claude/row-c17-specialize-constant-arith - Branch - vortex-data/vortex

Specialize Constant for the arithmetic-write fast path

#8002Closed

Comparing

claude/row-c17-specialize-constant-arith

(

7987423

) with

claude/row-c16-arith-write-fast-path

(

224fdab

)

-12%

Regression: 1

Untouched: 1220

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

1221 total

new_alp_prim_test_between[f32, 16384]

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

-12%

103.7 µs118.3 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

take_10_contiguous

encodings/fastlanes/benches/bitpacking_take.rs

+3%

26.5 µs25.8 µs

new_bp_prim_test_between[i16, 2048]

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

+2%

48.6 µs47.9 µs

compress[(1000, 16)]

encodings/runend/benches/run_end_compress.rs

+1%

55.4 µs54.7 µs

decompress[u32, (1000, 16)]

encodings/runend/benches/run_end_compress.rs

+1%

21.6 µs21.4 µs

cuda/runend_100runs/dispatch_u32[100M]

vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda

+1%

844.8 µs837.6 µs

cuda/alp_f32/10%[100M]

vortex-cuda/benches/alp_cuda.rs::benches::benchmark_alp_decode::cuda

+1%

4.5 ms4.5 ms

cuda/bitpacked_patched_u8/unpack/10%[100M]

vortex-cuda/benches/bitpacked_cuda.rs::benches::benchmark_bitunpack_with_patches::cuda

+1%

481.7 µs479.2 µs

cuda/bitpacked_patched_u32/unpack/10%[100M]

vortex-cuda/benches/bitpacked_cuda.rs::benches::benchmark_bitunpack_with_patches::cuda

+1%

1.2 ms1.2 ms

to_arrow_dtype

vortex-array/benches/to_arrow.rs

6.5 µs6.4 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

1.1 ms1.1 ms

cuda/dict_widen_u8_to_u32/dispatch_u32[100M]

vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda

952.3 µs949.2 µs

dict_canonicalize_zipfian[16, 1000]

vortex-array/benches/take_primitive.rs

47.6 µs47.5 µs

take_indices[(10000, 16)]

encodings/runend/benches/run_end_compress.rs

97.5 µs97.2 µs

cuda/dict_nowiden_u32_to_u32/dispatch_u32[100M]

vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda

964.4 µs961.5 µs

cuda/dict_64vals_bp6bw_codes_for_bp6bw_values/dispatch_u32[100M]

vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda

1.1 ms1 ms

cuda/bitpacked_patched_u8/unpack/1%[100M]

vortex-cuda/benches/bitpacked_cuda.rs::benches::benchmark_bitunpack_with_patches::cuda

384.2 µs383.1 µs

take_indices[(10000, 1024)]

encodings/runend/benches/run_end_compress.rs

54.1 µs53.9 µs

runend_compress_u32

vortex/benches/single_encoding_throughput.rs

5 ms5 ms

decompress[u64, (10000, 4)]

encodings/runend/benches/run_end_compress.rs

142 µs141.7 µs

cuda/alp_for_bp_6bw_f32/dispatch_f32[100M]

vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda

1.1 ms1 ms

extend_from_array_non_zctl_overlapping[(1000, 8)]

vortex-array/benches/listview_builder_extend.rs

611.5 µs610.3 µs

filter_powerlaw_by_correlated_runs[1000]

vortex-array/benches/filter_bool.rs

31.3 µs31.2 µs

new_raw_prim_test_between[f32, 2048]

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

33.8 µs33.7 µs

Commits

Click on a commit to change the comparison range

Base

claude/row-c16-arith-write-fast-path

224fdab

-12.39%

Specialize Constant for the arithmetic-write fast path

7987423

3 days ago

by claude

Home Terms Privacy Docs