonical_into_non_nullable[(10000, 100, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-29%

1.9 ms2.7 ms

into_canonical_non_nullable[(10000, 100, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-29%

1.9 ms2.7 ms

canonical_into_non_nullable[(10000, 100, 0.01)]

encodings/fastlanes/benches/canonicalize_bench.rs

-27%

2.1 ms2.9 ms

into_canonical_non_nullable[(10000, 100, 0.01)]

encodings/fastlanes/benches/canonicalize_bench.rs

-27%

2.2 ms3 ms

canonical_into_non_nullable[(10000, 1, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-21%

30.9 µs39 µs

canonical_into_non_nullable[(10000, 1, 0.01)]

encodings/fastlanes/benches/canonicalize_bench.rs

-18%

36 µs44.2 µs

canonical_into_non_nullable[(10000, 100, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

-18%

3.7 ms4.5 ms

into_canonical_non_nullable[(10000, 100, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

-18%

3.8 ms4.6 ms

u16_FoR[1K]

vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u16

-18%

5.6 µs6.9 µs

patched_take_10k_contiguous_patches

encodings/fastlanes/benches/bitpacking_take.rs

-17%

2 ms2.5 ms

into_canonical_nullable[(10000, 100, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

-16%

4.4 ms5.2 ms

u16_FoR[10M]

vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u16

-14%

9.7 µs11.4 µs

canonical_into_non_nullable[(10000, 1, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

-14%

52 µs60.2 µs

patched_take_10k_contiguous_not_patches

encodings/fastlanes/benches/bitpacking_take.rs

-10%

1.2 ms1.4 ms

canonical_into_nullable[(10000, 10, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

+19%

528.8 µs444.6 µs

into_canonical_nullable[(10000, 10, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

+19%

537.4 µs452.3 µs

into_canonical_nullable[(10000, 10, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

+12%

710.5 µs632.3 µs

into_canonical_nullable[(10000, 1, 0.1)]

encodings/fastlanes/benches/canonicalize_bench.rs

+6%

98.7 µs93.4 µs

into_canonical_non_nullable[(10000, 1000, 0.0)]

encodings/fastlanes/benches/canonicalize_bench.rs

+5%

27.7 ms26.4 ms

new_bp_prim_test_between[i32, 2048]

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

+4%

37 µs35.5 µs

chunked_dict_primitive_canonical_into[u64, (1000, 100, 100)]

vortex-array/benches/chunked_dict_builder.rs

+3%

1.2 ms1.1 ms

take_map[(0.1, 1.0)]

vortex-array/benches/take_patches.rs

+2%

3.6 ms3.5 ms

chunked_dict_primitive_into_canonical[f64, (1000, 100, 10)]

vortex-array/benches/chunked_dict_builder.rs

+2%

147 µs144.4 µs

chunked_dict_primitive_canonical_into[u64, (1000, 10, 10)]

vortex-array/benches/chunked_dict_builder.rs

+2%

134.2 µs132.1 µs

Commits

Click on a commit to change the comparison range

Base

develop

238d063

-29.68%

chore: custom kernel launcher API to remove macro

5cd76db

2 days ago

by 0ax1

Home Terms Privacy Docs